Qin Liu
commited on
Commit
•
c41e67c
1
Parent(s):
4259541
Model save
Browse files- README.md +59 -0
- all_results.json +9 -0
- generation_config.json +12 -0
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- train_results.json +9 -0
- trainer_state.json +924 -0
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
base_model: Jackie999/llama3-sudo-5epochs-tofu_full_sft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: llama3-sudo-sft-5epochs-forget10mix600-1sft-2sft
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# llama3-sudo-sft-5epochs-forget10mix600-1sft-2sft
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Jackie999/llama3-sudo-5epochs-tofu_full_sft](https://huggingface.co/Jackie999/llama3-sudo-5epochs-tofu_full_sft) on an unknown dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-05
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 4
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 4
|
| 