Add HuggingFaceH4/starcoder2-15b-ift-v5.0 checkpoint
Browse files- README.md +71 -0
- added_tokens.json +4 -0
- all_results.json +14 -0
- config.json +31 -0
- eval_results.json +9 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +651 -0
- runs/Mar08_16-17-47_ip-26-0-163-147/events.out.tfevents.1709915296.ip-26-0-163-147.1763548.0 +3 -0
- runs/Mar08_18-36-38_ip-26-0-168-30/events.out.tfevents.1709923104.ip-26-0-168-30.2820495.0 +3 -0
- runs/Mar08_18-36-38_ip-26-0-168-30/events.out.tfevents.1709936860.ip-26-0-168-30.2820495.1 +3 -0
- runs/Mar08_21-16-43_ip-26-0-167-51/events.out.tfevents.1709932888.ip-26-0-167-51.328029.0 +3 -0
- runs/Mar08_21-16-43_ip-26-0-167-51/events.out.tfevents.1709947427.ip-26-0-167-51.328029.1 +3 -0
- runs/Mar08_21-26-05_ip-26-0-172-252/events.out.tfevents.1709933435.ip-26-0-172-252.2556335.0 +3 -0
- runs/Mar08_21-26-05_ip-26-0-172-252/events.out.tfevents.1709948930.ip-26-0-172-252.2556335.1 +3 -0
- runs/Mar08_21-27-27_ip-26-0-164-18/events.out.tfevents.1709933533.ip-26-0-164-18.2014308.0 +3 -0
- runs/Mar08_21-56-54_ip-26-0-173-121/events.out.tfevents.1709935115.ip-26-0-173-121.311205.0 +3 -0
- runs/Mar08_22-00-45_ip-26-0-160-225/events.out.tfevents.1709935775.ip-26-0-160-225.445184.0 +3 -0
- runs/Mar08_22-00-45_ip-26-0-160-225/events.out.tfevents.1709945594.ip-26-0-160-225.445184.1 +3 -0
- runs/Mar08_22-17-01_ip-26-0-163-58/events.out.tfevents.1709936545.ip-26-0-163-58.306463.0 +3 -0
- runs/Mar08_22-17-01_ip-26-0-163-58/events.out.tfevents.1709941542.ip-26-0-163-58.306463.1 +3 -0
- runs/Mar08_22-18-04_ip-26-0-170-31/events.out.tfevents.1709936621.ip-26-0-170-31.2209735.0 +3 -0
- runs/Mar08_22-18-04_ip-26-0-170-31/events.out.tfevents.1709943158.ip-26-0-170-31.2209735.1 +3 -0
- runs/Mar08_22-30-40_ip-26-0-168-30/events.out.tfevents.1709938809.ip-26-0-168-30.2846469.0 +3 -0
- runs/Mar08_22-30-40_ip-26-0-168-30/events.out.tfevents.1709952568.ip-26-0-168-30.2846469.1 +3 -0
- runs/Mar08_23-28-10_ip-26-0-173-121/events.out.tfevents.1709940599.ip-26-0-173-121.320213.0 +3 -0
- special_tokens_map.json +28 -0
- tokenizer.json +0 -0
- tokenizer_config.json +338 -0
- train_results.json +8 -0
- trainer_state.json +3883 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: bigcode-openrail-m
|
3 |
+
base_model: bigcode/starcoder2-15b
|
4 |
+
tags:
|
5 |
+
- alignment-handbook
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- HuggingFaceH4/airoboros-3.2
|
9 |
+
- HuggingFaceH4/Code-Feedback
|
10 |
+
- HuggingFaceH4/orca-math-word-problems-200k
|
11 |
+
- HuggingFaceH4/SystemChat
|
12 |
+
- HuggingFaceH4/capybara
|
13 |
+
model-index:
|
14 |
+
- name: starcoder2-15b-sft-v5.0
|
15 |
+
results: []
|
16 |
+
---
|
17 |
+
|
18 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
19 |
+
should probably proofread and complete it, then remove this comment. -->
|
20 |
+
|
21 |
+
# starcoder2-15b-sft-v5.0
|
22 |
+
|
23 |
+
This model is a fine-tuned version of [bigcode/starcoder2-15b](https://huggingface.co/bigcode/starcoder2-15b) on the HuggingFaceH4/airoboros-3.2, the HuggingFaceH4/Code-Feedback, the HuggingFaceH4/orca-math-word-problems-200k, the HuggingFaceH4/SystemChat and the HuggingFaceH4/capybara datasets.
|
24 |
+
It achieves the following results on the evaluation set:
|
25 |
+
- Loss: 0.6614
|
26 |
+
|
27 |
+
## Model description
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Intended uses & limitations
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training and evaluation data
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training procedure
|
40 |
+
|
41 |
+
### Training hyperparameters
|
42 |
+
|
43 |
+
The following hyperparameters were used during training:
|
44 |
+
- learning_rate: 2e-05
|
45 |
+
- train_batch_size: 8
|
46 |
+
- eval_batch_size: 8
|
47 |
+
- seed: 42
|
48 |
+
- distributed_type: multi-GPU
|
49 |
+
- num_devices: 16
|
50 |
+
- total_train_batch_size: 128
|
51 |
+
- total_eval_batch_size: 128
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: cosine
|
54 |
+
- lr_scheduler_warmup_ratio: 0.1
|
55 |
+
- num_epochs: 3
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
60 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
61 |
+
| 0.6422 | 1.0 | 910 | 0.6910 |
|
62 |
+
| 0.5701 | 2.0 | 1820 | 0.6639 |
|
63 |
+
| 0.5227 | 3.0 | 2730 | 0.6614 |
|
64 |
+
|
65 |
+
|
66 |
+
### Framework versions
|
67 |
+
|
68 |
+
- Transformers 4.39.0.dev0
|
69 |
+
- Pytorch 2.1.2+cu121
|
70 |
+
- Datasets 2.16.1
|
71 |
+
- Tokenizers 0.15.1
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 49153,
|
3 |
+
"<|im_start|>": 49152
|
4 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.6613607406616211,
|
4 |
+
"eval_runtime": 13.2548,
|
5 |
+
"eval_samples": 3200,
|
6 |
+
"eval_samples_per_second": 103.962,
|
7 |
+
"eval_steps_per_second": 0.83,
|
8 |
+
"perplexity": 1.9374268770613925,
|
9 |
+
"train_loss": 0.6159939037574517,
|
10 |
+
"train_runtime": 13745.4884,
|
11 |
+
"train_samples": 344926,
|
12 |
+
"train_samples_per_second": 25.399,
|
13 |
+
"train_steps_per_second": 0.199
|
14 |
+
}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bigcode/starcoder2-15b",
|
3 |
+
"architectures": [
|
4 |
+
"Starcoder2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"embedding_dropout": 0.1,
|
9 |
+
"eos_token_id": 0,
|
10 |
+
"hidden_act": "gelu_pytorch_tanh",
|
11 |
+
"hidden_size": 6144,
|
12 |
+
"initializer_range": 0.01275,
|
13 |
+
"intermediate_size": 24576,
|
14 |
+
"max_position_embeddings": 16384,
|
15 |
+
"mlp_type": "default",
|
16 |
+
"model_type": "starcoder2",
|
17 |
+
"norm_epsilon": 1e-05,
|
18 |
+
"norm_type": "layer_norm",
|
19 |
+
"num_attention_heads": 48,
|
20 |
+
"num_hidden_layers": 40,
|
21 |
+
"num_key_value_heads": 4,
|
22 |
+
"residual_dropout": 0.1,
|
23 |
+
"rope_theta": 100000,
|
24 |
+
"sliding_window": 4096,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.39.0.dev0",
|
28 |
+
"use_bias": true,
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 49154
|
31 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_loss": 0.6613607406616211,
|
4 |
+
"eval_runtime": 13.2548,
|
5 |
+
"eval_samples": 3200,
|
6 |
+
"eval_samples_per_second": 103.962,
|
7 |
+
"eval_steps_per_second": 0.83,
|
8 |
+
"perplexity": 1.9374268770613925
|
9 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.39.0.dev0"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4d42fbff705dc05edbb65f0ae3f51df701209be99287e4475dbe9399dc6fe18
|
3 |
+
size 4908132312
|
model-00002-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d2e3ca209549ff47ede1f0c26ca18dbc993337298eb2d82caaef7b637b52d43
|
3 |
+
size 4996327240
|
model-00003-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7230487178cdba324781f21e3be5fc6d858b752370c353877074e49c423cf7a
|
3 |
+
size 4983729152
|
model-00004-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab59837a2010f9d57928176bcc8953efa3d372d5e31229b29cdfa5d773eb374e
|
3 |
+
size 4996327312
|
model-00005-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3fea31b72aed8d39bf1adf512f9fba77f05669cface5ccbf12badc06ede4fa3
|
3 |
+
size 4983729152
|
model-00006-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee54a75dde9875e171ccc6ea270d84b97c131b1bfff843e4f3ffa5f0cdc95904
|
3 |
+
size 4996327312
|
model-00007-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dedf79db5b5196be63a2259994515677bc831d8ccd10e9db4b3af671029533a
|
3 |
+
size 2051327128
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,651 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 31915827200
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00007-of-00007.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.bias": "model-00001-of-00007.safetensors",
|
9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
10 |
+
"model.layers.0.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
|
11 |
+
"model.layers.0.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
|
12 |
+
"model.layers.0.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
|
13 |
+
"model.layers.0.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
|
14 |
+
"model.layers.0.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
|
15 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
16 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
17 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
18 |
+
"model.layers.0.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
|
19 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
20 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
21 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
22 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
23 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
24 |
+
"model.layers.1.input_layernorm.bias": "model-00001-of-00007.safetensors",
|
25 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
26 |
+
"model.layers.1.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
|
27 |
+
"model.layers.1.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
|
28 |
+
"model.layers.1.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
|
29 |
+
"model.layers.1.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
|
30 |
+
"model.layers.1.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
|
31 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
32 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
33 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
34 |
+
"model.layers.1.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
|
35 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
36 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
37 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
38 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
39 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
40 |
+
"model.layers.10.input_layernorm.bias": "model-00002-of-00007.safetensors",
|
41 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
42 |
+
"model.layers.10.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
|
43 |
+
"model.layers.10.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
|
44 |
+
"model.layers.10.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
|
45 |
+
"model.layers.10.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
|
46 |
+
"model.layers.10.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
|
47 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
48 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
49 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
50 |
+
"model.layers.10.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
|
51 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
52 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
53 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
54 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
55 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
56 |
+
"model.layers.11.input_layernorm.bias": "model-00002-of-00007.safetensors",
|
57 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
58 |
+
"model.layers.11.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
|
59 |
+
"model.layers.11.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
|
60 |
+
"model.layers.11.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
|
61 |
+
"model.layers.11.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
|
62 |
+
"model.layers.11.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
|
63 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
64 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
65 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
66 |
+
"model.layers.11.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
|
67 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
68 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
69 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
70 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
71 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
72 |
+
"model.layers.12.input_layernorm.bias": "model-00003-of-00007.safetensors",
|
73 |
+
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
74 |
+
"model.layers.12.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
|
75 |
+
"model.layers.12.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
|
76 |
+
"model.layers.12.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
|
77 |
+
"model.layers.12.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
|
78 |
+
"model.layers.12.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
|
79 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
80 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
81 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
82 |
+
"model.layers.12.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
|
83 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
84 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
85 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
86 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
87 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
88 |
+
"model.layers.13.input_layernorm.bias": "model-00003-of-00007.safetensors",
|
89 |
+
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
90 |
+
"model.layers.13.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
|
91 |
+
"model.layers.13.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
|
92 |
+
"model.layers.13.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
|
93 |
+
"model.layers.13.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
|
94 |
+
"model.layers.13.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
|
95 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
96 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
97 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
98 |
+
"model.layers.13.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
|
99 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
100 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
101 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
102 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
103 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
104 |
+
"model.layers.14.input_layernorm.bias": "model-00003-of-00007.safetensors",
|
105 |
+
"model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
106 |
+
"model.layers.14.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
|
107 |
+
"model.layers.14.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
|
108 |
+
"model.layers.14.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
|
109 |
+
"model.layers.14.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
|
110 |
+
"model.layers.14.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
|
111 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
112 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
113 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
114 |
+
"model.layers.14.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
|
115 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
116 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
117 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
118 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
119 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
120 |
+
"model.layers.15.input_layernorm.bias": "model-00003-of-00007.safetensors",
|
121 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
122 |
+
"model.layers.15.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
|
123 |
+
"model.layers.15.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
|
124 |
+
"model.layers.15.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
|
125 |
+
"model.layers.15.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
|
126 |
+
"model.layers.15.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
|
127 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
128 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
129 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
130 |
+
"model.layers.15.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
|
131 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
132 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
133 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
134 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
135 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
136 |
+
"model.layers.16.input_layernorm.bias": "model-00003-of-00007.safetensors",
|
137 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
138 |
+
"model.layers.16.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
|
139 |
+
"model.layers.16.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
|
140 |
+
"model.layers.16.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
|
141 |
+
"model.layers.16.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
|
142 |
+
"model.layers.16.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
|
143 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
144 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
145 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
146 |
+
"model.layers.16.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
|
147 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
148 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
149 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
150 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
151 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
152 |
+
"model.layers.17.input_layernorm.bias": "model-00003-of-00007.safetensors",
|
153 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
154 |
+
"model.layers.17.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
|
155 |
+
"model.layers.17.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
|
156 |
+
"model.layers.17.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
|
157 |
+
"model.layers.17.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
|
158 |
+
"model.layers.17.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
|
159 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
|
160 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
161 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
162 |
+
"model.layers.17.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
|
163 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
164 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
165 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
166 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
167 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
168 |
+
"model.layers.18.input_layernorm.bias": "model-00004-of-00007.safetensors",
|
169 |
+
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
170 |
+
"model.layers.18.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
|
171 |
+
"model.layers.18.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
|
172 |
+
"model.layers.18.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
|
173 |
+
"model.layers.18.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
|
174 |
+
"model.layers.18.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
|
175 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
176 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
|
177 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
178 |
+
"model.layers.18.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
|
179 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
180 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
|
181 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
182 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
|
183 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
184 |
+
"model.layers.19.input_layernorm.bias": "model-00004-of-00007.safetensors",
|
185 |
+
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
186 |
+
"model.layers.19.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
|
187 |
+
"model.layers.19.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
|
188 |
+
"model.layers.19.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
|
189 |
+
"model.layers.19.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
|
190 |
+
"model.layers.19.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
|
191 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
192 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
193 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
194 |
+
"model.layers.19.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
|
195 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
196 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
197 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
198 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
199 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
200 |
+
"model.layers.2.input_layernorm.bias": "model-00001-of-00007.safetensors",
|
201 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
202 |
+
"model.layers.2.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
|
203 |
+
"model.layers.2.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
|
204 |
+
"model.layers.2.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
|
205 |
+
"model.layers.2.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
|
206 |
+
"model.layers.2.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
|
207 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
208 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
209 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
210 |
+
"model.layers.2.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
|
211 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
212 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
213 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
214 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
215 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
216 |
+
"model.layers.20.input_layernorm.bias": "model-00004-of-00007.safetensors",
|
217 |
+
"model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
218 |
+
"model.layers.20.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
|
219 |
+
"model.layers.20.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
|
220 |
+
"model.layers.20.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
|
221 |
+
"model.layers.20.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
|
222 |
+
"model.layers.20.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
|
223 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
224 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
225 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
226 |
+
"model.layers.20.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
|
227 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
228 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
229 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
230 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
231 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
232 |
+
"model.layers.21.input_layernorm.bias": "model-00004-of-00007.safetensors",
|
233 |
+
"model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
234 |
+
"model.layers.21.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
|
235 |
+
"model.layers.21.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
|
236 |
+
"model.layers.21.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
|
237 |
+
"model.layers.21.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
|
238 |
+
"model.layers.21.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
|
239 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
240 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
241 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
242 |
+
"model.layers.21.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
|
243 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
244 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
245 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
246 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
247 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
248 |
+
"model.layers.22.input_layernorm.bias": "model-00004-of-00007.safetensors",
|
249 |
+
"model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
250 |
+
"model.layers.22.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
|
251 |
+
"model.layers.22.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
|
252 |
+
"model.layers.22.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
|
253 |
+
"model.layers.22.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
|
254 |
+
"model.layers.22.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
|
255 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
256 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
257 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
258 |
+
"model.layers.22.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
|
259 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
260 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
261 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
262 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
263 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
264 |
+
"model.layers.23.input_layernorm.bias": "model-00004-of-00007.safetensors",
|
265 |
+
"model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
266 |
+
"model.layers.23.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
|
267 |
+
"model.layers.23.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
|
268 |
+
"model.layers.23.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
|
269 |
+
"model.layers.23.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
|
270 |
+
"model.layers.23.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
|
271 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
272 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
273 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
274 |
+
"model.layers.23.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
|
275 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
276 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
277 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
278 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
279 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
280 |
+
"model.layers.24.input_layernorm.bias": "model-00004-of-00007.safetensors",
|
281 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
282 |
+
"model.layers.24.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
|
283 |
+
"model.layers.24.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
|
284 |
+
"model.layers.24.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
|
285 |
+
"model.layers.24.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
|
286 |
+
"model.layers.24.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
|
287 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
|
288 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
289 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
290 |
+
"model.layers.24.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
|
291 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
292 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
293 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
294 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
295 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
296 |
+
"model.layers.25.input_layernorm.bias": "model-00005-of-00007.safetensors",
|
297 |
+
"model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
298 |
+
"model.layers.25.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
|
299 |
+
"model.layers.25.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
|
300 |
+
"model.layers.25.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
|
301 |
+
"model.layers.25.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
|
302 |
+
"model.layers.25.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
|
303 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
304 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
|
305 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
306 |
+
"model.layers.25.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
|
307 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
308 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
|
309 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
310 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
|
311 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
312 |
+
"model.layers.26.input_layernorm.bias": "model-00005-of-00007.safetensors",
|
313 |
+
"model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
314 |
+
"model.layers.26.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
|
315 |
+
"model.layers.26.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
|
316 |
+
"model.layers.26.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
|
317 |
+
"model.layers.26.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
|
318 |
+
"model.layers.26.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
|
319 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
320 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
321 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
322 |
+
"model.layers.26.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
|
323 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
324 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
325 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
326 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
327 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
328 |
+
"model.layers.27.input_layernorm.bias": "model-00005-of-00007.safetensors",
|
329 |
+
"model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
330 |
+
"model.layers.27.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
|
331 |
+
"model.layers.27.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
|
332 |
+
"model.layers.27.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
|
333 |
+
"model.layers.27.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
|
334 |
+
"model.layers.27.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
|
335 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
336 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
337 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
338 |
+
"model.layers.27.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
|
339 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
340 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
341 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
342 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
343 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
344 |
+
"model.layers.28.input_layernorm.bias": "model-00005-of-00007.safetensors",
|
345 |
+
"model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
346 |
+
"model.layers.28.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
|
347 |
+
"model.layers.28.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
|
348 |
+
"model.layers.28.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
|
349 |
+
"model.layers.28.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
|
350 |
+
"model.layers.28.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
|
351 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
352 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
353 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
354 |
+
"model.layers.28.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
|
355 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
356 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
357 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
358 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
359 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
360 |
+
"model.layers.29.input_layernorm.bias": "model-00005-of-00007.safetensors",
|
361 |
+
"model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
362 |
+
"model.layers.29.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
|
363 |
+
"model.layers.29.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
|
364 |
+
"model.layers.29.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
|
365 |
+
"model.layers.29.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
|
366 |
+
"model.layers.29.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
|
367 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
368 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
369 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
370 |
+
"model.layers.29.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
|
371 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
372 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
373 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
374 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
375 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
376 |
+
"model.layers.3.input_layernorm.bias": "model-00001-of-00007.safetensors",
|
377 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
378 |
+
"model.layers.3.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
|
379 |
+
"model.layers.3.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
|
380 |
+
"model.layers.3.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
|
381 |
+
"model.layers.3.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
|
382 |
+
"model.layers.3.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
|
383 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
384 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
385 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
386 |
+
"model.layers.3.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
|
387 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
388 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
389 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
390 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
391 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
392 |
+
"model.layers.30.input_layernorm.bias": "model-00005-of-00007.safetensors",
|
393 |
+
"model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
394 |
+
"model.layers.30.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
|
395 |
+
"model.layers.30.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
|
396 |
+
"model.layers.30.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
|
397 |
+
"model.layers.30.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
|
398 |
+
"model.layers.30.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
|
399 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
|
400 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
401 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
402 |
+
"model.layers.30.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
|
403 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
404 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
405 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
406 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
407 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
408 |
+
"model.layers.31.input_layernorm.bias": "model-00006-of-00007.safetensors",
|
409 |
+
"model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
410 |
+
"model.layers.31.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
|
411 |
+
"model.layers.31.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
|
412 |
+
"model.layers.31.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
|
413 |
+
"model.layers.31.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
|
414 |
+
"model.layers.31.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
|
415 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
416 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
|
417 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
418 |
+
"model.layers.31.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
|
419 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
420 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
|
421 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
422 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
|
423 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
424 |
+
"model.layers.32.input_layernorm.bias": "model-00006-of-00007.safetensors",
|
425 |
+
"model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
426 |
+
"model.layers.32.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
|
427 |
+
"model.layers.32.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
|
428 |
+
"model.layers.32.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
|
429 |
+
"model.layers.32.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
|
430 |
+
"model.layers.32.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
|
431 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
432 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
433 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
434 |
+
"model.layers.32.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
|
435 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
436 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
437 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
438 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
439 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
440 |
+
"model.layers.33.input_layernorm.bias": "model-00006-of-00007.safetensors",
|
441 |
+
"model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
442 |
+
"model.layers.33.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
|
443 |
+
"model.layers.33.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
|
444 |
+
"model.layers.33.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
|
445 |
+
"model.layers.33.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
|
446 |
+
"model.layers.33.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
|
447 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
448 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
449 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
450 |
+
"model.layers.33.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
|
451 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
452 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
453 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
454 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
455 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
456 |
+
"model.layers.34.input_layernorm.bias": "model-00006-of-00007.safetensors",
|
457 |
+
"model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
458 |
+
"model.layers.34.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
|
459 |
+
"model.layers.34.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
|
460 |
+
"model.layers.34.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
|
461 |
+
"model.layers.34.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
|
462 |
+
"model.layers.34.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
|
463 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
464 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
465 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
466 |
+
"model.layers.34.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
|
467 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
468 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
469 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
470 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
471 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
472 |
+
"model.layers.35.input_layernorm.bias": "model-00006-of-00007.safetensors",
|
473 |
+
"model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
474 |
+
"model.layers.35.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
|
475 |
+
"model.layers.35.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
|
476 |
+
"model.layers.35.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
|
477 |
+
"model.layers.35.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
|
478 |
+
"model.layers.35.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
|
479 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
480 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
481 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
482 |
+
"model.layers.35.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
|
483 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
484 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
485 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
486 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
487 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
488 |
+
"model.layers.36.input_layernorm.bias": "model-00006-of-00007.safetensors",
|
489 |
+
"model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
490 |
+
"model.layers.36.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
|
491 |
+
"model.layers.36.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
|
492 |
+
"model.layers.36.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
|
493 |
+
"model.layers.36.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
|
494 |
+
"model.layers.36.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
|
495 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
496 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
497 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
498 |
+
"model.layers.36.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
|
499 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
500 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
501 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
502 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
503 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
504 |
+
"model.layers.37.input_layernorm.bias": "model-00006-of-00007.safetensors",
|
505 |
+
"model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
506 |
+
"model.layers.37.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
|
507 |
+
"model.layers.37.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
|
508 |
+
"model.layers.37.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
|
509 |
+
"model.layers.37.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
|
510 |
+
"model.layers.37.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
|
511 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
|
512 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
513 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
514 |
+
"model.layers.37.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
|
515 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
516 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
517 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
518 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
519 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
520 |
+
"model.layers.38.input_layernorm.bias": "model-00007-of-00007.safetensors",
|
521 |
+
"model.layers.38.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
522 |
+
"model.layers.38.mlp.c_fc.bias": "model-00007-of-00007.safetensors",
|
523 |
+
"model.layers.38.mlp.c_fc.weight": "model-00007-of-00007.safetensors",
|
524 |
+
"model.layers.38.mlp.c_proj.bias": "model-00007-of-00007.safetensors",
|
525 |
+
"model.layers.38.mlp.c_proj.weight": "model-00007-of-00007.safetensors",
|
526 |
+
"model.layers.38.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
|
527 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
528 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
|
529 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
530 |
+
"model.layers.38.self_attn.o_proj.bias": "model-00007-of-00007.safetensors",
|
531 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
532 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
|
533 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
534 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
|
535 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
536 |
+
"model.layers.39.input_layernorm.bias": "model-00007-of-00007.safetensors",
|
537 |
+
"model.layers.39.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
538 |
+
"model.layers.39.mlp.c_fc.bias": "model-00007-of-00007.safetensors",
|
539 |
+
"model.layers.39.mlp.c_fc.weight": "model-00007-of-00007.safetensors",
|
540 |
+
"model.layers.39.mlp.c_proj.bias": "model-00007-of-00007.safetensors",
|
541 |
+
"model.layers.39.mlp.c_proj.weight": "model-00007-of-00007.safetensors",
|
542 |
+
"model.layers.39.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
|
543 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
|
544 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
|
545 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
546 |
+
"model.layers.39.self_attn.o_proj.bias": "model-00007-of-00007.safetensors",
|
547 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
548 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
|
549 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
550 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
|
551 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
552 |
+
"model.layers.4.input_layernorm.bias": "model-00001-of-00007.safetensors",
|
553 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
|
554 |
+
"model.layers.4.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
|
555 |
+
"model.layers.4.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
|
556 |
+
"model.layers.4.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
|
557 |
+
"model.layers.4.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
|
558 |
+
"model.layers.4.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
|
559 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
|
560 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
561 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
562 |
+
"model.layers.4.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
|
563 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
564 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
565 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
566 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
567 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
568 |
+
"model.layers.5.input_layernorm.bias": "model-00002-of-00007.safetensors",
|
569 |
+
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
570 |
+
"model.layers.5.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
|
571 |
+
"model.layers.5.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
|
572 |
+
"model.layers.5.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
|
573 |
+
"model.layers.5.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
|
574 |
+
"model.layers.5.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
|
575 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
576 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
|
577 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
578 |
+
"model.layers.5.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
|
579 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
580 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
|
581 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
582 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
|
583 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
584 |
+
"model.layers.6.input_layernorm.bias": "model-00002-of-00007.safetensors",
|
585 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
586 |
+
"model.layers.6.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
|
587 |
+
"model.layers.6.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
|
588 |
+
"model.layers.6.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
|
589 |
+
"model.layers.6.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
|
590 |
+
"model.layers.6.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
|
591 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
592 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
593 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
594 |
+
"model.layers.6.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
|
595 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
596 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
597 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
598 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
599 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
600 |
+
"model.layers.7.input_layernorm.bias": "model-00002-of-00007.safetensors",
|
601 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
602 |
+
"model.layers.7.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
|
603 |
+
"model.layers.7.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
|
604 |
+
"model.layers.7.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
|
605 |
+
"model.layers.7.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
|
606 |
+
"model.layers.7.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
|
607 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
608 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
609 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
610 |
+
"model.layers.7.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
|
611 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
612 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
613 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
614 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
615 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
616 |
+
"model.layers.8.input_layernorm.bias": "model-00002-of-00007.safetensors",
|
617 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
618 |
+
"model.layers.8.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
|
619 |
+
"model.layers.8.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
|
620 |
+
"model.layers.8.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
|
621 |
+
"model.layers.8.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
|
622 |
+
"model.layers.8.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
|
623 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
624 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
625 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
626 |
+
"model.layers.8.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
|
627 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
628 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
629 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
630 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
631 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
632 |
+
"model.layers.9.input_layernorm.bias": "model-00002-of-00007.safetensors",
|
633 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
634 |
+
"model.layers.9.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
|
635 |
+
"model.layers.9.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
|
636 |
+
"model.layers.9.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
|
637 |
+
"model.layers.9.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
|
638 |
+
"model.layers.9.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
|
639 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
|
640 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
|
641 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
642 |
+
"model.layers.9.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
|
643 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
644 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
|
645 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
646 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
|
647 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
648 |
+
"model.norm.bias": "model-00007-of-00007.safetensors",
|
649 |
+
"model.norm.weight": "model-00007-of-00007.safetensors"
|
650 |
+
}
|
651 |
+
}
|
runs/Mar08_16-17-47_ip-26-0-163-147/events.out.tfevents.1709915296.ip-26-0-163-147.1763548.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f24061e05cb68d6656fbeb9eb97ee71ee770a76a889dd2de54d31416ab4be7fb
|
3 |
+
size 48612
|
runs/Mar08_18-36-38_ip-26-0-168-30/events.out.tfevents.1709923104.ip-26-0-168-30.2820495.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a128747e9ca38ebb9f652d6bfcc35609a3704100ee7136628845688db499ca8
|
3 |
+
size 121669
|
runs/Mar08_18-36-38_ip-26-0-168-30/events.out.tfevents.1709936860.ip-26-0-168-30.2820495.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fc59d04e0191824a5384f445688fada1eb5c0d96b64d6cf16f987ea3a59c036
|
3 |
+
size 359
|
runs/Mar08_21-16-43_ip-26-0-167-51/events.out.tfevents.1709932888.ip-26-0-167-51.328029.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e720988e253cc7002ac1208eb083ffc6ea48b692b88c73942a5eef1316c567e7
|
3 |
+
size 121675
|
runs/Mar08_21-16-43_ip-26-0-167-51/events.out.tfevents.1709947427.ip-26-0-167-51.328029.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3700a1edbdcdc5461f727c9d730c803256940d83832e91f12f86fb66eefdfbb4
|
3 |
+
size 359
|
runs/Mar08_21-26-05_ip-26-0-172-252/events.out.tfevents.1709933435.ip-26-0-172-252.2556335.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47a3a24f07c116fd409201790c225ff8683a1873000482bb3a6f9fecdf279b69
|
3 |
+
size 121676
|
runs/Mar08_21-26-05_ip-26-0-172-252/events.out.tfevents.1709948930.ip-26-0-172-252.2556335.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7e3d2bfe0d255a910f40f3de7b9741ee01d4bae81abd095b372e859438a7591
|
3 |
+
size 359
|
runs/Mar08_21-27-27_ip-26-0-164-18/events.out.tfevents.1709933533.ip-26-0-164-18.2014308.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3724ac8cf023d7f9cf0d60367c2b56665b4cb7965c5d71ac7b6f01b68d6c881
|
3 |
+
size 6851
|
runs/Mar08_21-56-54_ip-26-0-173-121/events.out.tfevents.1709935115.ip-26-0-173-121.311205.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:732012a5b451b4dc3c09e3f9e6da60d77431dc2e6bdb26f517ce9996490549a6
|
3 |
+
size 43705
|
runs/Mar08_22-00-45_ip-26-0-160-225/events.out.tfevents.1709935775.ip-26-0-160-225.445184.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8624fdfb6f00df7fe679aec6f633f7525560285ff2c730f99b7709c2ea584328
|
3 |
+
size 88121
|
runs/Mar08_22-00-45_ip-26-0-160-225/events.out.tfevents.1709945594.ip-26-0-160-225.445184.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cd37bef74b6698bfd2641bc8aaa9eed0c625d9397c91722a24410999170c0cd
|
3 |
+
size 359
|
runs/Mar08_22-17-01_ip-26-0-163-58/events.out.tfevents.1709936545.ip-26-0-163-58.306463.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac2c8cab80a21f3cf0c981a8985a7b4d6625f4f4a0ff7430e7de7fd20e95adf4
|
3 |
+
size 47819
|
runs/Mar08_22-17-01_ip-26-0-163-58/events.out.tfevents.1709941542.ip-26-0-163-58.306463.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97b0f1a101a4b7977d1de0df75343f7c71f396cdf2c49560e3d1a4eda4b1326d
|
3 |
+
size 359
|
runs/Mar08_22-18-04_ip-26-0-170-31/events.out.tfevents.1709936621.ip-26-0-170-31.2209735.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec0fb10f88bfb5df46fb61c7d31ec283bebd3759d9aa8e808f0762220382f510
|
3 |
+
size 61112
|
runs/Mar08_22-18-04_ip-26-0-170-31/events.out.tfevents.1709943158.ip-26-0-170-31.2209735.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b4fdb51d0bd9d9cd85bf1f5aac72cbc0479429be30b8588e9af2b0e44b9969e
|
3 |
+
size 359
|
runs/Mar08_22-30-40_ip-26-0-168-30/events.out.tfevents.1709938809.ip-26-0-168-30.2846469.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79eacd641094ccd84cdd1f6ba319a33f2fa7d14a1e3486054869e0f7f15414bc
|
3 |
+
size 121669
|
runs/Mar08_22-30-40_ip-26-0-168-30/events.out.tfevents.1709952568.ip-26-0-168-30.2846469.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f09c606bb91a6cfd91a47ea08860441f57e4769fc0e2ee45db23322832e1b41
|
3 |
+
size 359
|
runs/Mar08_23-28-10_ip-26-0-173-121/events.out.tfevents.1709940599.ip-26-0-173-121.320213.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e5501f78dae58ae3d318b6de03478ef93ffa5e11b9c1a23e2e4f0e42bec0df9
|
3 |
+
size 43705
|
special_tokens_map.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|im_start|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|im_end|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": "<|im_start|>",
|
19 |
+
"eos_token": "<|im_end|>",
|
20 |
+
"pad_token": "<|im_end|>",
|
21 |
+
"unk_token": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
}
|
28 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,338 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<fim_prefix>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<fim_middle>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<fim_suffix>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<fim_pad>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"5": {
|
45 |
+
"content": "<repo_name>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"6": {
|
53 |
+
"content": "<file_sep>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"7": {
|
61 |
+
"content": "<issue_start>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"8": {
|
69 |
+
"content": "<issue_comment>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"9": {
|
77 |
+
"content": "<issue_closed>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"10": {
|
85 |
+
"content": "<jupyter_start>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"11": {
|
93 |
+
"content": "<jupyter_text>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"12": {
|
101 |
+
"content": "<jupyter_code>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"13": {
|
109 |
+
"content": "<jupyter_output>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"14": {
|
117 |
+
"content": "<jupyter_script>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"15": {
|
125 |
+
"content": "<empty_output>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"16": {
|
133 |
+
"content": "<code_to_intermediate>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"17": {
|
141 |
+
"content": "<intermediate_to_code>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"18": {
|
149 |
+
"content": "<pr>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"19": {
|
157 |
+
"content": "<pr_status>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"20": {
|
165 |
+
"content": "<pr_is_merged>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"21": {
|
173 |
+
"content": "<pr_base>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"22": {
|
181 |
+
"content": "<pr_file>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"23": {
|
189 |
+
"content": "<pr_base_code>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"24": {
|
197 |
+
"content": "<pr_diff>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"25": {
|
205 |
+
"content": "<pr_diff_hunk>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"26": {
|
213 |
+
"content": "<pr_comment>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"27": {
|
221 |
+
"content": "<pr_event_id>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"28": {
|
229 |
+
"content": "<pr_review>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"29": {
|
237 |
+
"content": "<pr_review_state>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"30": {
|
245 |
+
"content": "<pr_review_comment>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"31": {
|
253 |
+
"content": "<pr_in_reply_to_review_id>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"32": {
|
261 |
+
"content": "<pr_in_reply_to_comment_id>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"33": {
|
269 |
+
"content": "<pr_diff_hunk_comment_line>",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"34": {
|
277 |
+
"content": "<NAME>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"35": {
|
285 |
+
"content": "<EMAIL>",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"36": {
|
293 |
+
"content": "<KEY>",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"37": {
|
301 |
+
"content": "<PASSWORD>",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"49152": {
|
309 |
+
"content": "<|im_start|>",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"49153": {
|
317 |
+
"content": "<|im_end|>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
}
|
324 |
+
},
|
325 |
+
"additional_special_tokens": [
|
326 |
+
"<|im_start|>",
|
327 |
+
"<|im_end|>"
|
328 |
+
],
|
329 |
+
"bos_token": "<|im_start|>",
|
330 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
331 |
+
"clean_up_tokenization_spaces": true,
|
332 |
+
"eos_token": "<|im_end|>",
|
333 |
+
"model_max_length": 2048,
|
334 |
+
"pad_token": "<|im_end|>",
|
335 |
+
"tokenizer_class": "GPT2Tokenizer",
|
336 |
+
"unk_token": "<|endoftext|>",
|
337 |
+
"vocab_size": 49152
|
338 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"train_loss": 0.6159939037574517,
|
4 |
+
"train_runtime": 13745.4884,
|
5 |
+
"train_samples": 344926,
|
6 |
+
"train_samples_per_second": 25.399,
|
7 |
+
"train_steps_per_second": 0.199
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3883 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2730,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"grad_norm": 2.5403712464892836,
|
14 |
+
"learning_rate": 7.326007326007327e-08,
|
15 |
+
"loss": 1.379,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.01,
|
20 |
+
"grad_norm": 2.5059454164116177,
|
21 |
+
"learning_rate": 3.6630036630036635e-07,
|
22 |
+
"loss": 1.411,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.01,
|
27 |
+
"grad_norm": 2.403039830631443,
|
28 |
+
"learning_rate": 7.326007326007327e-07,
|
29 |
+
"loss": 1.3904,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.02,
|
34 |
+
"grad_norm": 2.187796179583603,
|
35 |
+
"learning_rate": 1.098901098901099e-06,
|
36 |
+
"loss": 1.3698,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.02,
|
41 |
+
"grad_norm": 1.4489435205825498,
|
42 |
+
"learning_rate": 1.4652014652014654e-06,
|
43 |
+
"loss": 1.2609,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.03,
|
48 |
+
"grad_norm": 1.483113856101743,
|
49 |
+
"learning_rate": 1.8315018315018316e-06,
|
50 |
+
"loss": 1.1341,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.03,
|
55 |
+
"grad_norm": 0.7051067484479403,
|
56 |
+
"learning_rate": 2.197802197802198e-06,
|
57 |
+
"loss": 1.0478,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.04,
|
62 |
+
"grad_norm": 0.7254079611231652,
|
63 |
+
"learning_rate": 2.564102564102564e-06,
|
64 |
+
"loss": 1.0312,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.04,
|
69 |
+
"grad_norm": 0.6389491910662315,
|
70 |
+
"learning_rate": 2.930402930402931e-06,
|
71 |
+
"loss": 0.9897,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.05,
|
76 |
+
"grad_norm": 0.500844994643637,
|
77 |
+
"learning_rate": 3.2967032967032968e-06,
|
78 |
+
"loss": 0.9549,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.05,
|
83 |
+
"grad_norm": 0.4201833928940666,
|
84 |
+
"learning_rate": 3.663003663003663e-06,
|
85 |
+
"loss": 0.9373,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.06,
|
90 |
+
"grad_norm": 0.370974019020061,
|
91 |
+
"learning_rate": 4.0293040293040296e-06,
|
92 |
+
"loss": 0.9118,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.07,
|
97 |
+
"grad_norm": 0.34743939582124356,
|
98 |
+
"learning_rate": 4.395604395604396e-06,
|
99 |
+
"loss": 0.8832,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.07,
|
104 |
+
"grad_norm": 0.30550288282826443,
|
105 |
+
"learning_rate": 4.761904761904762e-06,
|
106 |
+
"loss": 0.8905,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.08,
|
111 |
+
"grad_norm": 0.3877890435103539,
|
112 |
+
"learning_rate": 5.128205128205128e-06,
|
113 |
+
"loss": 0.8745,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.08,
|
118 |
+
"grad_norm": 0.4090389705350457,
|
119 |
+
"learning_rate": 5.494505494505495e-06,
|
120 |
+
"loss": 0.869,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.09,
|
125 |
+
"grad_norm": 0.28471599620620913,
|
126 |
+
"learning_rate": 5.860805860805862e-06,
|
127 |
+
"loss": 0.8701,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.09,
|
132 |
+
"grad_norm": 0.2835464196942085,
|
133 |
+
"learning_rate": 6.227106227106228e-06,
|
134 |
+
"loss": 0.8566,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.1,
|
139 |
+
"grad_norm": 0.3339230231336609,
|
140 |
+
"learning_rate": 6.5934065934065935e-06,
|
141 |
+
"loss": 0.8926,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.1,
|
146 |
+
"grad_norm": 0.26409030663411054,
|
147 |
+
"learning_rate": 6.95970695970696e-06,
|
148 |
+
"loss": 0.8639,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.11,
|
153 |
+
"grad_norm": 0.2548657900119433,
|
154 |
+
"learning_rate": 7.326007326007326e-06,
|
155 |
+
"loss": 0.8574,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.12,
|
160 |
+
"grad_norm": 0.33583619074613247,
|
161 |
+
"learning_rate": 7.692307692307694e-06,
|
162 |
+
"loss": 0.8371,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.12,
|
167 |
+
"grad_norm": 0.26284318740686946,
|
168 |
+
"learning_rate": 8.058608058608059e-06,
|
169 |
+
"loss": 0.8209,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.13,
|
174 |
+
"grad_norm": 0.27047354400674645,
|
175 |
+
"learning_rate": 8.424908424908426e-06,
|
176 |
+
"loss": 0.8125,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.13,
|
181 |
+
"grad_norm": 0.25311492465959046,
|
182 |
+
"learning_rate": 8.791208791208792e-06,
|
183 |
+
"loss": 0.8371,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.14,
|
188 |
+
"grad_norm": 0.27273984018778547,
|
189 |
+
"learning_rate": 9.157509157509158e-06,
|
190 |
+
"loss": 0.8361,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.14,
|
195 |
+
"grad_norm": 0.2789308175031694,
|
196 |
+
"learning_rate": 9.523809523809525e-06,
|
197 |
+
"loss": 0.7995,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.15,
|
202 |
+
"grad_norm": 0.26030914277390094,
|
203 |
+
"learning_rate": 9.890109890109892e-06,
|
204 |
+
"loss": 0.8137,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.15,
|
209 |
+
"grad_norm": 0.8625694710794981,
|
210 |
+
"learning_rate": 1.0256410256410256e-05,
|
211 |
+
"loss": 0.7968,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.16,
|
216 |
+
"grad_norm": 0.26526694267370393,
|
217 |
+
"learning_rate": 1.0622710622710623e-05,
|
218 |
+
"loss": 0.8011,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.16,
|
223 |
+
"grad_norm": 0.2786629865850713,
|
224 |
+
"learning_rate": 1.098901098901099e-05,
|
225 |
+
"loss": 0.7944,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.17,
|
230 |
+
"grad_norm": 0.2547160983307644,
|
231 |
+
"learning_rate": 1.1355311355311356e-05,
|
232 |
+
"loss": 0.8072,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.18,
|
237 |
+
"grad_norm": 0.252471949121061,
|
238 |
+
"learning_rate": 1.1721611721611723e-05,
|
239 |
+
"loss": 0.7941,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.18,
|
244 |
+
"grad_norm": 0.25858945532947464,
|
245 |
+
"learning_rate": 1.2087912087912089e-05,
|
246 |
+
"loss": 0.7951,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.19,
|
251 |
+
"grad_norm": 0.247980244139678,
|
252 |
+
"learning_rate": 1.2454212454212456e-05,
|
253 |
+
"loss": 0.7858,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.19,
|
258 |
+
"grad_norm": 0.255903929999623,
|
259 |
+
"learning_rate": 1.2820512820512823e-05,
|
260 |
+
"loss": 0.7878,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.2,
|
265 |
+
"grad_norm": 0.6019780019252425,
|
266 |
+
"learning_rate": 1.3186813186813187e-05,
|
267 |
+
"loss": 0.7795,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.2,
|
272 |
+
"grad_norm": 0.27779059252699495,
|
273 |
+
"learning_rate": 1.3553113553113554e-05,
|
274 |
+
"loss": 0.7754,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.21,
|
279 |
+
"grad_norm": 0.2710280200562755,
|
280 |
+
"learning_rate": 1.391941391941392e-05,
|
281 |
+
"loss": 0.7855,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.21,
|
286 |
+
"grad_norm": 0.2743116770469599,
|
287 |
+
"learning_rate": 1.4285714285714287e-05,
|
288 |
+
"loss": 0.7565,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.22,
|
293 |
+
"grad_norm": 0.26037793315040886,
|
294 |
+
"learning_rate": 1.4652014652014653e-05,
|
295 |
+
"loss": 0.7726,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.23,
|
300 |
+
"grad_norm": 0.26090200965795596,
|
301 |
+
"learning_rate": 1.501831501831502e-05,
|
302 |
+
"loss": 0.7653,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.23,
|
307 |
+
"grad_norm": 0.2632394726032374,
|
308 |
+
"learning_rate": 1.5384615384615387e-05,
|
309 |
+
"loss": 0.777,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.24,
|
314 |
+
"grad_norm": 0.2540381175124688,
|
315 |
+
"learning_rate": 1.575091575091575e-05,
|
316 |
+
"loss": 0.7433,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.24,
|
321 |
+
"grad_norm": 0.2627604876525692,
|
322 |
+
"learning_rate": 1.6117216117216118e-05,
|
323 |
+
"loss": 0.7597,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.25,
|
328 |
+
"grad_norm": 0.2651216093866056,
|
329 |
+
"learning_rate": 1.6483516483516486e-05,
|
330 |
+
"loss": 0.7609,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.25,
|
335 |
+
"grad_norm": 0.24401238946000964,
|
336 |
+
"learning_rate": 1.6849816849816853e-05,
|
337 |
+
"loss": 0.7469,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.26,
|
342 |
+
"grad_norm": 0.2547534354636469,
|
343 |
+
"learning_rate": 1.721611721611722e-05,
|
344 |
+
"loss": 0.7641,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.26,
|
349 |
+
"grad_norm": 0.24893607597108447,
|
350 |
+
"learning_rate": 1.7582417582417584e-05,
|
351 |
+
"loss": 0.7323,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.27,
|
356 |
+
"grad_norm": 0.2530974475033568,
|
357 |
+
"learning_rate": 1.794871794871795e-05,
|
358 |
+
"loss": 0.7533,
|
359 |
+
"step": 245
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.27,
|
363 |
+
"grad_norm": 0.2733773460887857,
|
364 |
+
"learning_rate": 1.8315018315018315e-05,
|
365 |
+
"loss": 0.7538,
|
366 |
+
"step": 250
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.28,
|
370 |
+
"grad_norm": 0.27130243796420767,
|
371 |
+
"learning_rate": 1.8681318681318682e-05,
|
372 |
+
"loss": 0.7665,
|
373 |
+
"step": 255
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.29,
|
377 |
+
"grad_norm": 0.25889603349835133,
|
378 |
+
"learning_rate": 1.904761904761905e-05,
|
379 |
+
"loss": 0.737,
|
380 |
+
"step": 260
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.29,
|
384 |
+
"grad_norm": 0.2758988715664599,
|
385 |
+
"learning_rate": 1.9413919413919417e-05,
|
386 |
+
"loss": 0.7587,
|
387 |
+
"step": 265
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.3,
|
391 |
+
"grad_norm": 0.24591163232882832,
|
392 |
+
"learning_rate": 1.9780219780219784e-05,
|
393 |
+
"loss": 0.7503,
|
394 |
+
"step": 270
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.3,
|
398 |
+
"grad_norm": 0.29213859652031626,
|
399 |
+
"learning_rate": 1.9999967302150437e-05,
|
400 |
+
"loss": 0.7544,
|
401 |
+
"step": 275
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.31,
|
405 |
+
"grad_norm": 0.23841997418474895,
|
406 |
+
"learning_rate": 1.9999599453798523e-05,
|
407 |
+
"loss": 0.738,
|
408 |
+
"step": 280
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.31,
|
412 |
+
"grad_norm": 0.23103339591842176,
|
413 |
+
"learning_rate": 1.9998822899867633e-05,
|
414 |
+
"loss": 0.7316,
|
415 |
+
"step": 285
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.32,
|
419 |
+
"grad_norm": 0.24038013908936962,
|
420 |
+
"learning_rate": 1.9997637672097222e-05,
|
421 |
+
"loss": 0.7202,
|
422 |
+
"step": 290
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.32,
|
426 |
+
"grad_norm": 0.24246381579537735,
|
427 |
+
"learning_rate": 1.9996043818930153e-05,
|
428 |
+
"loss": 0.7463,
|
429 |
+
"step": 295
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.33,
|
433 |
+
"grad_norm": 0.24527189059683477,
|
434 |
+
"learning_rate": 1.9994041405510705e-05,
|
435 |
+
"loss": 0.755,
|
436 |
+
"step": 300
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.34,
|
440 |
+
"grad_norm": 0.24371499098074792,
|
441 |
+
"learning_rate": 1.999163051368191e-05,
|
442 |
+
"loss": 0.7599,
|
443 |
+
"step": 305
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.34,
|
447 |
+
"grad_norm": 0.2575400741876107,
|
448 |
+
"learning_rate": 1.9988811241982206e-05,
|
449 |
+
"loss": 0.7443,
|
450 |
+
"step": 310
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.35,
|
454 |
+
"grad_norm": 0.2404592716601957,
|
455 |
+
"learning_rate": 1.9985583705641418e-05,
|
456 |
+
"loss": 0.7327,
|
457 |
+
"step": 315
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.35,
|
461 |
+
"grad_norm": 0.24637921462827092,
|
462 |
+
"learning_rate": 1.9981948036576045e-05,
|
463 |
+
"loss": 0.7339,
|
464 |
+
"step": 320
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.36,
|
468 |
+
"grad_norm": 0.24681007900489016,
|
469 |
+
"learning_rate": 1.997790438338385e-05,
|
470 |
+
"loss": 0.7265,
|
471 |
+
"step": 325
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.36,
|
475 |
+
"grad_norm": 0.2690257655867855,
|
476 |
+
"learning_rate": 1.997345291133783e-05,
|
477 |
+
"loss": 0.7232,
|
478 |
+
"step": 330
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.37,
|
482 |
+
"grad_norm": 0.2534124946734991,
|
483 |
+
"learning_rate": 1.9968593802379405e-05,
|
484 |
+
"loss": 0.7327,
|
485 |
+
"step": 335
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.37,
|
489 |
+
"grad_norm": 0.23796973039683816,
|
490 |
+
"learning_rate": 1.9963327255111033e-05,
|
491 |
+
"loss": 0.7218,
|
492 |
+
"step": 340
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.38,
|
496 |
+
"grad_norm": 0.23546876853519053,
|
497 |
+
"learning_rate": 1.9957653484788054e-05,
|
498 |
+
"loss": 0.7291,
|
499 |
+
"step": 345
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.38,
|
503 |
+
"grad_norm": 0.2629306598176605,
|
504 |
+
"learning_rate": 1.9951572723309918e-05,
|
505 |
+
"loss": 0.7177,
|
506 |
+
"step": 350
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.39,
|
510 |
+
"grad_norm": 0.2392128886783249,
|
511 |
+
"learning_rate": 1.99450852192107e-05,
|
512 |
+
"loss": 0.7082,
|
513 |
+
"step": 355
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.4,
|
517 |
+
"grad_norm": 0.23159963577625967,
|
518 |
+
"learning_rate": 1.9938191237648924e-05,
|
519 |
+
"loss": 0.7031,
|
520 |
+
"step": 360
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.4,
|
524 |
+
"grad_norm": 0.2522691194103305,
|
525 |
+
"learning_rate": 1.9930891060396757e-05,
|
526 |
+
"loss": 0.7094,
|
527 |
+
"step": 365
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.41,
|
531 |
+
"grad_norm": 0.2708112490882325,
|
532 |
+
"learning_rate": 1.992318498582846e-05,
|
533 |
+
"loss": 0.7201,
|
534 |
+
"step": 370
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.41,
|
538 |
+
"grad_norm": 0.2293891910969228,
|
539 |
+
"learning_rate": 1.9915073328908217e-05,
|
540 |
+
"loss": 0.7144,
|
541 |
+
"step": 375
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.42,
|
545 |
+
"grad_norm": 0.25206778778834,
|
546 |
+
"learning_rate": 1.9906556421177256e-05,
|
547 |
+
"loss": 0.7234,
|
548 |
+
"step": 380
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.42,
|
552 |
+
"grad_norm": 0.2518785514497742,
|
553 |
+
"learning_rate": 1.989763461074029e-05,
|
554 |
+
"loss": 0.7141,
|
555 |
+
"step": 385
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.43,
|
559 |
+
"grad_norm": 0.2378420502334953,
|
560 |
+
"learning_rate": 1.9888308262251286e-05,
|
561 |
+
"loss": 0.7231,
|
562 |
+
"step": 390
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.43,
|
566 |
+
"grad_norm": 0.24009865726485224,
|
567 |
+
"learning_rate": 1.987857775689859e-05,
|
568 |
+
"loss": 0.7187,
|
569 |
+
"step": 395
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.44,
|
573 |
+
"grad_norm": 0.28274675300361035,
|
574 |
+
"learning_rate": 1.9868443492389307e-05,
|
575 |
+
"loss": 0.7044,
|
576 |
+
"step": 400
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.45,
|
580 |
+
"grad_norm": 0.22963475241854425,
|
581 |
+
"learning_rate": 1.985790588293308e-05,
|
582 |
+
"loss": 0.7104,
|
583 |
+
"step": 405
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.45,
|
587 |
+
"grad_norm": 0.2377445508195736,
|
588 |
+
"learning_rate": 1.9846965359225127e-05,
|
589 |
+
"loss": 0.6946,
|
590 |
+
"step": 410
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.46,
|
594 |
+
"grad_norm": 0.2608944217378828,
|
595 |
+
"learning_rate": 1.9835622368428673e-05,
|
596 |
+
"loss": 0.7113,
|
597 |
+
"step": 415
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.46,
|
601 |
+
"grad_norm": 0.24157694006779415,
|
602 |
+
"learning_rate": 1.9823877374156647e-05,
|
603 |
+
"loss": 0.698,
|
604 |
+
"step": 420
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.47,
|
608 |
+
"grad_norm": 0.23398315907950198,
|
609 |
+
"learning_rate": 1.9811730856452754e-05,
|
610 |
+
"loss": 0.7257,
|
611 |
+
"step": 425
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.47,
|
615 |
+
"grad_norm": 0.23894709403347192,
|
616 |
+
"learning_rate": 1.9799183311771823e-05,
|
617 |
+
"loss": 0.7184,
|
618 |
+
"step": 430
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.48,
|
622 |
+
"grad_norm": 0.23431405547670192,
|
623 |
+
"learning_rate": 1.9786235252959555e-05,
|
624 |
+
"loss": 0.7128,
|
625 |
+
"step": 435
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.48,
|
629 |
+
"grad_norm": 0.2376569203749501,
|
630 |
+
"learning_rate": 1.977288720923153e-05,
|
631 |
+
"loss": 0.7203,
|
632 |
+
"step": 440
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.49,
|
636 |
+
"grad_norm": 0.23231143839603255,
|
637 |
+
"learning_rate": 1.9759139726151597e-05,
|
638 |
+
"loss": 0.7082,
|
639 |
+
"step": 445
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.49,
|
643 |
+
"grad_norm": 0.22602078925455668,
|
644 |
+
"learning_rate": 1.9744993365609563e-05,
|
645 |
+
"loss": 0.6944,
|
646 |
+
"step": 450
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.5,
|
650 |
+
"grad_norm": 0.22861362046539935,
|
651 |
+
"learning_rate": 1.973044870579824e-05,
|
652 |
+
"loss": 0.698,
|
653 |
+
"step": 455
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.51,
|
657 |
+
"grad_norm": 0.24188463913379904,
|
658 |
+
"learning_rate": 1.9715506341189795e-05,
|
659 |
+
"loss": 0.7015,
|
660 |
+
"step": 460
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.51,
|
664 |
+
"grad_norm": 0.2327706520398592,
|
665 |
+
"learning_rate": 1.970016688251147e-05,
|
666 |
+
"loss": 0.7054,
|
667 |
+
"step": 465
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.52,
|
671 |
+
"grad_norm": 0.2298533583392459,
|
672 |
+
"learning_rate": 1.9684430956720613e-05,
|
673 |
+
"loss": 0.7005,
|
674 |
+
"step": 470
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.52,
|
678 |
+
"grad_norm": 0.23290007131084822,
|
679 |
+
"learning_rate": 1.966829920697905e-05,
|
680 |
+
"loss": 0.7098,
|
681 |
+
"step": 475
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.53,
|
685 |
+
"grad_norm": 0.23281363580583736,
|
686 |
+
"learning_rate": 1.9651772292626804e-05,
|
687 |
+
"loss": 0.6818,
|
688 |
+
"step": 480
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.53,
|
692 |
+
"grad_norm": 0.23817560008326671,
|
693 |
+
"learning_rate": 1.963485088915514e-05,
|
694 |
+
"loss": 0.7088,
|
695 |
+
"step": 485
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.54,
|
699 |
+
"grad_norm": 0.2350735880544215,
|
700 |
+
"learning_rate": 1.961753568817896e-05,
|
701 |
+
"loss": 0.7066,
|
702 |
+
"step": 490
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.54,
|
706 |
+
"grad_norm": 0.23884064719455786,
|
707 |
+
"learning_rate": 1.959982739740854e-05,
|
708 |
+
"loss": 0.7042,
|
709 |
+
"step": 495
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.55,
|
713 |
+
"grad_norm": 0.21790596438572063,
|
714 |
+
"learning_rate": 1.9581726740620585e-05,
|
715 |
+
"loss": 0.6757,
|
716 |
+
"step": 500
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.55,
|
720 |
+
"grad_norm": 0.23917884378106077,
|
721 |
+
"learning_rate": 1.9563234457628678e-05,
|
722 |
+
"loss": 0.6921,
|
723 |
+
"step": 505
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.56,
|
727 |
+
"grad_norm": 0.2399642009348881,
|
728 |
+
"learning_rate": 1.954435130425301e-05,
|
729 |
+
"loss": 0.7047,
|
730 |
+
"step": 510
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.57,
|
734 |
+
"grad_norm": 0.23880300515157055,
|
735 |
+
"learning_rate": 1.952507805228951e-05,
|
736 |
+
"loss": 0.6884,
|
737 |
+
"step": 515
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.57,
|
741 |
+
"grad_norm": 0.23179275898540247,
|
742 |
+
"learning_rate": 1.9505415489478293e-05,
|
743 |
+
"loss": 0.6932,
|
744 |
+
"step": 520
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.58,
|
748 |
+
"grad_norm": 0.2216104142333809,
|
749 |
+
"learning_rate": 1.9485364419471454e-05,
|
750 |
+
"loss": 0.6728,
|
751 |
+
"step": 525
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.58,
|
755 |
+
"grad_norm": 0.22858244743422157,
|
756 |
+
"learning_rate": 1.9464925661800247e-05,
|
757 |
+
"loss": 0.6809,
|
758 |
+
"step": 530
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.59,
|
762 |
+
"grad_norm": 0.22424934505435848,
|
763 |
+
"learning_rate": 1.9444100051841556e-05,
|
764 |
+
"loss": 0.6967,
|
765 |
+
"step": 535
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.59,
|
769 |
+
"grad_norm": 0.2895129667800956,
|
770 |
+
"learning_rate": 1.9422888440783773e-05,
|
771 |
+
"loss": 0.6989,
|
772 |
+
"step": 540
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.6,
|
776 |
+
"grad_norm": 0.240457298966355,
|
777 |
+
"learning_rate": 1.9401291695592e-05,
|
778 |
+
"loss": 0.6818,
|
779 |
+
"step": 545
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.6,
|
783 |
+
"grad_norm": 0.22825665925272676,
|
784 |
+
"learning_rate": 1.9379310698972618e-05,
|
785 |
+
"loss": 0.6922,
|
786 |
+
"step": 550
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.61,
|
790 |
+
"grad_norm": 0.2172530625853638,
|
791 |
+
"learning_rate": 1.935694634933721e-05,
|
792 |
+
"loss": 0.6627,
|
793 |
+
"step": 555
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.62,
|
797 |
+
"grad_norm": 0.22221082939742373,
|
798 |
+
"learning_rate": 1.933419956076584e-05,
|
799 |
+
"loss": 0.6744,
|
800 |
+
"step": 560
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.62,
|
804 |
+
"grad_norm": 0.2264067795562855,
|
805 |
+
"learning_rate": 1.9311071262969675e-05,
|
806 |
+
"loss": 0.6641,
|
807 |
+
"step": 565
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.63,
|
811 |
+
"grad_norm": 0.2254067456859091,
|
812 |
+
"learning_rate": 1.9287562401253023e-05,
|
813 |
+
"loss": 0.6892,
|
814 |
+
"step": 570
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.63,
|
818 |
+
"grad_norm": 0.2370414298818578,
|
819 |
+
"learning_rate": 1.9263673936474662e-05,
|
820 |
+
"loss": 0.6779,
|
821 |
+
"step": 575
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.64,
|
825 |
+
"grad_norm": 0.22087990811265876,
|
826 |
+
"learning_rate": 1.9239406845008583e-05,
|
827 |
+
"loss": 0.6805,
|
828 |
+
"step": 580
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.64,
|
832 |
+
"grad_norm": 0.22405579155571978,
|
833 |
+
"learning_rate": 1.921476211870408e-05,
|
834 |
+
"loss": 0.6661,
|
835 |
+
"step": 585
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.65,
|
839 |
+
"grad_norm": 0.22938270799667376,
|
840 |
+
"learning_rate": 1.918974076484521e-05,
|
841 |
+
"loss": 0.6773,
|
842 |
+
"step": 590
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.65,
|
846 |
+
"grad_norm": 0.24245138817040104,
|
847 |
+
"learning_rate": 1.916434380610963e-05,
|
848 |
+
"loss": 0.6922,
|
849 |
+
"step": 595
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.66,
|
853 |
+
"grad_norm": 0.22591029702471543,
|
854 |
+
"learning_rate": 1.9138572280526795e-05,
|
855 |
+
"loss": 0.6672,
|
856 |
+
"step": 600
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.66,
|
860 |
+
"grad_norm": 0.22886503680106302,
|
861 |
+
"learning_rate": 1.911242724143552e-05,
|
862 |
+
"loss": 0.6574,
|
863 |
+
"step": 605
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.67,
|
867 |
+
"grad_norm": 0.23592282593270214,
|
868 |
+
"learning_rate": 1.908590975744094e-05,
|
869 |
+
"loss": 0.6701,
|
870 |
+
"step": 610
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.68,
|
874 |
+
"grad_norm": 0.2263018036424681,
|
875 |
+
"learning_rate": 1.9059020912370836e-05,
|
876 |
+
"loss": 0.6645,
|
877 |
+
"step": 615
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.68,
|
881 |
+
"grad_norm": 0.23573388350757823,
|
882 |
+
"learning_rate": 1.9031761805231322e-05,
|
883 |
+
"loss": 0.6789,
|
884 |
+
"step": 620
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.69,
|
888 |
+
"grad_norm": 0.2264306405740615,
|
889 |
+
"learning_rate": 1.9004133550161953e-05,
|
890 |
+
"loss": 0.6798,
|
891 |
+
"step": 625
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.69,
|
895 |
+
"grad_norm": 0.23127140958344955,
|
896 |
+
"learning_rate": 1.8976137276390145e-05,
|
897 |
+
"loss": 0.6918,
|
898 |
+
"step": 630
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.7,
|
902 |
+
"grad_norm": 0.22485640726090023,
|
903 |
+
"learning_rate": 1.894777412818506e-05,
|
904 |
+
"loss": 0.6579,
|
905 |
+
"step": 635
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.7,
|
909 |
+
"grad_norm": 0.2164772947483346,
|
910 |
+
"learning_rate": 1.891904526481083e-05,
|
911 |
+
"loss": 0.6729,
|
912 |
+
"step": 640
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.71,
|
916 |
+
"grad_norm": 0.21930341038212908,
|
917 |
+
"learning_rate": 1.8889951860479165e-05,
|
918 |
+
"loss": 0.6636,
|
919 |
+
"step": 645
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.71,
|
923 |
+
"grad_norm": 0.2212836429863629,
|
924 |
+
"learning_rate": 1.8860495104301346e-05,
|
925 |
+
"loss": 0.7046,
|
926 |
+
"step": 650
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.72,
|
930 |
+
"grad_norm": 0.236222638103693,
|
931 |
+
"learning_rate": 1.8830676200239666e-05,
|
932 |
+
"loss": 0.6544,
|
933 |
+
"step": 655
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.73,
|
937 |
+
"grad_norm": 0.23689174767504043,
|
938 |
+
"learning_rate": 1.8800496367058187e-05,
|
939 |
+
"loss": 0.6619,
|
940 |
+
"step": 660
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.73,
|
944 |
+
"grad_norm": 0.22794708045955256,
|
945 |
+
"learning_rate": 1.8769956838272937e-05,
|
946 |
+
"loss": 0.6536,
|
947 |
+
"step": 665
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.74,
|
951 |
+
"grad_norm": 0.2284737343207547,
|
952 |
+
"learning_rate": 1.8739058862101487e-05,
|
953 |
+
"loss": 0.6716,
|
954 |
+
"step": 670
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.74,
|
958 |
+
"grad_norm": 0.22074952318779162,
|
959 |
+
"learning_rate": 1.8707803701411946e-05,
|
960 |
+
"loss": 0.671,
|
961 |
+
"step": 675
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.75,
|
965 |
+
"grad_norm": 0.2215061880912214,
|
966 |
+
"learning_rate": 1.8676192633671342e-05,
|
967 |
+
"loss": 0.6865,
|
968 |
+
"step": 680
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.75,
|
972 |
+
"grad_norm": 0.23413437096611026,
|
973 |
+
"learning_rate": 1.8644226950893394e-05,
|
974 |
+
"loss": 0.6707,
|
975 |
+
"step": 685
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.76,
|
979 |
+
"grad_norm": 0.22955684806244817,
|
980 |
+
"learning_rate": 1.861190795958573e-05,
|
981 |
+
"loss": 0.6835,
|
982 |
+
"step": 690
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.76,
|
986 |
+
"grad_norm": 0.22476186793320183,
|
987 |
+
"learning_rate": 1.857923698069646e-05,
|
988 |
+
"loss": 0.6597,
|
989 |
+
"step": 695
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.77,
|
993 |
+
"grad_norm": 0.22821748154651522,
|
994 |
+
"learning_rate": 1.8546215349560204e-05,
|
995 |
+
"loss": 0.6769,
|
996 |
+
"step": 700
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.77,
|
1000 |
+
"grad_norm": 0.22293250318189695,
|
1001 |
+
"learning_rate": 1.8512844415843514e-05,
|
1002 |
+
"loss": 0.6828,
|
1003 |
+
"step": 705
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.78,
|
1007 |
+
"grad_norm": 0.22191425457543576,
|
1008 |
+
"learning_rate": 1.8479125543489694e-05,
|
1009 |
+
"loss": 0.6849,
|
1010 |
+
"step": 710
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.79,
|
1014 |
+
"grad_norm": 0.22106154189199517,
|
1015 |
+
"learning_rate": 1.844506011066308e-05,
|
1016 |
+
"loss": 0.6877,
|
1017 |
+
"step": 715
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.79,
|
1021 |
+
"grad_norm": 0.22662154758390868,
|
1022 |
+
"learning_rate": 1.841064950969268e-05,
|
1023 |
+
"loss": 0.6579,
|
1024 |
+
"step": 720
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.8,
|
1028 |
+
"grad_norm": 0.22395783462295688,
|
1029 |
+
"learning_rate": 1.8375895147015285e-05,
|
1030 |
+
"loss": 0.6808,
|
1031 |
+
"step": 725
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.8,
|
1035 |
+
"grad_norm": 0.22270568666818555,
|
1036 |
+
"learning_rate": 1.8340798443117992e-05,
|
1037 |
+
"loss": 0.6705,
|
1038 |
+
"step": 730
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.81,
|
1042 |
+
"grad_norm": 0.2150504585631758,
|
1043 |
+
"learning_rate": 1.8305360832480118e-05,
|
1044 |
+
"loss": 0.6628,
|
1045 |
+
"step": 735
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.81,
|
1049 |
+
"grad_norm": 0.21416406499964488,
|
1050 |
+
"learning_rate": 1.8269583763514603e-05,
|
1051 |
+
"loss": 0.6602,
|
1052 |
+
"step": 740
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.82,
|
1056 |
+
"grad_norm": 0.22446619283908673,
|
1057 |
+
"learning_rate": 1.8233468698508786e-05,
|
1058 |
+
"loss": 0.6516,
|
1059 |
+
"step": 745
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.82,
|
1063 |
+
"grad_norm": 0.22209820477583542,
|
1064 |
+
"learning_rate": 1.819701711356464e-05,
|
1065 |
+
"loss": 0.6719,
|
1066 |
+
"step": 750
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.83,
|
1070 |
+
"grad_norm": 0.20930564484300637,
|
1071 |
+
"learning_rate": 1.8160230498538464e-05,
|
1072 |
+
"loss": 0.6462,
|
1073 |
+
"step": 755
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 0.84,
|
1077 |
+
"grad_norm": 0.2157300926603618,
|
1078 |
+
"learning_rate": 1.8123110356979955e-05,
|
1079 |
+
"loss": 0.6386,
|
1080 |
+
"step": 760
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 0.84,
|
1084 |
+
"grad_norm": 0.2278341187144425,
|
1085 |
+
"learning_rate": 1.808565820607078e-05,
|
1086 |
+
"loss": 0.6864,
|
1087 |
+
"step": 765
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 0.85,
|
1091 |
+
"grad_norm": 0.22190749729143514,
|
1092 |
+
"learning_rate": 1.8047875576562556e-05,
|
1093 |
+
"loss": 0.6606,
|
1094 |
+
"step": 770
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.85,
|
1098 |
+
"grad_norm": 0.22188524148964123,
|
1099 |
+
"learning_rate": 1.8009764012714283e-05,
|
1100 |
+
"loss": 0.6369,
|
1101 |
+
"step": 775
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.86,
|
1105 |
+
"grad_norm": 0.24010299878120459,
|
1106 |
+
"learning_rate": 1.7971325072229227e-05,
|
1107 |
+
"loss": 0.6586,
|
1108 |
+
"step": 780
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 0.86,
|
1112 |
+
"grad_norm": 0.2129875521525412,
|
1113 |
+
"learning_rate": 1.7932560326191265e-05,
|
1114 |
+
"loss": 0.6446,
|
1115 |
+
"step": 785
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 0.87,
|
1119 |
+
"grad_norm": 0.2284930031799763,
|
1120 |
+
"learning_rate": 1.789347135900066e-05,
|
1121 |
+
"loss": 0.6704,
|
1122 |
+
"step": 790
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.87,
|
1126 |
+
"grad_norm": 0.21164688299648138,
|
1127 |
+
"learning_rate": 1.7854059768309292e-05,
|
1128 |
+
"loss": 0.6501,
|
1129 |
+
"step": 795
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 0.88,
|
1133 |
+
"grad_norm": 0.2185026582076693,
|
1134 |
+
"learning_rate": 1.7814327164955388e-05,
|
1135 |
+
"loss": 0.6504,
|
1136 |
+
"step": 800
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 0.88,
|
1140 |
+
"grad_norm": 0.23885266134914798,
|
1141 |
+
"learning_rate": 1.777427517289766e-05,
|
1142 |
+
"loss": 0.6534,
|
1143 |
+
"step": 805
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.89,
|
1147 |
+
"grad_norm": 0.24735644831293754,
|
1148 |
+
"learning_rate": 1.773390542914894e-05,
|
1149 |
+
"loss": 0.6593,
|
1150 |
+
"step": 810
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 0.9,
|
1154 |
+
"grad_norm": 0.21801160079829443,
|
1155 |
+
"learning_rate": 1.7693219583709266e-05,
|
1156 |
+
"loss": 0.6538,
|
1157 |
+
"step": 815
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.9,
|
1161 |
+
"grad_norm": 0.23033125474961877,
|
1162 |
+
"learning_rate": 1.765221929949845e-05,
|
1163 |
+
"loss": 0.6544,
|
1164 |
+
"step": 820
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 0.91,
|
1168 |
+
"grad_norm": 0.21636906024225588,
|
1169 |
+
"learning_rate": 1.7610906252288097e-05,
|
1170 |
+
"loss": 0.6678,
|
1171 |
+
"step": 825
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 0.91,
|
1175 |
+
"grad_norm": 0.22862735644017182,
|
1176 |
+
"learning_rate": 1.7569282130633137e-05,
|
1177 |
+
"loss": 0.6676,
|
1178 |
+
"step": 830
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.92,
|
1182 |
+
"grad_norm": 0.22135157314088189,
|
1183 |
+
"learning_rate": 1.752734863580278e-05,
|
1184 |
+
"loss": 0.6463,
|
1185 |
+
"step": 835
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.92,
|
1189 |
+
"grad_norm": 0.21472268874726408,
|
1190 |
+
"learning_rate": 1.7485107481711014e-05,
|
1191 |
+
"loss": 0.6525,
|
1192 |
+
"step": 840
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 0.93,
|
1196 |
+
"grad_norm": 0.21461981313008696,
|
1197 |
+
"learning_rate": 1.7442560394846518e-05,
|
1198 |
+
"loss": 0.6484,
|
1199 |
+
"step": 845
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 0.93,
|
1203 |
+
"grad_norm": 0.21774234081011679,
|
1204 |
+
"learning_rate": 1.739970911420213e-05,
|
1205 |
+
"loss": 0.651,
|
1206 |
+
"step": 850
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 0.94,
|
1210 |
+
"grad_norm": 0.21598579831580747,
|
1211 |
+
"learning_rate": 1.7356555391203745e-05,
|
1212 |
+
"loss": 0.6785,
|
1213 |
+
"step": 855
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 0.95,
|
1217 |
+
"grad_norm": 0.22611280288574187,
|
1218 |
+
"learning_rate": 1.7313100989638745e-05,
|
1219 |
+
"loss": 0.6579,
|
1220 |
+
"step": 860
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 0.95,
|
1224 |
+
"grad_norm": 0.2118379153642089,
|
1225 |
+
"learning_rate": 1.7269347685583913e-05,
|
1226 |
+
"loss": 0.658,
|
1227 |
+
"step": 865
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.96,
|
1231 |
+
"grad_norm": 0.2098318370691198,
|
1232 |
+
"learning_rate": 1.7225297267332815e-05,
|
1233 |
+
"loss": 0.6628,
|
1234 |
+
"step": 870
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.96,
|
1238 |
+
"grad_norm": 0.2096338281124951,
|
1239 |
+
"learning_rate": 1.7180951535322742e-05,
|
1240 |
+
"loss": 0.6519,
|
1241 |
+
"step": 875
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 0.97,
|
1245 |
+
"grad_norm": 0.2277800903608631,
|
1246 |
+
"learning_rate": 1.7136312302061097e-05,
|
1247 |
+
"loss": 0.6396,
|
1248 |
+
"step": 880
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.97,
|
1252 |
+
"grad_norm": 0.2104470768411409,
|
1253 |
+
"learning_rate": 1.7091381392051333e-05,
|
1254 |
+
"loss": 0.6434,
|
1255 |
+
"step": 885
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 0.98,
|
1259 |
+
"grad_norm": 0.2142332846578606,
|
1260 |
+
"learning_rate": 1.704616064171836e-05,
|
1261 |
+
"loss": 0.6384,
|
1262 |
+
"step": 890
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 0.98,
|
1266 |
+
"grad_norm": 0.21219425658206706,
|
1267 |
+
"learning_rate": 1.7000651899333512e-05,
|
1268 |
+
"loss": 0.6346,
|
1269 |
+
"step": 895
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.99,
|
1273 |
+
"grad_norm": 0.2208443696000645,
|
1274 |
+
"learning_rate": 1.6954857024938976e-05,
|
1275 |
+
"loss": 0.648,
|
1276 |
+
"step": 900
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 0.99,
|
1280 |
+
"grad_norm": 0.21055402887891725,
|
1281 |
+
"learning_rate": 1.6908777890271794e-05,
|
1282 |
+
"loss": 0.6472,
|
1283 |
+
"step": 905
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 1.0,
|
1287 |
+
"grad_norm": 0.2122526858833542,
|
1288 |
+
"learning_rate": 1.686241637868734e-05,
|
1289 |
+
"loss": 0.6422,
|
1290 |
+
"step": 910
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 1.0,
|
1294 |
+
"eval_loss": 0.6909855604171753,
|
1295 |
+
"eval_runtime": 13.3743,
|
1296 |
+
"eval_samples_per_second": 103.034,
|
1297 |
+
"eval_steps_per_second": 0.822,
|
1298 |
+
"step": 910
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 1.01,
|
1302 |
+
"grad_norm": 0.2376946716415055,
|
1303 |
+
"learning_rate": 1.6815774385082355e-05,
|
1304 |
+
"loss": 0.6025,
|
1305 |
+
"step": 915
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 1.01,
|
1309 |
+
"grad_norm": 0.21981152940016552,
|
1310 |
+
"learning_rate": 1.6768853815817506e-05,
|
1311 |
+
"loss": 0.6149,
|
1312 |
+
"step": 920
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 1.02,
|
1316 |
+
"grad_norm": 0.2114064615721331,
|
1317 |
+
"learning_rate": 1.6721656588639444e-05,
|
1318 |
+
"loss": 0.6084,
|
1319 |
+
"step": 925
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 1.02,
|
1323 |
+
"grad_norm": 0.21343882616611637,
|
1324 |
+
"learning_rate": 1.6674184632602447e-05,
|
1325 |
+
"loss": 0.6192,
|
1326 |
+
"step": 930
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 1.03,
|
1330 |
+
"grad_norm": 0.20964848533593644,
|
1331 |
+
"learning_rate": 1.6626439887989552e-05,
|
1332 |
+
"loss": 0.577,
|
1333 |
+
"step": 935
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 1.03,
|
1337 |
+
"grad_norm": 0.21080943869356272,
|
1338 |
+
"learning_rate": 1.6578424306233282e-05,
|
1339 |
+
"loss": 0.5858,
|
1340 |
+
"step": 940
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 1.04,
|
1344 |
+
"grad_norm": 0.21972421289491473,
|
1345 |
+
"learning_rate": 1.653013984983585e-05,
|
1346 |
+
"loss": 0.5907,
|
1347 |
+
"step": 945
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 1.04,
|
1351 |
+
"grad_norm": 0.2148077134860289,
|
1352 |
+
"learning_rate": 1.6481588492288985e-05,
|
1353 |
+
"loss": 0.5974,
|
1354 |
+
"step": 950
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 1.05,
|
1358 |
+
"grad_norm": 0.222495841900069,
|
1359 |
+
"learning_rate": 1.643277221799323e-05,
|
1360 |
+
"loss": 0.5979,
|
1361 |
+
"step": 955
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 1.05,
|
1365 |
+
"grad_norm": 0.21883932168474696,
|
1366 |
+
"learning_rate": 1.638369302217687e-05,
|
1367 |
+
"loss": 0.6077,
|
1368 |
+
"step": 960
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 1.06,
|
1372 |
+
"grad_norm": 0.20756222937087987,
|
1373 |
+
"learning_rate": 1.633435291081437e-05,
|
1374 |
+
"loss": 0.5886,
|
1375 |
+
"step": 965
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 1.07,
|
1379 |
+
"grad_norm": 0.22034735404299097,
|
1380 |
+
"learning_rate": 1.6284753900544384e-05,
|
1381 |
+
"loss": 0.6023,
|
1382 |
+
"step": 970
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 1.07,
|
1386 |
+
"grad_norm": 0.2178991358059654,
|
1387 |
+
"learning_rate": 1.6234898018587336e-05,
|
1388 |
+
"loss": 0.6077,
|
1389 |
+
"step": 975
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.08,
|
1393 |
+
"grad_norm": 0.21185656324247812,
|
1394 |
+
"learning_rate": 1.618478730266255e-05,
|
1395 |
+
"loss": 0.5891,
|
1396 |
+
"step": 980
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 1.08,
|
1400 |
+
"grad_norm": 0.2225195916998371,
|
1401 |
+
"learning_rate": 1.6134423800904985e-05,
|
1402 |
+
"loss": 0.6082,
|
1403 |
+
"step": 985
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 1.09,
|
1407 |
+
"grad_norm": 0.21175099229044173,
|
1408 |
+
"learning_rate": 1.6083809571781498e-05,
|
1409 |
+
"loss": 0.6022,
|
1410 |
+
"step": 990
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 1.09,
|
1414 |
+
"grad_norm": 0.21693130048041695,
|
1415 |
+
"learning_rate": 1.6032946684006745e-05,
|
1416 |
+
"loss": 0.5877,
|
1417 |
+
"step": 995
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 1.1,
|
1421 |
+
"grad_norm": 0.20628677851436183,
|
1422 |
+
"learning_rate": 1.598183721645858e-05,
|
1423 |
+
"loss": 0.6025,
|
1424 |
+
"step": 1000
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 1.1,
|
1428 |
+
"grad_norm": 0.21136866931809867,
|
1429 |
+
"learning_rate": 1.5930483258093144e-05,
|
1430 |
+
"loss": 0.6056,
|
1431 |
+
"step": 1005
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 1.11,
|
1435 |
+
"grad_norm": 0.21628647967275302,
|
1436 |
+
"learning_rate": 1.5878886907859423e-05,
|
1437 |
+
"loss": 0.5973,
|
1438 |
+
"step": 1010
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 1.12,
|
1442 |
+
"grad_norm": 0.21460811563007248,
|
1443 |
+
"learning_rate": 1.5827050274613512e-05,
|
1444 |
+
"loss": 0.6151,
|
1445 |
+
"step": 1015
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 1.12,
|
1449 |
+
"grad_norm": 0.21019968808729894,
|
1450 |
+
"learning_rate": 1.57749754770324e-05,
|
1451 |
+
"loss": 0.5871,
|
1452 |
+
"step": 1020
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 1.13,
|
1456 |
+
"grad_norm": 0.21602614964752764,
|
1457 |
+
"learning_rate": 1.5722664643527362e-05,
|
1458 |
+
"loss": 0.6088,
|
1459 |
+
"step": 1025
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 1.13,
|
1463 |
+
"grad_norm": 0.21863820245310453,
|
1464 |
+
"learning_rate": 1.567011991215699e-05,
|
1465 |
+
"loss": 0.5968,
|
1466 |
+
"step": 1030
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 1.14,
|
1470 |
+
"grad_norm": 0.21638329517362545,
|
1471 |
+
"learning_rate": 1.561734343053979e-05,
|
1472 |
+
"loss": 0.5879,
|
1473 |
+
"step": 1035
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 1.14,
|
1477 |
+
"grad_norm": 0.21082524836877004,
|
1478 |
+
"learning_rate": 1.5564337355766412e-05,
|
1479 |
+
"loss": 0.583,
|
1480 |
+
"step": 1040
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 1.15,
|
1484 |
+
"grad_norm": 0.2055779159254746,
|
1485 |
+
"learning_rate": 1.551110385431148e-05,
|
1486 |
+
"loss": 0.5934,
|
1487 |
+
"step": 1045
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 1.15,
|
1491 |
+
"grad_norm": 0.22359885758488707,
|
1492 |
+
"learning_rate": 1.5457645101945046e-05,
|
1493 |
+
"loss": 0.5824,
|
1494 |
+
"step": 1050
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 1.16,
|
1498 |
+
"grad_norm": 0.2194479570684916,
|
1499 |
+
"learning_rate": 1.540396328364367e-05,
|
1500 |
+
"loss": 0.6125,
|
1501 |
+
"step": 1055
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.16,
|
1505 |
+
"grad_norm": 0.21187983654193793,
|
1506 |
+
"learning_rate": 1.5350060593501086e-05,
|
1507 |
+
"loss": 0.6028,
|
1508 |
+
"step": 1060
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 1.17,
|
1512 |
+
"grad_norm": 0.21206606898137628,
|
1513 |
+
"learning_rate": 1.5295939234638566e-05,
|
1514 |
+
"loss": 0.5934,
|
1515 |
+
"step": 1065
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 1.18,
|
1519 |
+
"grad_norm": 0.20258591515345375,
|
1520 |
+
"learning_rate": 1.5241601419114842e-05,
|
1521 |
+
"loss": 0.5775,
|
1522 |
+
"step": 1070
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 1.18,
|
1526 |
+
"grad_norm": 0.2136809123465599,
|
1527 |
+
"learning_rate": 1.5187049367835709e-05,
|
1528 |
+
"loss": 0.5941,
|
1529 |
+
"step": 1075
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 1.19,
|
1533 |
+
"grad_norm": 0.21728230317859182,
|
1534 |
+
"learning_rate": 1.5132285310463243e-05,
|
1535 |
+
"loss": 0.5832,
|
1536 |
+
"step": 1080
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 1.19,
|
1540 |
+
"grad_norm": 0.2173442514170428,
|
1541 |
+
"learning_rate": 1.507731148532468e-05,
|
1542 |
+
"loss": 0.5896,
|
1543 |
+
"step": 1085
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 1.2,
|
1547 |
+
"grad_norm": 0.2171859843513773,
|
1548 |
+
"learning_rate": 1.5022130139320916e-05,
|
1549 |
+
"loss": 0.6007,
|
1550 |
+
"step": 1090
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 1.2,
|
1554 |
+
"grad_norm": 0.22340196606689453,
|
1555 |
+
"learning_rate": 1.4966743527834691e-05,
|
1556 |
+
"loss": 0.6034,
|
1557 |
+
"step": 1095
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.21,
|
1561 |
+
"grad_norm": 0.20721993882081483,
|
1562 |
+
"learning_rate": 1.4911153914638388e-05,
|
1563 |
+
"loss": 0.6027,
|
1564 |
+
"step": 1100
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 1.21,
|
1568 |
+
"grad_norm": 0.21607496950020452,
|
1569 |
+
"learning_rate": 1.4855363571801523e-05,
|
1570 |
+
"loss": 0.6128,
|
1571 |
+
"step": 1105
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 1.22,
|
1575 |
+
"grad_norm": 0.21215405353798844,
|
1576 |
+
"learning_rate": 1.4799374779597866e-05,
|
1577 |
+
"loss": 0.583,
|
1578 |
+
"step": 1110
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 1.23,
|
1582 |
+
"grad_norm": 0.21724719376448562,
|
1583 |
+
"learning_rate": 1.474318982641225e-05,
|
1584 |
+
"loss": 0.5913,
|
1585 |
+
"step": 1115
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 1.23,
|
1589 |
+
"grad_norm": 0.22458471606601424,
|
1590 |
+
"learning_rate": 1.4686811008647037e-05,
|
1591 |
+
"loss": 0.612,
|
1592 |
+
"step": 1120
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 1.24,
|
1596 |
+
"grad_norm": 0.21247586240459654,
|
1597 |
+
"learning_rate": 1.463024063062827e-05,
|
1598 |
+
"loss": 0.5855,
|
1599 |
+
"step": 1125
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.24,
|
1603 |
+
"grad_norm": 0.22045045025828708,
|
1604 |
+
"learning_rate": 1.457348100451146e-05,
|
1605 |
+
"loss": 0.5883,
|
1606 |
+
"step": 1130
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 1.25,
|
1610 |
+
"grad_norm": 0.214769725773024,
|
1611 |
+
"learning_rate": 1.4516534450187126e-05,
|
1612 |
+
"loss": 0.5877,
|
1613 |
+
"step": 1135
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 1.25,
|
1617 |
+
"grad_norm": 0.2160947649465179,
|
1618 |
+
"learning_rate": 1.4459403295185933e-05,
|
1619 |
+
"loss": 0.5951,
|
1620 |
+
"step": 1140
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 1.26,
|
1624 |
+
"grad_norm": 0.21080831461558835,
|
1625 |
+
"learning_rate": 1.4402089874583594e-05,
|
1626 |
+
"loss": 0.5616,
|
1627 |
+
"step": 1145
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 1.26,
|
1631 |
+
"grad_norm": 0.3517838242091068,
|
1632 |
+
"learning_rate": 1.4344596530905412e-05,
|
1633 |
+
"loss": 0.5981,
|
1634 |
+
"step": 1150
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 1.27,
|
1638 |
+
"grad_norm": 0.2170223068256742,
|
1639 |
+
"learning_rate": 1.4286925614030542e-05,
|
1640 |
+
"loss": 0.5962,
|
1641 |
+
"step": 1155
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 1.27,
|
1645 |
+
"grad_norm": 0.20876572174386707,
|
1646 |
+
"learning_rate": 1.4229079481095949e-05,
|
1647 |
+
"loss": 0.5705,
|
1648 |
+
"step": 1160
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 1.28,
|
1652 |
+
"grad_norm": 0.2114530881165322,
|
1653 |
+
"learning_rate": 1.4171060496400055e-05,
|
1654 |
+
"loss": 0.5831,
|
1655 |
+
"step": 1165
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 1.29,
|
1659 |
+
"grad_norm": 0.2124316227899679,
|
1660 |
+
"learning_rate": 1.4112871031306118e-05,
|
1661 |
+
"loss": 0.5927,
|
1662 |
+
"step": 1170
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 1.29,
|
1666 |
+
"grad_norm": 0.24069796832607096,
|
1667 |
+
"learning_rate": 1.4054513464145303e-05,
|
1668 |
+
"loss": 0.5843,
|
1669 |
+
"step": 1175
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 1.3,
|
1673 |
+
"grad_norm": 0.21761542079259927,
|
1674 |
+
"learning_rate": 1.3995990180119478e-05,
|
1675 |
+
"loss": 0.5913,
|
1676 |
+
"step": 1180
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 1.3,
|
1680 |
+
"grad_norm": 0.22376197027518,
|
1681 |
+
"learning_rate": 1.3937303571203718e-05,
|
1682 |
+
"loss": 0.5937,
|
1683 |
+
"step": 1185
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 1.31,
|
1687 |
+
"grad_norm": 0.21270100949939988,
|
1688 |
+
"learning_rate": 1.387845603604855e-05,
|
1689 |
+
"loss": 0.6087,
|
1690 |
+
"step": 1190
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 1.31,
|
1694 |
+
"grad_norm": 0.2061356457768136,
|
1695 |
+
"learning_rate": 1.3819449979881907e-05,
|
1696 |
+
"loss": 0.5913,
|
1697 |
+
"step": 1195
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 1.32,
|
1701 |
+
"grad_norm": 0.21386723380022615,
|
1702 |
+
"learning_rate": 1.3760287814410822e-05,
|
1703 |
+
"loss": 0.5993,
|
1704 |
+
"step": 1200
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 1.32,
|
1708 |
+
"grad_norm": 0.21228068552627186,
|
1709 |
+
"learning_rate": 1.3700971957722861e-05,
|
1710 |
+
"loss": 0.5957,
|
1711 |
+
"step": 1205
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 1.33,
|
1715 |
+
"grad_norm": 0.22337829074807855,
|
1716 |
+
"learning_rate": 1.3641504834187288e-05,
|
1717 |
+
"loss": 0.5877,
|
1718 |
+
"step": 1210
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 1.34,
|
1722 |
+
"grad_norm": 0.20603083898424746,
|
1723 |
+
"learning_rate": 1.3581888874355969e-05,
|
1724 |
+
"loss": 0.5925,
|
1725 |
+
"step": 1215
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 1.34,
|
1729 |
+
"grad_norm": 0.21192778054346198,
|
1730 |
+
"learning_rate": 1.3522126514864047e-05,
|
1731 |
+
"loss": 0.5891,
|
1732 |
+
"step": 1220
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 1.35,
|
1736 |
+
"grad_norm": 0.2084884476447279,
|
1737 |
+
"learning_rate": 1.346222019833033e-05,
|
1738 |
+
"loss": 0.5834,
|
1739 |
+
"step": 1225
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 1.35,
|
1743 |
+
"grad_norm": 0.2147834275155995,
|
1744 |
+
"learning_rate": 1.3402172373257466e-05,
|
1745 |
+
"loss": 0.5699,
|
1746 |
+
"step": 1230
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 1.36,
|
1750 |
+
"grad_norm": 0.2098959357243527,
|
1751 |
+
"learning_rate": 1.3341985493931877e-05,
|
1752 |
+
"loss": 0.5962,
|
1753 |
+
"step": 1235
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 1.36,
|
1757 |
+
"grad_norm": 0.21524463993944057,
|
1758 |
+
"learning_rate": 1.3281662020323434e-05,
|
1759 |
+
"loss": 0.5732,
|
1760 |
+
"step": 1240
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 1.37,
|
1764 |
+
"grad_norm": 0.21867167573117696,
|
1765 |
+
"learning_rate": 1.3221204417984907e-05,
|
1766 |
+
"loss": 0.5955,
|
1767 |
+
"step": 1245
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 1.37,
|
1771 |
+
"grad_norm": 0.21413713721132682,
|
1772 |
+
"learning_rate": 1.3160615157951218e-05,
|
1773 |
+
"loss": 0.6075,
|
1774 |
+
"step": 1250
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 1.38,
|
1778 |
+
"grad_norm": 0.21839276156580137,
|
1779 |
+
"learning_rate": 1.3099896716638414e-05,
|
1780 |
+
"loss": 0.6037,
|
1781 |
+
"step": 1255
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 1.38,
|
1785 |
+
"grad_norm": 0.2083037589975683,
|
1786 |
+
"learning_rate": 1.303905157574247e-05,
|
1787 |
+
"loss": 0.5824,
|
1788 |
+
"step": 1260
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 1.39,
|
1792 |
+
"grad_norm": 0.2113647393844558,
|
1793 |
+
"learning_rate": 1.297808222213785e-05,
|
1794 |
+
"loss": 0.583,
|
1795 |
+
"step": 1265
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 1.4,
|
1799 |
+
"grad_norm": 0.21208258707761682,
|
1800 |
+
"learning_rate": 1.2916991147775867e-05,
|
1801 |
+
"loss": 0.5968,
|
1802 |
+
"step": 1270
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 1.4,
|
1806 |
+
"grad_norm": 0.21585097977939674,
|
1807 |
+
"learning_rate": 1.2855780849582828e-05,
|
1808 |
+
"loss": 0.605,
|
1809 |
+
"step": 1275
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 1.41,
|
1813 |
+
"grad_norm": 0.2177190382165568,
|
1814 |
+
"learning_rate": 1.2794453829357974e-05,
|
1815 |
+
"loss": 0.5917,
|
1816 |
+
"step": 1280
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 1.41,
|
1820 |
+
"grad_norm": 0.20918133994979798,
|
1821 |
+
"learning_rate": 1.2733012593671235e-05,
|
1822 |
+
"loss": 0.5808,
|
1823 |
+
"step": 1285
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 1.42,
|
1827 |
+
"grad_norm": 0.20727620915430647,
|
1828 |
+
"learning_rate": 1.2671459653760781e-05,
|
1829 |
+
"loss": 0.5848,
|
1830 |
+
"step": 1290
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 1.42,
|
1834 |
+
"grad_norm": 0.21127807703832494,
|
1835 |
+
"learning_rate": 1.2609797525430374e-05,
|
1836 |
+
"loss": 0.5918,
|
1837 |
+
"step": 1295
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 1.43,
|
1841 |
+
"grad_norm": 0.22995739968919704,
|
1842 |
+
"learning_rate": 1.2548028728946548e-05,
|
1843 |
+
"loss": 0.5788,
|
1844 |
+
"step": 1300
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 1.43,
|
1848 |
+
"grad_norm": 0.283656419786389,
|
1849 |
+
"learning_rate": 1.2486155788935599e-05,
|
1850 |
+
"loss": 0.5696,
|
1851 |
+
"step": 1305
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 1.44,
|
1855 |
+
"grad_norm": 0.2060037733197605,
|
1856 |
+
"learning_rate": 1.24241812342804e-05,
|
1857 |
+
"loss": 0.5679,
|
1858 |
+
"step": 1310
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 1.45,
|
1862 |
+
"grad_norm": 0.20635796088681332,
|
1863 |
+
"learning_rate": 1.2362107598017037e-05,
|
1864 |
+
"loss": 0.5724,
|
1865 |
+
"step": 1315
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 1.45,
|
1869 |
+
"grad_norm": 0.22467393881977182,
|
1870 |
+
"learning_rate": 1.2299937417231269e-05,
|
1871 |
+
"loss": 0.5955,
|
1872 |
+
"step": 1320
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 1.46,
|
1876 |
+
"grad_norm": 0.2074247154565041,
|
1877 |
+
"learning_rate": 1.2237673232954854e-05,
|
1878 |
+
"loss": 0.5971,
|
1879 |
+
"step": 1325
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 1.46,
|
1883 |
+
"grad_norm": 0.2424465336794506,
|
1884 |
+
"learning_rate": 1.2175317590061676e-05,
|
1885 |
+
"loss": 0.5781,
|
1886 |
+
"step": 1330
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 1.47,
|
1890 |
+
"grad_norm": 0.22257500583547102,
|
1891 |
+
"learning_rate": 1.2112873037163728e-05,
|
1892 |
+
"loss": 0.5839,
|
1893 |
+
"step": 1335
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 1.47,
|
1897 |
+
"grad_norm": 0.2066344256103609,
|
1898 |
+
"learning_rate": 1.2050342126506958e-05,
|
1899 |
+
"loss": 0.5739,
|
1900 |
+
"step": 1340
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 1.48,
|
1904 |
+
"grad_norm": 0.22883829030621783,
|
1905 |
+
"learning_rate": 1.1987727413866936e-05,
|
1906 |
+
"loss": 0.5834,
|
1907 |
+
"step": 1345
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 1.48,
|
1911 |
+
"grad_norm": 0.2078381748570218,
|
1912 |
+
"learning_rate": 1.1925031458444416e-05,
|
1913 |
+
"loss": 0.5987,
|
1914 |
+
"step": 1350
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 1.49,
|
1918 |
+
"grad_norm": 0.19775167797301507,
|
1919 |
+
"learning_rate": 1.1862256822760704e-05,
|
1920 |
+
"loss": 0.6014,
|
1921 |
+
"step": 1355
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 1.49,
|
1925 |
+
"grad_norm": 0.22122261973414395,
|
1926 |
+
"learning_rate": 1.1799406072552963e-05,
|
1927 |
+
"loss": 0.6051,
|
1928 |
+
"step": 1360
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 1.5,
|
1932 |
+
"grad_norm": 0.2048271696065503,
|
1933 |
+
"learning_rate": 1.1736481776669307e-05,
|
1934 |
+
"loss": 0.5836,
|
1935 |
+
"step": 1365
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 1.51,
|
1939 |
+
"grad_norm": 0.2089570875625985,
|
1940 |
+
"learning_rate": 1.1673486506963824e-05,
|
1941 |
+
"loss": 0.5969,
|
1942 |
+
"step": 1370
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 1.51,
|
1946 |
+
"grad_norm": 0.20686459307988367,
|
1947 |
+
"learning_rate": 1.1610422838191473e-05,
|
1948 |
+
"loss": 0.5838,
|
1949 |
+
"step": 1375
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 1.52,
|
1953 |
+
"grad_norm": 0.2011184871623206,
|
1954 |
+
"learning_rate": 1.1547293347902813e-05,
|
1955 |
+
"loss": 0.5809,
|
1956 |
+
"step": 1380
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 1.52,
|
1960 |
+
"grad_norm": 0.20796307453083696,
|
1961 |
+
"learning_rate": 1.148410061633869e-05,
|
1962 |
+
"loss": 0.577,
|
1963 |
+
"step": 1385
|
1964 |
+
},
|
1965 |
+
{
|
1966 |
+
"epoch": 1.53,
|
1967 |
+
"grad_norm": 0.21285626663848575,
|
1968 |
+
"learning_rate": 1.1420847226324746e-05,
|
1969 |
+
"loss": 0.5842,
|
1970 |
+
"step": 1390
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 1.53,
|
1974 |
+
"grad_norm": 0.21073449630208443,
|
1975 |
+
"learning_rate": 1.135753576316588e-05,
|
1976 |
+
"loss": 0.5631,
|
1977 |
+
"step": 1395
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 1.54,
|
1981 |
+
"grad_norm": 0.21419628737948346,
|
1982 |
+
"learning_rate": 1.1294168814540554e-05,
|
1983 |
+
"loss": 0.5725,
|
1984 |
+
"step": 1400
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 1.54,
|
1988 |
+
"grad_norm": 0.21145643817601928,
|
1989 |
+
"learning_rate": 1.1230748970395056e-05,
|
1990 |
+
"loss": 0.5841,
|
1991 |
+
"step": 1405
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 1.55,
|
1995 |
+
"grad_norm": 0.21985931289420635,
|
1996 |
+
"learning_rate": 1.1167278822837621e-05,
|
1997 |
+
"loss": 0.5921,
|
1998 |
+
"step": 1410
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 1.55,
|
2002 |
+
"grad_norm": 0.21769355752757327,
|
2003 |
+
"learning_rate": 1.1103760966032497e-05,
|
2004 |
+
"loss": 0.5969,
|
2005 |
+
"step": 1415
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 1.56,
|
2009 |
+
"grad_norm": 0.205702651788512,
|
2010 |
+
"learning_rate": 1.1040197996093915e-05,
|
2011 |
+
"loss": 0.5998,
|
2012 |
+
"step": 1420
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 1.57,
|
2016 |
+
"grad_norm": 0.2123850240700951,
|
2017 |
+
"learning_rate": 1.0976592510979982e-05,
|
2018 |
+
"loss": 0.602,
|
2019 |
+
"step": 1425
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 1.57,
|
2023 |
+
"grad_norm": 0.2080343816532754,
|
2024 |
+
"learning_rate": 1.0912947110386484e-05,
|
2025 |
+
"loss": 0.5779,
|
2026 |
+
"step": 1430
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 1.58,
|
2030 |
+
"grad_norm": 0.24850849809790562,
|
2031 |
+
"learning_rate": 1.084926439564065e-05,
|
2032 |
+
"loss": 0.6032,
|
2033 |
+
"step": 1435
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 1.58,
|
2037 |
+
"grad_norm": 0.21564897773144823,
|
2038 |
+
"learning_rate": 1.0785546969594813e-05,
|
2039 |
+
"loss": 0.5869,
|
2040 |
+
"step": 1440
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 1.59,
|
2044 |
+
"grad_norm": 0.20762144286700152,
|
2045 |
+
"learning_rate": 1.0721797436520044e-05,
|
2046 |
+
"loss": 0.5826,
|
2047 |
+
"step": 1445
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 1.59,
|
2051 |
+
"grad_norm": 0.2063081386274062,
|
2052 |
+
"learning_rate": 1.0658018401999681e-05,
|
2053 |
+
"loss": 0.5704,
|
2054 |
+
"step": 1450
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 1.6,
|
2058 |
+
"grad_norm": 0.20663776641786638,
|
2059 |
+
"learning_rate": 1.0594212472822865e-05,
|
2060 |
+
"loss": 0.5699,
|
2061 |
+
"step": 1455
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 1.6,
|
2065 |
+
"grad_norm": 0.2041445625688445,
|
2066 |
+
"learning_rate": 1.053038225687798e-05,
|
2067 |
+
"loss": 0.5844,
|
2068 |
+
"step": 1460
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 1.61,
|
2072 |
+
"grad_norm": 0.2130137089909296,
|
2073 |
+
"learning_rate": 1.0466530363046057e-05,
|
2074 |
+
"loss": 0.5863,
|
2075 |
+
"step": 1465
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 1.62,
|
2079 |
+
"grad_norm": 0.20861757470403922,
|
2080 |
+
"learning_rate": 1.0402659401094154e-05,
|
2081 |
+
"loss": 0.5967,
|
2082 |
+
"step": 1470
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 1.62,
|
2086 |
+
"grad_norm": 0.2027441783860282,
|
2087 |
+
"learning_rate": 1.033877198156868e-05,
|
2088 |
+
"loss": 0.5897,
|
2089 |
+
"step": 1475
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 1.63,
|
2093 |
+
"grad_norm": 0.213846779001926,
|
2094 |
+
"learning_rate": 1.0274870715688713e-05,
|
2095 |
+
"loss": 0.6025,
|
2096 |
+
"step": 1480
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 1.63,
|
2100 |
+
"grad_norm": 0.2127779802918096,
|
2101 |
+
"learning_rate": 1.0210958215239249e-05,
|
2102 |
+
"loss": 0.6056,
|
2103 |
+
"step": 1485
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 1.64,
|
2107 |
+
"grad_norm": 0.20745193969187556,
|
2108 |
+
"learning_rate": 1.0147037092464469e-05,
|
2109 |
+
"loss": 0.577,
|
2110 |
+
"step": 1490
|
2111 |
+
},
|
2112 |
+
{
|
2113 |
+
"epoch": 1.64,
|
2114 |
+
"grad_norm": 0.21182819095935948,
|
2115 |
+
"learning_rate": 1.0083109959960974e-05,
|
2116 |
+
"loss": 0.5864,
|
2117 |
+
"step": 1495
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 1.65,
|
2121 |
+
"grad_norm": 0.19696271189726422,
|
2122 |
+
"learning_rate": 1.0019179430570984e-05,
|
2123 |
+
"loss": 0.5928,
|
2124 |
+
"step": 1500
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 1.65,
|
2128 |
+
"grad_norm": 0.20879291422466129,
|
2129 |
+
"learning_rate": 9.955248117275566e-06,
|
2130 |
+
"loss": 0.5759,
|
2131 |
+
"step": 1505
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 1.66,
|
2135 |
+
"grad_norm": 0.20354233979841574,
|
2136 |
+
"learning_rate": 9.891318633087831e-06,
|
2137 |
+
"loss": 0.5752,
|
2138 |
+
"step": 1510
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 1.66,
|
2142 |
+
"grad_norm": 0.20873959818273613,
|
2143 |
+
"learning_rate": 9.827393590946116e-06,
|
2144 |
+
"loss": 0.5781,
|
2145 |
+
"step": 1515
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 1.67,
|
2149 |
+
"grad_norm": 0.20270163619729287,
|
2150 |
+
"learning_rate": 9.763475603607215e-06,
|
2151 |
+
"loss": 0.5766,
|
2152 |
+
"step": 1520
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 1.68,
|
2156 |
+
"grad_norm": 0.20654005706496942,
|
2157 |
+
"learning_rate": 9.699567283539567e-06,
|
2158 |
+
"loss": 0.5681,
|
2159 |
+
"step": 1525
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 1.68,
|
2163 |
+
"grad_norm": 0.20618557107103305,
|
2164 |
+
"learning_rate": 9.635671242816503e-06,
|
2165 |
+
"loss": 0.609,
|
2166 |
+
"step": 1530
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 1.69,
|
2170 |
+
"grad_norm": 0.21061722996416557,
|
2171 |
+
"learning_rate": 9.571790093009445e-06,
|
2172 |
+
"loss": 0.5934,
|
2173 |
+
"step": 1535
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 1.69,
|
2177 |
+
"grad_norm": 0.21093457717343486,
|
2178 |
+
"learning_rate": 9.50792644508122e-06,
|
2179 |
+
"loss": 0.581,
|
2180 |
+
"step": 1540
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 1.7,
|
2184 |
+
"grad_norm": 0.21238370099560738,
|
2185 |
+
"learning_rate": 9.44408290927929e-06,
|
2186 |
+
"loss": 0.5739,
|
2187 |
+
"step": 1545
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 1.7,
|
2191 |
+
"grad_norm": 0.2164905762404212,
|
2192 |
+
"learning_rate": 9.380262095029113e-06,
|
2193 |
+
"loss": 0.5927,
|
2194 |
+
"step": 1550
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 1.71,
|
2198 |
+
"grad_norm": 0.20454952313454147,
|
2199 |
+
"learning_rate": 9.316466610827446e-06,
|
2200 |
+
"loss": 0.5873,
|
2201 |
+
"step": 1555
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 1.71,
|
2205 |
+
"grad_norm": 0.20592385724986123,
|
2206 |
+
"learning_rate": 9.252699064135759e-06,
|
2207 |
+
"loss": 0.5671,
|
2208 |
+
"step": 1560
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 1.72,
|
2212 |
+
"grad_norm": 0.2033785032533706,
|
2213 |
+
"learning_rate": 9.188962061273664e-06,
|
2214 |
+
"loss": 0.5658,
|
2215 |
+
"step": 1565
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 1.73,
|
2219 |
+
"grad_norm": 0.21054461531122468,
|
2220 |
+
"learning_rate": 9.125258207312365e-06,
|
2221 |
+
"loss": 0.5792,
|
2222 |
+
"step": 1570
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 1.73,
|
2226 |
+
"grad_norm": 0.21120511900125027,
|
2227 |
+
"learning_rate": 9.061590105968208e-06,
|
2228 |
+
"loss": 0.5854,
|
2229 |
+
"step": 1575
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 1.74,
|
2233 |
+
"grad_norm": 0.20830877482379653,
|
2234 |
+
"learning_rate": 8.997960359496248e-06,
|
2235 |
+
"loss": 0.5826,
|
2236 |
+
"step": 1580
|
2237 |
+
},
|
2238 |
+
{
|
2239 |
+
"epoch": 1.74,
|
2240 |
+
"grad_norm": 0.20288306787814717,
|
2241 |
+
"learning_rate": 8.934371568583893e-06,
|
2242 |
+
"loss": 0.5706,
|
2243 |
+
"step": 1585
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 1.75,
|
2247 |
+
"grad_norm": 0.21694924382055683,
|
2248 |
+
"learning_rate": 8.8708263322446e-06,
|
2249 |
+
"loss": 0.5951,
|
2250 |
+
"step": 1590
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"epoch": 1.75,
|
2254 |
+
"grad_norm": 0.20903099761718094,
|
2255 |
+
"learning_rate": 8.807327247711667e-06,
|
2256 |
+
"loss": 0.5824,
|
2257 |
+
"step": 1595
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 1.76,
|
2261 |
+
"grad_norm": 0.20063759680689586,
|
2262 |
+
"learning_rate": 8.743876910332057e-06,
|
2263 |
+
"loss": 0.5614,
|
2264 |
+
"step": 1600
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 1.76,
|
2268 |
+
"grad_norm": 0.20409842230229638,
|
2269 |
+
"learning_rate": 8.680477913460339e-06,
|
2270 |
+
"loss": 0.5946,
|
2271 |
+
"step": 1605
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 1.77,
|
2275 |
+
"grad_norm": 0.20466612084153943,
|
2276 |
+
"learning_rate": 8.617132848352672e-06,
|
2277 |
+
"loss": 0.5652,
|
2278 |
+
"step": 1610
|
2279 |
+
},
|
2280 |
+
{
|
2281 |
+
"epoch": 1.77,
|
2282 |
+
"grad_norm": 0.20697633678427196,
|
2283 |
+
"learning_rate": 8.553844304060908e-06,
|
2284 |
+
"loss": 0.5812,
|
2285 |
+
"step": 1615
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 1.78,
|
2289 |
+
"grad_norm": 0.21720588749316946,
|
2290 |
+
"learning_rate": 8.490614867326775e-06,
|
2291 |
+
"loss": 0.6117,
|
2292 |
+
"step": 1620
|
2293 |
+
},
|
2294 |
+
{
|
2295 |
+
"epoch": 1.79,
|
2296 |
+
"grad_norm": 0.20226043800686028,
|
2297 |
+
"learning_rate": 8.427447122476148e-06,
|
2298 |
+
"loss": 0.5813,
|
2299 |
+
"step": 1625
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 1.79,
|
2303 |
+
"grad_norm": 0.20240033305212438,
|
2304 |
+
"learning_rate": 8.364343651313406e-06,
|
2305 |
+
"loss": 0.5838,
|
2306 |
+
"step": 1630
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 1.8,
|
2310 |
+
"grad_norm": 0.20457722466303066,
|
2311 |
+
"learning_rate": 8.301307033015928e-06,
|
2312 |
+
"loss": 0.5838,
|
2313 |
+
"step": 1635
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 1.8,
|
2317 |
+
"grad_norm": 0.21113002739789974,
|
2318 |
+
"learning_rate": 8.23833984402868e-06,
|
2319 |
+
"loss": 0.5642,
|
2320 |
+
"step": 1640
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 1.81,
|
2324 |
+
"grad_norm": 0.20884646327430137,
|
2325 |
+
"learning_rate": 8.175444657958875e-06,
|
2326 |
+
"loss": 0.5887,
|
2327 |
+
"step": 1645
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 1.81,
|
2331 |
+
"grad_norm": 0.2117374486270568,
|
2332 |
+
"learning_rate": 8.112624045470834e-06,
|
2333 |
+
"loss": 0.5586,
|
2334 |
+
"step": 1650
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 1.82,
|
2338 |
+
"grad_norm": 0.2153924095751537,
|
2339 |
+
"learning_rate": 8.04988057418088e-06,
|
2340 |
+
"loss": 0.5586,
|
2341 |
+
"step": 1655
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 1.82,
|
2345 |
+
"grad_norm": 0.2242880757841404,
|
2346 |
+
"learning_rate": 7.987216808552409e-06,
|
2347 |
+
"loss": 0.584,
|
2348 |
+
"step": 1660
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 1.83,
|
2352 |
+
"grad_norm": 0.2052097826707033,
|
2353 |
+
"learning_rate": 7.924635309791065e-06,
|
2354 |
+
"loss": 0.5734,
|
2355 |
+
"step": 1665
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 1.84,
|
2359 |
+
"grad_norm": 0.20970207818516165,
|
2360 |
+
"learning_rate": 7.862138635740078e-06,
|
2361 |
+
"loss": 0.5794,
|
2362 |
+
"step": 1670
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 1.84,
|
2366 |
+
"grad_norm": 0.22854744935308324,
|
2367 |
+
"learning_rate": 7.799729340775688e-06,
|
2368 |
+
"loss": 0.5665,
|
2369 |
+
"step": 1675
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 1.85,
|
2373 |
+
"grad_norm": 0.21044359070616686,
|
2374 |
+
"learning_rate": 7.73740997570278e-06,
|
2375 |
+
"loss": 0.5798,
|
2376 |
+
"step": 1680
|
2377 |
+
},
|
2378 |
+
{
|
2379 |
+
"epoch": 1.85,
|
2380 |
+
"grad_norm": 0.22708073388787278,
|
2381 |
+
"learning_rate": 7.675183087650592e-06,
|
2382 |
+
"loss": 0.5801,
|
2383 |
+
"step": 1685
|
2384 |
+
},
|
2385 |
+
{
|
2386 |
+
"epoch": 1.86,
|
2387 |
+
"grad_norm": 0.2033282205763091,
|
2388 |
+
"learning_rate": 7.613051219968624e-06,
|
2389 |
+
"loss": 0.5839,
|
2390 |
+
"step": 1690
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 1.86,
|
2394 |
+
"grad_norm": 0.20524876955037163,
|
2395 |
+
"learning_rate": 7.551016912122692e-06,
|
2396 |
+
"loss": 0.5669,
|
2397 |
+
"step": 1695
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 1.87,
|
2401 |
+
"grad_norm": 0.2084171272109649,
|
2402 |
+
"learning_rate": 7.489082699591128e-06,
|
2403 |
+
"loss": 0.5772,
|
2404 |
+
"step": 1700
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"epoch": 1.87,
|
2408 |
+
"grad_norm": 0.2045659246543415,
|
2409 |
+
"learning_rate": 7.4272511137611405e-06,
|
2410 |
+
"loss": 0.5888,
|
2411 |
+
"step": 1705
|
2412 |
+
},
|
2413 |
+
{
|
2414 |
+
"epoch": 1.88,
|
2415 |
+
"grad_norm": 0.2238357346707814,
|
2416 |
+
"learning_rate": 7.3655246818253626e-06,
|
2417 |
+
"loss": 0.5778,
|
2418 |
+
"step": 1710
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 1.88,
|
2422 |
+
"grad_norm": 0.20675904524387453,
|
2423 |
+
"learning_rate": 7.303905926678565e-06,
|
2424 |
+
"loss": 0.5716,
|
2425 |
+
"step": 1715
|
2426 |
+
},
|
2427 |
+
{
|
2428 |
+
"epoch": 1.89,
|
2429 |
+
"grad_norm": 0.19722673110072383,
|
2430 |
+
"learning_rate": 7.242397366814516e-06,
|
2431 |
+
"loss": 0.5807,
|
2432 |
+
"step": 1720
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 1.9,
|
2436 |
+
"grad_norm": 0.2048782845337188,
|
2437 |
+
"learning_rate": 7.181001516223074e-06,
|
2438 |
+
"loss": 0.5826,
|
2439 |
+
"step": 1725
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 1.9,
|
2443 |
+
"grad_norm": 0.20915644349360044,
|
2444 |
+
"learning_rate": 7.1197208842874175e-06,
|
2445 |
+
"loss": 0.5604,
|
2446 |
+
"step": 1730
|
2447 |
+
},
|
2448 |
+
{
|
2449 |
+
"epoch": 1.91,
|
2450 |
+
"grad_norm": 0.20273160113226266,
|
2451 |
+
"learning_rate": 7.058557975681488e-06,
|
2452 |
+
"loss": 0.5333,
|
2453 |
+
"step": 1735
|
2454 |
+
},
|
2455 |
+
{
|
2456 |
+
"epoch": 1.91,
|
2457 |
+
"grad_norm": 0.20926689973709214,
|
2458 |
+
"learning_rate": 6.997515290267611e-06,
|
2459 |
+
"loss": 0.5946,
|
2460 |
+
"step": 1740
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 1.92,
|
2464 |
+
"grad_norm": 0.21243148030222134,
|
2465 |
+
"learning_rate": 6.936595322994328e-06,
|
2466 |
+
"loss": 0.5704,
|
2467 |
+
"step": 1745
|
2468 |
+
},
|
2469 |
+
{
|
2470 |
+
"epoch": 1.92,
|
2471 |
+
"grad_norm": 0.2322671841870559,
|
2472 |
+
"learning_rate": 6.8758005637944245e-06,
|
2473 |
+
"loss": 0.5672,
|
2474 |
+
"step": 1750
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 1.93,
|
2478 |
+
"grad_norm": 0.20191574871457757,
|
2479 |
+
"learning_rate": 6.815133497483157e-06,
|
2480 |
+
"loss": 0.5531,
|
2481 |
+
"step": 1755
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 1.93,
|
2485 |
+
"grad_norm": 0.1979263709848421,
|
2486 |
+
"learning_rate": 6.754596603656687e-06,
|
2487 |
+
"loss": 0.5855,
|
2488 |
+
"step": 1760
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"epoch": 1.94,
|
2492 |
+
"grad_norm": 0.20297785849664604,
|
2493 |
+
"learning_rate": 6.694192356590743e-06,
|
2494 |
+
"loss": 0.5611,
|
2495 |
+
"step": 1765
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 1.95,
|
2499 |
+
"grad_norm": 0.2057255315804723,
|
2500 |
+
"learning_rate": 6.633923225139498e-06,
|
2501 |
+
"loss": 0.5603,
|
2502 |
+
"step": 1770
|
2503 |
+
},
|
2504 |
+
{
|
2505 |
+
"epoch": 1.95,
|
2506 |
+
"grad_norm": 0.2039103225151876,
|
2507 |
+
"learning_rate": 6.573791672634638e-06,
|
2508 |
+
"loss": 0.564,
|
2509 |
+
"step": 1775
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"epoch": 1.96,
|
2513 |
+
"grad_norm": 0.20729859585281207,
|
2514 |
+
"learning_rate": 6.513800156784709e-06,
|
2515 |
+
"loss": 0.5665,
|
2516 |
+
"step": 1780
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 1.96,
|
2520 |
+
"grad_norm": 0.21039586635611288,
|
2521 |
+
"learning_rate": 6.453951129574644e-06,
|
2522 |
+
"loss": 0.5731,
|
2523 |
+
"step": 1785
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 1.97,
|
2527 |
+
"grad_norm": 0.2517268650469455,
|
2528 |
+
"learning_rate": 6.394247037165559e-06,
|
2529 |
+
"loss": 0.5895,
|
2530 |
+
"step": 1790
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 1.97,
|
2534 |
+
"grad_norm": 0.20420292346101634,
|
2535 |
+
"learning_rate": 6.3346903197947564e-06,
|
2536 |
+
"loss": 0.5822,
|
2537 |
+
"step": 1795
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 1.98,
|
2541 |
+
"grad_norm": 0.2005713051020868,
|
2542 |
+
"learning_rate": 6.275283411676008e-06,
|
2543 |
+
"loss": 0.5747,
|
2544 |
+
"step": 1800
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 1.98,
|
2548 |
+
"grad_norm": 0.20383448396361142,
|
2549 |
+
"learning_rate": 6.216028740900042e-06,
|
2550 |
+
"loss": 0.564,
|
2551 |
+
"step": 1805
|
2552 |
+
},
|
2553 |
+
{
|
2554 |
+
"epoch": 1.99,
|
2555 |
+
"grad_norm": 0.20518916264594467,
|
2556 |
+
"learning_rate": 6.1569287293353274e-06,
|
2557 |
+
"loss": 0.569,
|
2558 |
+
"step": 1810
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 1.99,
|
2562 |
+
"grad_norm": 0.20991517111604094,
|
2563 |
+
"learning_rate": 6.097985792529055e-06,
|
2564 |
+
"loss": 0.5776,
|
2565 |
+
"step": 1815
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 2.0,
|
2569 |
+
"grad_norm": 0.20901449217066023,
|
2570 |
+
"learning_rate": 6.039202339608432e-06,
|
2571 |
+
"loss": 0.5701,
|
2572 |
+
"step": 1820
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 2.0,
|
2576 |
+
"eval_loss": 0.6639273166656494,
|
2577 |
+
"eval_runtime": 13.2474,
|
2578 |
+
"eval_samples_per_second": 104.021,
|
2579 |
+
"eval_steps_per_second": 0.83,
|
2580 |
+
"step": 1820
|
2581 |
+
},
|
2582 |
+
{
|
2583 |
+
"epoch": 2.01,
|
2584 |
+
"grad_norm": 0.22019281423746326,
|
2585 |
+
"learning_rate": 5.980580773182214e-06,
|
2586 |
+
"loss": 0.522,
|
2587 |
+
"step": 1825
|
2588 |
+
},
|
2589 |
+
{
|
2590 |
+
"epoch": 2.01,
|
2591 |
+
"grad_norm": 0.20628500931618077,
|
2592 |
+
"learning_rate": 5.922123489242499e-06,
|
2593 |
+
"loss": 0.5217,
|
2594 |
+
"step": 1830
|
2595 |
+
},
|
2596 |
+
{
|
2597 |
+
"epoch": 2.02,
|
2598 |
+
"grad_norm": 0.21214052920599313,
|
2599 |
+
"learning_rate": 5.8638328770667905e-06,
|
2600 |
+
"loss": 0.5158,
|
2601 |
+
"step": 1835
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 2.02,
|
2605 |
+
"grad_norm": 0.2125306506706992,
|
2606 |
+
"learning_rate": 5.805711319120358e-06,
|
2607 |
+
"loss": 0.5266,
|
2608 |
+
"step": 1840
|
2609 |
+
},
|
2610 |
+
{
|
2611 |
+
"epoch": 2.03,
|
2612 |
+
"grad_norm": 0.20497451303661474,
|
2613 |
+
"learning_rate": 5.747761190958859e-06,
|
2614 |
+
"loss": 0.5379,
|
2615 |
+
"step": 1845
|
2616 |
+
},
|
2617 |
+
{
|
2618 |
+
"epoch": 2.03,
|
2619 |
+
"grad_norm": 0.20908534530239564,
|
2620 |
+
"learning_rate": 5.689984861131221e-06,
|
2621 |
+
"loss": 0.5235,
|
2622 |
+
"step": 1850
|
2623 |
+
},
|
2624 |
+
{
|
2625 |
+
"epoch": 2.04,
|
2626 |
+
"grad_norm": 0.21454631325571177,
|
2627 |
+
"learning_rate": 5.632384691082874e-06,
|
2628 |
+
"loss": 0.559,
|
2629 |
+
"step": 1855
|
2630 |
+
},
|
2631 |
+
{
|
2632 |
+
"epoch": 2.04,
|
2633 |
+
"grad_norm": 0.20512681342425096,
|
2634 |
+
"learning_rate": 5.5749630350592e-06,
|
2635 |
+
"loss": 0.5112,
|
2636 |
+
"step": 1860
|
2637 |
+
},
|
2638 |
+
{
|
2639 |
+
"epoch": 2.05,
|
2640 |
+
"grad_norm": 0.21863556347579605,
|
2641 |
+
"learning_rate": 5.517722240009319e-06,
|
2642 |
+
"loss": 0.5252,
|
2643 |
+
"step": 1865
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 2.05,
|
2647 |
+
"grad_norm": 0.2042884660329648,
|
2648 |
+
"learning_rate": 5.460664645490172e-06,
|
2649 |
+
"loss": 0.5319,
|
2650 |
+
"step": 1870
|
2651 |
+
},
|
2652 |
+
{
|
2653 |
+
"epoch": 2.06,
|
2654 |
+
"grad_norm": 0.20585363297531442,
|
2655 |
+
"learning_rate": 5.403792583570884e-06,
|
2656 |
+
"loss": 0.5486,
|
2657 |
+
"step": 1875
|
2658 |
+
},
|
2659 |
+
{
|
2660 |
+
"epoch": 2.07,
|
2661 |
+
"grad_norm": 0.21017174229067934,
|
2662 |
+
"learning_rate": 5.347108378737469e-06,
|
2663 |
+
"loss": 0.5219,
|
2664 |
+
"step": 1880
|
2665 |
+
},
|
2666 |
+
{
|
2667 |
+
"epoch": 2.07,
|
2668 |
+
"grad_norm": 0.20323326084962492,
|
2669 |
+
"learning_rate": 5.290614347797802e-06,
|
2670 |
+
"loss": 0.5304,
|
2671 |
+
"step": 1885
|
2672 |
+
},
|
2673 |
+
{
|
2674 |
+
"epoch": 2.08,
|
2675 |
+
"grad_norm": 0.20641023175360712,
|
2676 |
+
"learning_rate": 5.234312799786921e-06,
|
2677 |
+
"loss": 0.5078,
|
2678 |
+
"step": 1890
|
2679 |
+
},
|
2680 |
+
{
|
2681 |
+
"epoch": 2.08,
|
2682 |
+
"grad_norm": 0.20699085777952853,
|
2683 |
+
"learning_rate": 5.1782060358726885e-06,
|
2684 |
+
"loss": 0.541,
|
2685 |
+
"step": 1895
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 2.09,
|
2689 |
+
"grad_norm": 0.21849299793363283,
|
2690 |
+
"learning_rate": 5.122296349261695e-06,
|
2691 |
+
"loss": 0.5382,
|
2692 |
+
"step": 1900
|
2693 |
+
},
|
2694 |
+
{
|
2695 |
+
"epoch": 2.09,
|
2696 |
+
"grad_norm": 0.2225675454375723,
|
2697 |
+
"learning_rate": 5.066586025105558e-06,
|
2698 |
+
"loss": 0.5222,
|
2699 |
+
"step": 1905
|
2700 |
+
},
|
2701 |
+
{
|
2702 |
+
"epoch": 2.1,
|
2703 |
+
"grad_norm": 0.21820736824894094,
|
2704 |
+
"learning_rate": 5.011077340407509e-06,
|
2705 |
+
"loss": 0.521,
|
2706 |
+
"step": 1910
|
2707 |
+
},
|
2708 |
+
{
|
2709 |
+
"epoch": 2.1,
|
2710 |
+
"grad_norm": 0.21040780570604573,
|
2711 |
+
"learning_rate": 4.955772563929334e-06,
|
2712 |
+
"loss": 0.5138,
|
2713 |
+
"step": 1915
|
2714 |
+
},
|
2715 |
+
{
|
2716 |
+
"epoch": 2.11,
|
2717 |
+
"grad_norm": 0.20328121606226746,
|
2718 |
+
"learning_rate": 4.900673956098644e-06,
|
2719 |
+
"loss": 0.5,
|
2720 |
+
"step": 1920
|
2721 |
+
},
|
2722 |
+
{
|
2723 |
+
"epoch": 2.12,
|
2724 |
+
"grad_norm": 0.20307162400180162,
|
2725 |
+
"learning_rate": 4.845783768916482e-06,
|
2726 |
+
"loss": 0.5205,
|
2727 |
+
"step": 1925
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 2.12,
|
2731 |
+
"grad_norm": 0.2145754172951753,
|
2732 |
+
"learning_rate": 4.79110424586528e-06,
|
2733 |
+
"loss": 0.5361,
|
2734 |
+
"step": 1930
|
2735 |
+
},
|
2736 |
+
{
|
2737 |
+
"epoch": 2.13,
|
2738 |
+
"grad_norm": 0.22278545561346286,
|
2739 |
+
"learning_rate": 4.736637621817176e-06,
|
2740 |
+
"loss": 0.5415,
|
2741 |
+
"step": 1935
|
2742 |
+
},
|
2743 |
+
{
|
2744 |
+
"epoch": 2.13,
|
2745 |
+
"grad_norm": 0.20777015428265447,
|
2746 |
+
"learning_rate": 4.682386122942649e-06,
|
2747 |
+
"loss": 0.5466,
|
2748 |
+
"step": 1940
|
2749 |
+
},
|
2750 |
+
{
|
2751 |
+
"epoch": 2.14,
|
2752 |
+
"grad_norm": 0.20476960423981388,
|
2753 |
+
"learning_rate": 4.628351966619531e-06,
|
2754 |
+
"loss": 0.5356,
|
2755 |
+
"step": 1945
|
2756 |
+
},
|
2757 |
+
{
|
2758 |
+
"epoch": 2.14,
|
2759 |
+
"grad_norm": 0.2026935858356193,
|
2760 |
+
"learning_rate": 4.5745373613424075e-06,
|
2761 |
+
"loss": 0.5183,
|
2762 |
+
"step": 1950
|
2763 |
+
},
|
2764 |
+
{
|
2765 |
+
"epoch": 2.15,
|
2766 |
+
"grad_norm": 0.20396283481465377,
|
2767 |
+
"learning_rate": 4.520944506632314e-06,
|
2768 |
+
"loss": 0.5282,
|
2769 |
+
"step": 1955
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 2.15,
|
2773 |
+
"grad_norm": 0.20723703288940273,
|
2774 |
+
"learning_rate": 4.467575592946865e-06,
|
2775 |
+
"loss": 0.5353,
|
2776 |
+
"step": 1960
|
2777 |
+
},
|
2778 |
+
{
|
2779 |
+
"epoch": 2.16,
|
2780 |
+
"grad_norm": 0.20283509715409914,
|
2781 |
+
"learning_rate": 4.414432801590703e-06,
|
2782 |
+
"loss": 0.5253,
|
2783 |
+
"step": 1965
|
2784 |
+
},
|
2785 |
+
{
|
2786 |
+
"epoch": 2.16,
|
2787 |
+
"grad_norm": 0.2052800409715183,
|
2788 |
+
"learning_rate": 4.361518304626366e-06,
|
2789 |
+
"loss": 0.5144,
|
2790 |
+
"step": 1970
|
2791 |
+
},
|
2792 |
+
{
|
2793 |
+
"epoch": 2.17,
|
2794 |
+
"grad_norm": 0.19650849856593194,
|
2795 |
+
"learning_rate": 4.308834264785483e-06,
|
2796 |
+
"loss": 0.515,
|
2797 |
+
"step": 1975
|
2798 |
+
},
|
2799 |
+
{
|
2800 |
+
"epoch": 2.18,
|
2801 |
+
"grad_norm": 0.20863894389929338,
|
2802 |
+
"learning_rate": 4.256382835380421e-06,
|
2803 |
+
"loss": 0.5202,
|
2804 |
+
"step": 1980
|
2805 |
+
},
|
2806 |
+
{
|
2807 |
+
"epoch": 2.18,
|
2808 |
+
"grad_norm": 0.20698871916210282,
|
2809 |
+
"learning_rate": 4.204166160216216e-06,
|
2810 |
+
"loss": 0.5341,
|
2811 |
+
"step": 1985
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 2.19,
|
2815 |
+
"grad_norm": 0.21288394644934694,
|
2816 |
+
"learning_rate": 4.1521863735030065e-06,
|
2817 |
+
"loss": 0.5428,
|
2818 |
+
"step": 1990
|
2819 |
+
},
|
2820 |
+
{
|
2821 |
+
"epoch": 2.19,
|
2822 |
+
"grad_norm": 0.21106167476818527,
|
2823 |
+
"learning_rate": 4.100445599768774e-06,
|
2824 |
+
"loss": 0.522,
|
2825 |
+
"step": 1995
|
2826 |
+
},
|
2827 |
+
{
|
2828 |
+
"epoch": 2.2,
|
2829 |
+
"grad_norm": 0.20964196528234977,
|
2830 |
+
"learning_rate": 4.048945953772504e-06,
|
2831 |
+
"loss": 0.5294,
|
2832 |
+
"step": 2000
|
2833 |
+
},
|
2834 |
+
{
|
2835 |
+
"epoch": 2.2,
|
2836 |
+
"grad_norm": 0.2186729758235947,
|
2837 |
+
"learning_rate": 3.99768954041778e-06,
|
2838 |
+
"loss": 0.5258,
|
2839 |
+
"step": 2005
|
2840 |
+
},
|
2841 |
+
{
|
2842 |
+
"epoch": 2.21,
|
2843 |
+
"grad_norm": 0.21074477316001103,
|
2844 |
+
"learning_rate": 3.946678454666719e-06,
|
2845 |
+
"loss": 0.5296,
|
2846 |
+
"step": 2010
|
2847 |
+
},
|
2848 |
+
{
|
2849 |
+
"epoch": 2.21,
|
2850 |
+
"grad_norm": 0.2082023730818782,
|
2851 |
+
"learning_rate": 3.89591478145437e-06,
|
2852 |
+
"loss": 0.5232,
|
2853 |
+
"step": 2015
|
2854 |
+
},
|
2855 |
+
{
|
2856 |
+
"epoch": 2.22,
|
2857 |
+
"grad_norm": 0.211665046662059,
|
2858 |
+
"learning_rate": 3.845400595603482e-06,
|
2859 |
+
"loss": 0.5325,
|
2860 |
+
"step": 2020
|
2861 |
+
},
|
2862 |
+
{
|
2863 |
+
"epoch": 2.23,
|
2864 |
+
"grad_norm": 0.20452212904152248,
|
2865 |
+
"learning_rate": 3.79513796173971e-06,
|
2866 |
+
"loss": 0.5208,
|
2867 |
+
"step": 2025
|
2868 |
+
},
|
2869 |
+
{
|
2870 |
+
"epoch": 2.23,
|
2871 |
+
"grad_norm": 0.20097361934014168,
|
2872 |
+
"learning_rate": 3.745128934207225e-06,
|
2873 |
+
"loss": 0.5154,
|
2874 |
+
"step": 2030
|
2875 |
+
},
|
2876 |
+
{
|
2877 |
+
"epoch": 2.24,
|
2878 |
+
"grad_norm": 0.20835101950643772,
|
2879 |
+
"learning_rate": 3.695375556984764e-06,
|
2880 |
+
"loss": 0.5221,
|
2881 |
+
"step": 2035
|
2882 |
+
},
|
2883 |
+
{
|
2884 |
+
"epoch": 2.24,
|
2885 |
+
"grad_norm": 0.20751752347710595,
|
2886 |
+
"learning_rate": 3.6458798636020477e-06,
|
2887 |
+
"loss": 0.5208,
|
2888 |
+
"step": 2040
|
2889 |
+
},
|
2890 |
+
{
|
2891 |
+
"epoch": 2.25,
|
2892 |
+
"grad_norm": 0.2083029476627408,
|
2893 |
+
"learning_rate": 3.59664387705672e-06,
|
2894 |
+
"loss": 0.524,
|
2895 |
+
"step": 2045
|
2896 |
+
},
|
2897 |
+
{
|
2898 |
+
"epoch": 2.25,
|
2899 |
+
"grad_norm": 0.20547050805474043,
|
2900 |
+
"learning_rate": 3.5476696097316253e-06,
|
2901 |
+
"loss": 0.5224,
|
2902 |
+
"step": 2050
|
2903 |
+
},
|
2904 |
+
{
|
2905 |
+
"epoch": 2.26,
|
2906 |
+
"grad_norm": 0.20721249112618484,
|
2907 |
+
"learning_rate": 3.4989590633125583e-06,
|
2908 |
+
"loss": 0.5335,
|
2909 |
+
"step": 2055
|
2910 |
+
},
|
2911 |
+
{
|
2912 |
+
"epoch": 2.26,
|
2913 |
+
"grad_norm": 0.2084694829774017,
|
2914 |
+
"learning_rate": 3.450514228706482e-06,
|
2915 |
+
"loss": 0.5229,
|
2916 |
+
"step": 2060
|
2917 |
+
},
|
2918 |
+
{
|
2919 |
+
"epoch": 2.27,
|
2920 |
+
"grad_norm": 0.20216282130770613,
|
2921 |
+
"learning_rate": 3.4023370859601192e-06,
|
2922 |
+
"loss": 0.5375,
|
2923 |
+
"step": 2065
|
2924 |
+
},
|
2925 |
+
{
|
2926 |
+
"epoch": 2.27,
|
2927 |
+
"grad_norm": 0.2036489936294621,
|
2928 |
+
"learning_rate": 3.3544296041790457e-06,
|
2929 |
+
"loss": 0.5123,
|
2930 |
+
"step": 2070
|
2931 |
+
},
|
2932 |
+
{
|
2933 |
+
"epoch": 2.28,
|
2934 |
+
"grad_norm": 0.20447914104651402,
|
2935 |
+
"learning_rate": 3.3067937414471986e-06,
|
2936 |
+
"loss": 0.5283,
|
2937 |
+
"step": 2075
|
2938 |
+
},
|
2939 |
+
{
|
2940 |
+
"epoch": 2.29,
|
2941 |
+
"grad_norm": 0.20966243005652113,
|
2942 |
+
"learning_rate": 3.2594314447468457e-06,
|
2943 |
+
"loss": 0.5207,
|
2944 |
+
"step": 2080
|
2945 |
+
},
|
2946 |
+
{
|
2947 |
+
"epoch": 2.29,
|
2948 |
+
"grad_norm": 0.20579910881393176,
|
2949 |
+
"learning_rate": 3.2123446498790214e-06,
|
2950 |
+
"loss": 0.518,
|
2951 |
+
"step": 2085
|
2952 |
+
},
|
2953 |
+
{
|
2954 |
+
"epoch": 2.3,
|
2955 |
+
"grad_norm": 0.19982035514392868,
|
2956 |
+
"learning_rate": 3.1655352813843886e-06,
|
2957 |
+
"loss": 0.53,
|
2958 |
+
"step": 2090
|
2959 |
+
},
|
2960 |
+
{
|
2961 |
+
"epoch": 2.3,
|
2962 |
+
"grad_norm": 0.2114271078042674,
|
2963 |
+
"learning_rate": 3.1190052524645752e-06,
|
2964 |
+
"loss": 0.5297,
|
2965 |
+
"step": 2095
|
2966 |
+
},
|
2967 |
+
{
|
2968 |
+
"epoch": 2.31,
|
2969 |
+
"grad_norm": 0.20832244818822046,
|
2970 |
+
"learning_rate": 3.0727564649040066e-06,
|
2971 |
+
"loss": 0.5102,
|
2972 |
+
"step": 2100
|
2973 |
+
},
|
2974 |
+
{
|
2975 |
+
"epoch": 2.31,
|
2976 |
+
"grad_norm": 0.2008612540571781,
|
2977 |
+
"learning_rate": 3.0267908089921438e-06,
|
2978 |
+
"loss": 0.525,
|
2979 |
+
"step": 2105
|
2980 |
+
},
|
2981 |
+
{
|
2982 |
+
"epoch": 2.32,
|
2983 |
+
"grad_norm": 0.21335420821701767,
|
2984 |
+
"learning_rate": 2.9811101634462414e-06,
|
2985 |
+
"loss": 0.5161,
|
2986 |
+
"step": 2110
|
2987 |
+
},
|
2988 |
+
{
|
2989 |
+
"epoch": 2.32,
|
2990 |
+
"grad_norm": 0.20450727458510107,
|
2991 |
+
"learning_rate": 2.93571639533455e-06,
|
2992 |
+
"loss": 0.5139,
|
2993 |
+
"step": 2115
|
2994 |
+
},
|
2995 |
+
{
|
2996 |
+
"epoch": 2.33,
|
2997 |
+
"grad_norm": 0.213686615068082,
|
2998 |
+
"learning_rate": 2.8906113600000153e-06,
|
2999 |
+
"loss": 0.5203,
|
3000 |
+
"step": 2120
|
3001 |
+
},
|
3002 |
+
{
|
3003 |
+
"epoch": 2.34,
|
3004 |
+
"grad_norm": 0.20772690016178588,
|
3005 |
+
"learning_rate": 2.8457969009844354e-06,
|
3006 |
+
"loss": 0.5437,
|
3007 |
+
"step": 2125
|
3008 |
+
},
|
3009 |
+
{
|
3010 |
+
"epoch": 2.34,
|
3011 |
+
"grad_norm": 0.20632381814936407,
|
3012 |
+
"learning_rate": 2.8012748499531195e-06,
|
3013 |
+
"loss": 0.5318,
|
3014 |
+
"step": 2130
|
3015 |
+
},
|
3016 |
+
{
|
3017 |
+
"epoch": 2.35,
|
3018 |
+
"grad_norm": 0.2016664102243559,
|
3019 |
+
"learning_rate": 2.7570470266200177e-06,
|
3020 |
+
"loss": 0.5165,
|
3021 |
+
"step": 2135
|
3022 |
+
},
|
3023 |
+
{
|
3024 |
+
"epoch": 2.35,
|
3025 |
+
"grad_norm": 0.20520163431623825,
|
3026 |
+
"learning_rate": 2.713115238673356e-06,
|
3027 |
+
"loss": 0.5193,
|
3028 |
+
"step": 2140
|
3029 |
+
},
|
3030 |
+
{
|
3031 |
+
"epoch": 2.36,
|
3032 |
+
"grad_norm": 0.214071163971577,
|
3033 |
+
"learning_rate": 2.669481281701739e-06,
|
3034 |
+
"loss": 0.5268,
|
3035 |
+
"step": 2145
|
3036 |
+
},
|
3037 |
+
{
|
3038 |
+
"epoch": 2.36,
|
3039 |
+
"grad_norm": 0.20652575043829738,
|
3040 |
+
"learning_rate": 2.626146939120757e-06,
|
3041 |
+
"loss": 0.5176,
|
3042 |
+
"step": 2150
|
3043 |
+
},
|
3044 |
+
{
|
3045 |
+
"epoch": 2.37,
|
3046 |
+
"grad_norm": 0.20623703636177199,
|
3047 |
+
"learning_rate": 2.5831139821001184e-06,
|
3048 |
+
"loss": 0.5194,
|
3049 |
+
"step": 2155
|
3050 |
+
},
|
3051 |
+
{
|
3052 |
+
"epoch": 2.37,
|
3053 |
+
"grad_norm": 0.2073488736443259,
|
3054 |
+
"learning_rate": 2.5403841694912333e-06,
|
3055 |
+
"loss": 0.521,
|
3056 |
+
"step": 2160
|
3057 |
+
},
|
3058 |
+
{
|
3059 |
+
"epoch": 2.38,
|
3060 |
+
"grad_norm": 0.20428316103740377,
|
3061 |
+
"learning_rate": 2.497959247755335e-06,
|
3062 |
+
"loss": 0.522,
|
3063 |
+
"step": 2165
|
3064 |
+
},
|
3065 |
+
{
|
3066 |
+
"epoch": 2.38,
|
3067 |
+
"grad_norm": 0.20624815834176138,
|
3068 |
+
"learning_rate": 2.455840950892099e-06,
|
3069 |
+
"loss": 0.5338,
|
3070 |
+
"step": 2170
|
3071 |
+
},
|
3072 |
+
{
|
3073 |
+
"epoch": 2.39,
|
3074 |
+
"grad_norm": 0.2107922125349263,
|
3075 |
+
"learning_rate": 2.414031000368767e-06,
|
3076 |
+
"loss": 0.5381,
|
3077 |
+
"step": 2175
|
3078 |
+
},
|
3079 |
+
{
|
3080 |
+
"epoch": 2.4,
|
3081 |
+
"grad_norm": 0.20453939515184638,
|
3082 |
+
"learning_rate": 2.372531105049789e-06,
|
3083 |
+
"loss": 0.5183,
|
3084 |
+
"step": 2180
|
3085 |
+
},
|
3086 |
+
{
|
3087 |
+
"epoch": 2.4,
|
3088 |
+
"grad_norm": 0.19793223071462618,
|
3089 |
+
"learning_rate": 2.331342961126988e-06,
|
3090 |
+
"loss": 0.5113,
|
3091 |
+
"step": 2185
|
3092 |
+
},
|
3093 |
+
{
|
3094 |
+
"epoch": 2.41,
|
3095 |
+
"grad_norm": 0.21378964248804647,
|
3096 |
+
"learning_rate": 2.290468252050204e-06,
|
3097 |
+
"loss": 0.5296,
|
3098 |
+
"step": 2190
|
3099 |
+
},
|
3100 |
+
{
|
3101 |
+
"epoch": 2.41,
|
3102 |
+
"grad_norm": 0.22063310823848487,
|
3103 |
+
"learning_rate": 2.2499086484585255e-06,
|
3104 |
+
"loss": 0.5169,
|
3105 |
+
"step": 2195
|
3106 |
+
},
|
3107 |
+
{
|
3108 |
+
"epoch": 2.42,
|
3109 |
+
"grad_norm": 0.20381232643959812,
|
3110 |
+
"learning_rate": 2.2096658081119793e-06,
|
3111 |
+
"loss": 0.5196,
|
3112 |
+
"step": 2200
|
3113 |
+
},
|
3114 |
+
{
|
3115 |
+
"epoch": 2.42,
|
3116 |
+
"grad_norm": 0.21044163878960068,
|
3117 |
+
"learning_rate": 2.1697413758237785e-06,
|
3118 |
+
"loss": 0.5373,
|
3119 |
+
"step": 2205
|
3120 |
+
},
|
3121 |
+
{
|
3122 |
+
"epoch": 2.43,
|
3123 |
+
"grad_norm": 0.20577762743347522,
|
3124 |
+
"learning_rate": 2.130136983393112e-06,
|
3125 |
+
"loss": 0.5095,
|
3126 |
+
"step": 2210
|
3127 |
+
},
|
3128 |
+
{
|
3129 |
+
"epoch": 2.43,
|
3130 |
+
"grad_norm": 0.20351905534806264,
|
3131 |
+
"learning_rate": 2.0908542495384276e-06,
|
3132 |
+
"loss": 0.5238,
|
3133 |
+
"step": 2215
|
3134 |
+
},
|
3135 |
+
{
|
3136 |
+
"epoch": 2.44,
|
3137 |
+
"grad_norm": 0.19865856316493957,
|
3138 |
+
"learning_rate": 2.051894779831286e-06,
|
3139 |
+
"loss": 0.516,
|
3140 |
+
"step": 2220
|
3141 |
+
},
|
3142 |
+
{
|
3143 |
+
"epoch": 2.45,
|
3144 |
+
"grad_norm": 0.19763372174700705,
|
3145 |
+
"learning_rate": 2.0132601666307295e-06,
|
3146 |
+
"loss": 0.5073,
|
3147 |
+
"step": 2225
|
3148 |
+
},
|
3149 |
+
{
|
3150 |
+
"epoch": 2.45,
|
3151 |
+
"grad_norm": 0.19981546411123563,
|
3152 |
+
"learning_rate": 1.9749519890182035e-06,
|
3153 |
+
"loss": 0.5233,
|
3154 |
+
"step": 2230
|
3155 |
+
},
|
3156 |
+
{
|
3157 |
+
"epoch": 2.46,
|
3158 |
+
"grad_norm": 0.2033638338024947,
|
3159 |
+
"learning_rate": 1.936971812733012e-06,
|
3160 |
+
"loss": 0.5023,
|
3161 |
+
"step": 2235
|
3162 |
+
},
|
3163 |
+
{
|
3164 |
+
"epoch": 2.46,
|
3165 |
+
"grad_norm": 0.20822189802082794,
|
3166 |
+
"learning_rate": 1.8993211901083353e-06,
|
3167 |
+
"loss": 0.5009,
|
3168 |
+
"step": 2240
|
3169 |
+
},
|
3170 |
+
{
|
3171 |
+
"epoch": 2.47,
|
3172 |
+
"grad_norm": 0.2079466895136193,
|
3173 |
+
"learning_rate": 1.8620016600077516e-06,
|
3174 |
+
"loss": 0.5256,
|
3175 |
+
"step": 2245
|
3176 |
+
},
|
3177 |
+
{
|
3178 |
+
"epoch": 2.47,
|
3179 |
+
"grad_norm": 0.20439899215227353,
|
3180 |
+
"learning_rate": 1.8250147477623836e-06,
|
3181 |
+
"loss": 0.5365,
|
3182 |
+
"step": 2250
|
3183 |
+
},
|
3184 |
+
{
|
3185 |
+
"epoch": 2.48,
|
3186 |
+
"grad_norm": 0.22075705014027322,
|
3187 |
+
"learning_rate": 1.7883619651085194e-06,
|
3188 |
+
"loss": 0.5168,
|
3189 |
+
"step": 2255
|
3190 |
+
},
|
3191 |
+
{
|
3192 |
+
"epoch": 2.48,
|
3193 |
+
"grad_norm": 0.1964170868119619,
|
3194 |
+
"learning_rate": 1.7520448101258325e-06,
|
3195 |
+
"loss": 0.5173,
|
3196 |
+
"step": 2260
|
3197 |
+
},
|
3198 |
+
{
|
3199 |
+
"epoch": 2.49,
|
3200 |
+
"grad_norm": 0.2018340951265649,
|
3201 |
+
"learning_rate": 1.716064767176172e-06,
|
3202 |
+
"loss": 0.5208,
|
3203 |
+
"step": 2265
|
3204 |
+
},
|
3205 |
+
{
|
3206 |
+
"epoch": 2.49,
|
3207 |
+
"grad_norm": 0.20205110525587222,
|
3208 |
+
"learning_rate": 1.6804233068428678e-06,
|
3209 |
+
"loss": 0.5321,
|
3210 |
+
"step": 2270
|
3211 |
+
},
|
3212 |
+
{
|
3213 |
+
"epoch": 2.5,
|
3214 |
+
"grad_norm": 0.21357970053476708,
|
3215 |
+
"learning_rate": 1.6451218858706374e-06,
|
3216 |
+
"loss": 0.5203,
|
3217 |
+
"step": 2275
|
3218 |
+
},
|
3219 |
+
{
|
3220 |
+
"epoch": 2.51,
|
3221 |
+
"grad_norm": 0.2060738726003442,
|
3222 |
+
"learning_rate": 1.6101619471060415e-06,
|
3223 |
+
"loss": 0.5206,
|
3224 |
+
"step": 2280
|
3225 |
+
},
|
3226 |
+
{
|
3227 |
+
"epoch": 2.51,
|
3228 |
+
"grad_norm": 0.20422451049362417,
|
3229 |
+
"learning_rate": 1.5755449194385164e-06,
|
3230 |
+
"loss": 0.5183,
|
3231 |
+
"step": 2285
|
3232 |
+
},
|
3233 |
+
{
|
3234 |
+
"epoch": 2.52,
|
3235 |
+
"grad_norm": 0.2002944726641853,
|
3236 |
+
"learning_rate": 1.5412722177419658e-06,
|
3237 |
+
"loss": 0.5315,
|
3238 |
+
"step": 2290
|
3239 |
+
},
|
3240 |
+
{
|
3241 |
+
"epoch": 2.52,
|
3242 |
+
"grad_norm": 0.20080246126740545,
|
3243 |
+
"learning_rate": 1.5073452428169444e-06,
|
3244 |
+
"loss": 0.5302,
|
3245 |
+
"step": 2295
|
3246 |
+
},
|
3247 |
+
{
|
3248 |
+
"epoch": 2.53,
|
3249 |
+
"grad_norm": 0.20361752591083399,
|
3250 |
+
"learning_rate": 1.4737653813333774e-06,
|
3251 |
+
"loss": 0.5178,
|
3252 |
+
"step": 2300
|
3253 |
+
},
|
3254 |
+
{
|
3255 |
+
"epoch": 2.53,
|
3256 |
+
"grad_norm": 0.19999788848075653,
|
3257 |
+
"learning_rate": 1.4405340057739203e-06,
|
3258 |
+
"loss": 0.5192,
|
3259 |
+
"step": 2305
|
3260 |
+
},
|
3261 |
+
{
|
3262 |
+
"epoch": 2.54,
|
3263 |
+
"grad_norm": 0.1959282126715599,
|
3264 |
+
"learning_rate": 1.407652474377832e-06,
|
3265 |
+
"loss": 0.5156,
|
3266 |
+
"step": 2310
|
3267 |
+
},
|
3268 |
+
{
|
3269 |
+
"epoch": 2.54,
|
3270 |
+
"grad_norm": 0.20774381542552106,
|
3271 |
+
"learning_rate": 1.3751221310854778e-06,
|
3272 |
+
"loss": 0.5056,
|
3273 |
+
"step": 2315
|
3274 |
+
},
|
3275 |
+
{
|
3276 |
+
"epoch": 2.55,
|
3277 |
+
"grad_norm": 0.2038197815633597,
|
3278 |
+
"learning_rate": 1.3429443054833913e-06,
|
3279 |
+
"loss": 0.5265,
|
3280 |
+
"step": 2320
|
3281 |
+
},
|
3282 |
+
{
|
3283 |
+
"epoch": 2.55,
|
3284 |
+
"grad_norm": 0.20325668884167009,
|
3285 |
+
"learning_rate": 1.311120312749935e-06,
|
3286 |
+
"loss": 0.5234,
|
3287 |
+
"step": 2325
|
3288 |
+
},
|
3289 |
+
{
|
3290 |
+
"epoch": 2.56,
|
3291 |
+
"grad_norm": 0.20390134033380405,
|
3292 |
+
"learning_rate": 1.2796514536015492e-06,
|
3293 |
+
"loss": 0.5368,
|
3294 |
+
"step": 2330
|
3295 |
+
},
|
3296 |
+
{
|
3297 |
+
"epoch": 2.57,
|
3298 |
+
"grad_norm": 0.20166563167725796,
|
3299 |
+
"learning_rate": 1.2485390142395793e-06,
|
3300 |
+
"loss": 0.5205,
|
3301 |
+
"step": 2335
|
3302 |
+
},
|
3303 |
+
{
|
3304 |
+
"epoch": 2.57,
|
3305 |
+
"grad_norm": 0.2022982713597928,
|
3306 |
+
"learning_rate": 1.2177842662977136e-06,
|
3307 |
+
"loss": 0.5231,
|
3308 |
+
"step": 2340
|
3309 |
+
},
|
3310 |
+
{
|
3311 |
+
"epoch": 2.58,
|
3312 |
+
"grad_norm": 0.21218295817596197,
|
3313 |
+
"learning_rate": 1.1873884667900125e-06,
|
3314 |
+
"loss": 0.5439,
|
3315 |
+
"step": 2345
|
3316 |
+
},
|
3317 |
+
{
|
3318 |
+
"epoch": 2.58,
|
3319 |
+
"grad_norm": 0.20473864934409344,
|
3320 |
+
"learning_rate": 1.1573528580595195e-06,
|
3321 |
+
"loss": 0.521,
|
3322 |
+
"step": 2350
|
3323 |
+
},
|
3324 |
+
{
|
3325 |
+
"epoch": 2.59,
|
3326 |
+
"grad_norm": 0.20949092154655793,
|
3327 |
+
"learning_rate": 1.1276786677274866e-06,
|
3328 |
+
"loss": 0.5105,
|
3329 |
+
"step": 2355
|
3330 |
+
},
|
3331 |
+
{
|
3332 |
+
"epoch": 2.59,
|
3333 |
+
"grad_norm": 0.20094255278913592,
|
3334 |
+
"learning_rate": 1.0983671086432146e-06,
|
3335 |
+
"loss": 0.5128,
|
3336 |
+
"step": 2360
|
3337 |
+
},
|
3338 |
+
{
|
3339 |
+
"epoch": 2.6,
|
3340 |
+
"grad_norm": 0.2057662784043456,
|
3341 |
+
"learning_rate": 1.069419378834461e-06,
|
3342 |
+
"loss": 0.5385,
|
3343 |
+
"step": 2365
|
3344 |
+
},
|
3345 |
+
{
|
3346 |
+
"epoch": 2.6,
|
3347 |
+
"grad_norm": 0.20176044390537098,
|
3348 |
+
"learning_rate": 1.040836661458482e-06,
|
3349 |
+
"loss": 0.5171,
|
3350 |
+
"step": 2370
|
3351 |
+
},
|
3352 |
+
{
|
3353 |
+
"epoch": 2.61,
|
3354 |
+
"grad_norm": 0.21932275472178112,
|
3355 |
+
"learning_rate": 1.0126201247536783e-06,
|
3356 |
+
"loss": 0.528,
|
3357 |
+
"step": 2375
|
3358 |
+
},
|
3359 |
+
{
|
3360 |
+
"epoch": 2.62,
|
3361 |
+
"grad_norm": 0.19746784289323338,
|
3362 |
+
"learning_rate": 9.8477092199184e-07,
|
3363 |
+
"loss": 0.511,
|
3364 |
+
"step": 2380
|
3365 |
+
},
|
3366 |
+
{
|
3367 |
+
"epoch": 2.62,
|
3368 |
+
"grad_norm": 0.20034469208109756,
|
3369 |
+
"learning_rate": 9.57290191431013e-07,
|
3370 |
+
"loss": 0.5227,
|
3371 |
+
"step": 2385
|
3372 |
+
},
|
3373 |
+
{
|
3374 |
+
"epoch": 2.63,
|
3375 |
+
"grad_norm": 0.20104497306207902,
|
3376 |
+
"learning_rate": 9.301790562689794e-07,
|
3377 |
+
"loss": 0.5277,
|
3378 |
+
"step": 2390
|
3379 |
+
},
|
3380 |
+
{
|
3381 |
+
"epoch": 2.63,
|
3382 |
+
"grad_norm": 0.1972303787668993,
|
3383 |
+
"learning_rate": 9.034386245973359e-07,
|
3384 |
+
"loss": 0.5147,
|
3385 |
+
"step": 2395
|
3386 |
+
},
|
3387 |
+
{
|
3388 |
+
"epoch": 2.64,
|
3389 |
+
"grad_norm": 0.20641734055273483,
|
3390 |
+
"learning_rate": 8.770699893562273e-07,
|
3391 |
+
"loss": 0.5256,
|
3392 |
+
"step": 2400
|
3393 |
+
},
|
3394 |
+
{
|
3395 |
+
"epoch": 2.64,
|
3396 |
+
"grad_norm": 0.2083707616895028,
|
3397 |
+
"learning_rate": 8.510742282896545e-07,
|
3398 |
+
"loss": 0.5154,
|
3399 |
+
"step": 2405
|
3400 |
+
},
|
3401 |
+
{
|
3402 |
+
"epoch": 2.65,
|
3403 |
+
"grad_norm": 0.20003452385731113,
|
3404 |
+
"learning_rate": 8.254524039014289e-07,
|
3405 |
+
"loss": 0.5333,
|
3406 |
+
"step": 2410
|
3407 |
+
},
|
3408 |
+
{
|
3409 |
+
"epoch": 2.65,
|
3410 |
+
"grad_norm": 0.20109885864318555,
|
3411 |
+
"learning_rate": 8.002055634117578e-07,
|
3412 |
+
"loss": 0.5088,
|
3413 |
+
"step": 2415
|
3414 |
+
},
|
3415 |
+
{
|
3416 |
+
"epoch": 2.66,
|
3417 |
+
"grad_norm": 0.20645302721542735,
|
3418 |
+
"learning_rate": 7.753347387144294e-07,
|
3419 |
+
"loss": 0.5126,
|
3420 |
+
"step": 2420
|
3421 |
+
},
|
3422 |
+
{
|
3423 |
+
"epoch": 2.66,
|
3424 |
+
"grad_norm": 0.20323590104576408,
|
3425 |
+
"learning_rate": 7.508409463346389e-07,
|
3426 |
+
"loss": 0.5234,
|
3427 |
+
"step": 2425
|
3428 |
+
},
|
3429 |
+
{
|
3430 |
+
"epoch": 2.67,
|
3431 |
+
"grad_norm": 0.20483041641048474,
|
3432 |
+
"learning_rate": 7.26725187387446e-07,
|
3433 |
+
"loss": 0.5207,
|
3434 |
+
"step": 2430
|
3435 |
+
},
|
3436 |
+
{
|
3437 |
+
"epoch": 2.68,
|
3438 |
+
"grad_norm": 0.20363185231425762,
|
3439 |
+
"learning_rate": 7.029884475368542e-07,
|
3440 |
+
"loss": 0.5234,
|
3441 |
+
"step": 2435
|
3442 |
+
},
|
3443 |
+
{
|
3444 |
+
"epoch": 2.68,
|
3445 |
+
"grad_norm": 0.19585624352673048,
|
3446 |
+
"learning_rate": 6.796316969555205e-07,
|
3447 |
+
"loss": 0.516,
|
3448 |
+
"step": 2440
|
3449 |
+
},
|
3450 |
+
{
|
3451 |
+
"epoch": 2.69,
|
3452 |
+
"grad_norm": 0.21163098285472737,
|
3453 |
+
"learning_rate": 6.566558902851161e-07,
|
3454 |
+
"loss": 0.5382,
|
3455 |
+
"step": 2445
|
3456 |
+
},
|
3457 |
+
{
|
3458 |
+
"epoch": 2.69,
|
3459 |
+
"grad_norm": 0.2061275767234072,
|
3460 |
+
"learning_rate": 6.340619665972847e-07,
|
3461 |
+
"loss": 0.5252,
|
3462 |
+
"step": 2450
|
3463 |
+
},
|
3464 |
+
{
|
3465 |
+
"epoch": 2.7,
|
3466 |
+
"grad_norm": 0.2050927030534903,
|
3467 |
+
"learning_rate": 6.118508493552866e-07,
|
3468 |
+
"loss": 0.5081,
|
3469 |
+
"step": 2455
|
3470 |
+
},
|
3471 |
+
{
|
3472 |
+
"epoch": 2.7,
|
3473 |
+
"grad_norm": 0.20411513952463778,
|
3474 |
+
"learning_rate": 5.900234463762367e-07,
|
3475 |
+
"loss": 0.5248,
|
3476 |
+
"step": 2460
|
3477 |
+
},
|
3478 |
+
{
|
3479 |
+
"epoch": 2.71,
|
3480 |
+
"grad_norm": 0.20399794959320638,
|
3481 |
+
"learning_rate": 5.685806497940027e-07,
|
3482 |
+
"loss": 0.5163,
|
3483 |
+
"step": 2465
|
3484 |
+
},
|
3485 |
+
{
|
3486 |
+
"epoch": 2.71,
|
3487 |
+
"grad_norm": 0.20891752353282228,
|
3488 |
+
"learning_rate": 5.475233360227516e-07,
|
3489 |
+
"loss": 0.529,
|
3490 |
+
"step": 2470
|
3491 |
+
},
|
3492 |
+
{
|
3493 |
+
"epoch": 2.72,
|
3494 |
+
"grad_norm": 0.2005044795674912,
|
3495 |
+
"learning_rate": 5.268523657211188e-07,
|
3496 |
+
"loss": 0.5009,
|
3497 |
+
"step": 2475
|
3498 |
+
},
|
3499 |
+
{
|
3500 |
+
"epoch": 2.73,
|
3501 |
+
"grad_norm": 0.2046930603550785,
|
3502 |
+
"learning_rate": 5.065685837570312e-07,
|
3503 |
+
"loss": 0.5165,
|
3504 |
+
"step": 2480
|
3505 |
+
},
|
3506 |
+
{
|
3507 |
+
"epoch": 2.73,
|
3508 |
+
"grad_norm": 0.20175610856641593,
|
3509 |
+
"learning_rate": 4.866728191731829e-07,
|
3510 |
+
"loss": 0.5182,
|
3511 |
+
"step": 2485
|
3512 |
+
},
|
3513 |
+
{
|
3514 |
+
"epoch": 2.74,
|
3515 |
+
"grad_norm": 0.2030309299250094,
|
3516 |
+
"learning_rate": 4.671658851531424e-07,
|
3517 |
+
"loss": 0.5199,
|
3518 |
+
"step": 2490
|
3519 |
+
},
|
3520 |
+
{
|
3521 |
+
"epoch": 2.74,
|
3522 |
+
"grad_norm": 0.1914622288737903,
|
3523 |
+
"learning_rate": 4.480485789881217e-07,
|
3524 |
+
"loss": 0.5177,
|
3525 |
+
"step": 2495
|
3526 |
+
},
|
3527 |
+
{
|
3528 |
+
"epoch": 2.75,
|
3529 |
+
"grad_norm": 0.19668048668936855,
|
3530 |
+
"learning_rate": 4.293216820443891e-07,
|
3531 |
+
"loss": 0.5308,
|
3532 |
+
"step": 2500
|
3533 |
+
},
|
3534 |
+
{
|
3535 |
+
"epoch": 2.75,
|
3536 |
+
"grad_norm": 0.22039481521735169,
|
3537 |
+
"learning_rate": 4.109859597313237e-07,
|
3538 |
+
"loss": 0.5283,
|
3539 |
+
"step": 2505
|
3540 |
+
},
|
3541 |
+
{
|
3542 |
+
"epoch": 2.76,
|
3543 |
+
"grad_norm": 0.20757846010886538,
|
3544 |
+
"learning_rate": 3.9304216147014853e-07,
|
3545 |
+
"loss": 0.5347,
|
3546 |
+
"step": 2510
|
3547 |
+
},
|
3548 |
+
{
|
3549 |
+
"epoch": 2.76,
|
3550 |
+
"grad_norm": 0.20740377627342962,
|
3551 |
+
"learning_rate": 3.7549102066328226e-07,
|
3552 |
+
"loss": 0.5307,
|
3553 |
+
"step": 2515
|
3554 |
+
},
|
3555 |
+
{
|
3556 |
+
"epoch": 2.77,
|
3557 |
+
"grad_norm": 0.2100472925176084,
|
3558 |
+
"learning_rate": 3.5833325466437697e-07,
|
3559 |
+
"loss": 0.5223,
|
3560 |
+
"step": 2520
|
3561 |
+
},
|
3562 |
+
{
|
3563 |
+
"epoch": 2.77,
|
3564 |
+
"grad_norm": 0.20177360779386036,
|
3565 |
+
"learning_rate": 3.4156956474898805e-07,
|
3566 |
+
"loss": 0.5255,
|
3567 |
+
"step": 2525
|
3568 |
+
},
|
3569 |
+
{
|
3570 |
+
"epoch": 2.78,
|
3571 |
+
"grad_norm": 0.20707380368033076,
|
3572 |
+
"learning_rate": 3.2520063608592165e-07,
|
3573 |
+
"loss": 0.5122,
|
3574 |
+
"step": 2530
|
3575 |
+
},
|
3576 |
+
{
|
3577 |
+
"epoch": 2.79,
|
3578 |
+
"grad_norm": 0.19965994990493274,
|
3579 |
+
"learning_rate": 3.0922713770922155e-07,
|
3580 |
+
"loss": 0.5214,
|
3581 |
+
"step": 2535
|
3582 |
+
},
|
3583 |
+
{
|
3584 |
+
"epoch": 2.79,
|
3585 |
+
"grad_norm": 0.20324516199000714,
|
3586 |
+
"learning_rate": 2.9364972249082747e-07,
|
3587 |
+
"loss": 0.5145,
|
3588 |
+
"step": 2540
|
3589 |
+
},
|
3590 |
+
{
|
3591 |
+
"epoch": 2.8,
|
3592 |
+
"grad_norm": 0.20150097372860662,
|
3593 |
+
"learning_rate": 2.7846902711389236e-07,
|
3594 |
+
"loss": 0.5132,
|
3595 |
+
"step": 2545
|
3596 |
+
},
|
3597 |
+
{
|
3598 |
+
"epoch": 2.8,
|
3599 |
+
"grad_norm": 0.2051450132081192,
|
3600 |
+
"learning_rate": 2.636856720467573e-07,
|
3601 |
+
"loss": 0.5128,
|
3602 |
+
"step": 2550
|
3603 |
+
},
|
3604 |
+
{
|
3605 |
+
"epoch": 2.81,
|
3606 |
+
"grad_norm": 0.20266490344541718,
|
3607 |
+
"learning_rate": 2.493002615175977e-07,
|
3608 |
+
"loss": 0.5122,
|
3609 |
+
"step": 2555
|
3610 |
+
},
|
3611 |
+
{
|
3612 |
+
"epoch": 2.81,
|
3613 |
+
"grad_norm": 0.20236603858533658,
|
3614 |
+
"learning_rate": 2.3531338348971366e-07,
|
3615 |
+
"loss": 0.5327,
|
3616 |
+
"step": 2560
|
3617 |
+
},
|
3618 |
+
{
|
3619 |
+
"epoch": 2.82,
|
3620 |
+
"grad_norm": 0.20530608079603682,
|
3621 |
+
"learning_rate": 2.217256096375131e-07,
|
3622 |
+
"loss": 0.5099,
|
3623 |
+
"step": 2565
|
3624 |
+
},
|
3625 |
+
{
|
3626 |
+
"epoch": 2.82,
|
3627 |
+
"grad_norm": 0.2000522109375465,
|
3628 |
+
"learning_rate": 2.0853749532314006e-07,
|
3629 |
+
"loss": 0.5299,
|
3630 |
+
"step": 2570
|
3631 |
+
},
|
3632 |
+
{
|
3633 |
+
"epoch": 2.83,
|
3634 |
+
"grad_norm": 0.20808661956102248,
|
3635 |
+
"learning_rate": 1.9574957957377294e-07,
|
3636 |
+
"loss": 0.5225,
|
3637 |
+
"step": 2575
|
3638 |
+
},
|
3639 |
+
{
|
3640 |
+
"epoch": 2.84,
|
3641 |
+
"grad_norm": 0.2026575467689292,
|
3642 |
+
"learning_rate": 1.8336238505959892e-07,
|
3643 |
+
"loss": 0.5286,
|
3644 |
+
"step": 2580
|
3645 |
+
},
|
3646 |
+
{
|
3647 |
+
"epoch": 2.84,
|
3648 |
+
"grad_norm": 0.2043520049010144,
|
3649 |
+
"learning_rate": 1.7137641807244754e-07,
|
3650 |
+
"loss": 0.5218,
|
3651 |
+
"step": 2585
|
3652 |
+
},
|
3653 |
+
{
|
3654 |
+
"epoch": 2.85,
|
3655 |
+
"grad_norm": 0.20057729109993613,
|
3656 |
+
"learning_rate": 1.5979216850509848e-07,
|
3657 |
+
"loss": 0.5225,
|
3658 |
+
"step": 2590
|
3659 |
+
},
|
3660 |
+
{
|
3661 |
+
"epoch": 2.85,
|
3662 |
+
"grad_norm": 0.20086887199752657,
|
3663 |
+
"learning_rate": 1.4861010983126202e-07,
|
3664 |
+
"loss": 0.521,
|
3665 |
+
"step": 2595
|
3666 |
+
},
|
3667 |
+
{
|
3668 |
+
"epoch": 2.86,
|
3669 |
+
"grad_norm": 0.20600288196892624,
|
3670 |
+
"learning_rate": 1.3783069908621772e-07,
|
3671 |
+
"loss": 0.5233,
|
3672 |
+
"step": 2600
|
3673 |
+
},
|
3674 |
+
{
|
3675 |
+
"epoch": 2.86,
|
3676 |
+
"grad_norm": 0.2032590701020277,
|
3677 |
+
"learning_rate": 1.274543768481451e-07,
|
3678 |
+
"loss": 0.5298,
|
3679 |
+
"step": 2605
|
3680 |
+
},
|
3681 |
+
{
|
3682 |
+
"epoch": 2.87,
|
3683 |
+
"grad_norm": 0.19937401805144794,
|
3684 |
+
"learning_rate": 1.1748156722011128e-07,
|
3685 |
+
"loss": 0.5012,
|
3686 |
+
"step": 2610
|
3687 |
+
},
|
3688 |
+
{
|
3689 |
+
"epoch": 2.87,
|
3690 |
+
"grad_norm": 0.2021678865177686,
|
3691 |
+
"learning_rate": 1.0791267781273263e-07,
|
3692 |
+
"loss": 0.5242,
|
3693 |
+
"step": 2615
|
3694 |
+
},
|
3695 |
+
{
|
3696 |
+
"epoch": 2.88,
|
3697 |
+
"grad_norm": 0.20777988223157803,
|
3698 |
+
"learning_rate": 9.874809972752697e-08,
|
3699 |
+
"loss": 0.5293,
|
3700 |
+
"step": 2620
|
3701 |
+
},
|
3702 |
+
{
|
3703 |
+
"epoch": 2.88,
|
3704 |
+
"grad_norm": 0.20368366862991866,
|
3705 |
+
"learning_rate": 8.99882075409153e-08,
|
3706 |
+
"loss": 0.5153,
|
3707 |
+
"step": 2625
|
3708 |
+
},
|
3709 |
+
{
|
3710 |
+
"epoch": 2.89,
|
3711 |
+
"grad_norm": 0.20787994510400237,
|
3712 |
+
"learning_rate": 8.16333592889207e-08,
|
3713 |
+
"loss": 0.5345,
|
3714 |
+
"step": 2630
|
3715 |
+
},
|
3716 |
+
{
|
3717 |
+
"epoch": 2.9,
|
3718 |
+
"grad_norm": 0.20946081246812162,
|
3719 |
+
"learning_rate": 7.368389645252772e-08,
|
3720 |
+
"loss": 0.5229,
|
3721 |
+
"step": 2635
|
3722 |
+
},
|
3723 |
+
{
|
3724 |
+
"epoch": 2.9,
|
3725 |
+
"grad_norm": 0.20571639236209135,
|
3726 |
+
"learning_rate": 6.61401439437348e-08,
|
3727 |
+
"loss": 0.5151,
|
3728 |
+
"step": 2640
|
3729 |
+
},
|
3730 |
+
{
|
3731 |
+
"epoch": 2.91,
|
3732 |
+
"grad_norm": 0.21182777269953695,
|
3733 |
+
"learning_rate": 5.9002410092262593e-08,
|
3734 |
+
"loss": 0.5207,
|
3735 |
+
"step": 2645
|
3736 |
+
},
|
3737 |
+
{
|
3738 |
+
"epoch": 2.91,
|
3739 |
+
"grad_norm": 0.1955808209671619,
|
3740 |
+
"learning_rate": 5.227098663296404e-08,
|
3741 |
+
"loss": 0.5073,
|
3742 |
+
"step": 2650
|
3743 |
+
},
|
3744 |
+
{
|
3745 |
+
"epoch": 2.92,
|
3746 |
+
"grad_norm": 0.20179292685793432,
|
3747 |
+
"learning_rate": 4.594614869388947e-08,
|
3748 |
+
"loss": 0.5212,
|
3749 |
+
"step": 2655
|
3750 |
+
},
|
3751 |
+
{
|
3752 |
+
"epoch": 2.92,
|
3753 |
+
"grad_norm": 0.20236344715337046,
|
3754 |
+
"learning_rate": 4.002815478505007e-08,
|
3755 |
+
"loss": 0.5208,
|
3756 |
+
"step": 2660
|
3757 |
+
},
|
3758 |
+
{
|
3759 |
+
"epoch": 2.93,
|
3760 |
+
"grad_norm": 0.2112521255560089,
|
3761 |
+
"learning_rate": 3.451724678784518e-08,
|
3762 |
+
"loss": 0.5155,
|
3763 |
+
"step": 2665
|
3764 |
+
},
|
3765 |
+
{
|
3766 |
+
"epoch": 2.93,
|
3767 |
+
"grad_norm": 0.1988319336416073,
|
3768 |
+
"learning_rate": 2.9413649945182475e-08,
|
3769 |
+
"loss": 0.5149,
|
3770 |
+
"step": 2670
|
3771 |
+
},
|
3772 |
+
{
|
3773 |
+
"epoch": 2.94,
|
3774 |
+
"grad_norm": 0.2393477878018782,
|
3775 |
+
"learning_rate": 2.47175728522675e-08,
|
3776 |
+
"loss": 0.5196,
|
3777 |
+
"step": 2675
|
3778 |
+
},
|
3779 |
+
{
|
3780 |
+
"epoch": 2.95,
|
3781 |
+
"grad_norm": 0.1989296468037607,
|
3782 |
+
"learning_rate": 2.0429207448078302e-08,
|
3783 |
+
"loss": 0.4954,
|
3784 |
+
"step": 2680
|
3785 |
+
},
|
3786 |
+
{
|
3787 |
+
"epoch": 2.95,
|
3788 |
+
"grad_norm": 0.21328717756995305,
|
3789 |
+
"learning_rate": 1.654872900752169e-08,
|
3790 |
+
"loss": 0.5211,
|
3791 |
+
"step": 2685
|
3792 |
+
},
|
3793 |
+
{
|
3794 |
+
"epoch": 2.96,
|
3795 |
+
"grad_norm": 0.2043004896942241,
|
3796 |
+
"learning_rate": 1.3076296134271194e-08,
|
3797 |
+
"loss": 0.5298,
|
3798 |
+
"step": 2690
|
3799 |
+
},
|
3800 |
+
{
|
3801 |
+
"epoch": 2.96,
|
3802 |
+
"grad_norm": 0.20203087493728625,
|
3803 |
+
"learning_rate": 1.0012050754277802e-08,
|
3804 |
+
"loss": 0.5142,
|
3805 |
+
"step": 2695
|
3806 |
+
},
|
3807 |
+
{
|
3808 |
+
"epoch": 2.97,
|
3809 |
+
"grad_norm": 0.20708771065311932,
|
3810 |
+
"learning_rate": 7.356118109977939e-09,
|
3811 |
+
"loss": 0.5352,
|
3812 |
+
"step": 2700
|
3813 |
+
},
|
3814 |
+
{
|
3815 |
+
"epoch": 2.97,
|
3816 |
+
"grad_norm": 0.20602452029141277,
|
3817 |
+
"learning_rate": 5.108606755168666e-09,
|
3818 |
+
"loss": 0.528,
|
3819 |
+
"step": 2705
|
3820 |
+
},
|
3821 |
+
{
|
3822 |
+
"epoch": 2.98,
|
3823 |
+
"grad_norm": 0.20878635383712413,
|
3824 |
+
"learning_rate": 3.269608550571235e-09,
|
3825 |
+
"loss": 0.5155,
|
3826 |
+
"step": 2710
|
3827 |
+
},
|
3828 |
+
{
|
3829 |
+
"epoch": 2.98,
|
3830 |
+
"grad_norm": 0.1972058695515002,
|
3831 |
+
"learning_rate": 1.839198660079644e-09,
|
3832 |
+
"loss": 0.5121,
|
3833 |
+
"step": 2715
|
3834 |
+
},
|
3835 |
+
{
|
3836 |
+
"epoch": 2.99,
|
3837 |
+
"grad_norm": 0.2017859212074039,
|
3838 |
+
"learning_rate": 8.174355476864293e-10,
|
3839 |
+
"loss": 0.5193,
|
3840 |
+
"step": 2720
|
3841 |
+
},
|
3842 |
+
{
|
3843 |
+
"epoch": 2.99,
|
3844 |
+
"grad_norm": 0.20180951712274753,
|
3845 |
+
"learning_rate": 2.0436097509235475e-10,
|
3846 |
+
"loss": 0.5331,
|
3847 |
+
"step": 2725
|
3848 |
+
},
|
3849 |
+
{
|
3850 |
+
"epoch": 3.0,
|
3851 |
+
"grad_norm": 0.2006750130728712,
|
3852 |
+
"learning_rate": 0.0,
|
3853 |
+
"loss": 0.5227,
|
3854 |
+
"step": 2730
|
3855 |
+
},
|
3856 |
+
{
|
3857 |
+
"epoch": 3.0,
|
3858 |
+
"eval_loss": 0.6613607406616211,
|
3859 |
+
"eval_runtime": 13.2749,
|
3860 |
+
"eval_samples_per_second": 103.805,
|
3861 |
+
"eval_steps_per_second": 0.829,
|
3862 |
+
"step": 2730
|
3863 |
+
},
|
3864 |
+
{
|
3865 |
+
"epoch": 3.0,
|
3866 |
+
"step": 2730,
|
3867 |
+
"total_flos": 1.183665069490176e+16,
|
3868 |
+
"train_loss": 0.6159939037574517,
|
3869 |
+
"train_runtime": 13745.4884,
|
3870 |
+
"train_samples_per_second": 25.399,
|
3871 |
+
"train_steps_per_second": 0.199
|
3872 |
+
}
|
3873 |
+
],
|
3874 |
+
"logging_steps": 5,
|
3875 |
+
"max_steps": 2730,
|
3876 |
+
"num_input_tokens_seen": 0,
|
3877 |
+
"num_train_epochs": 3,
|
3878 |
+
"save_steps": 100,
|
3879 |
+
"total_flos": 1.183665069490176e+16,
|
3880 |
+
"train_batch_size": 8,
|
3881 |
+
"trial_name": null,
|
3882 |
+
"trial_params": null
|
3883 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63228e190b2d1032f998e66c70c0651d7ad3fcdfc67be84ddc5308fe5644eca5
|
3 |
+
size 6520
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|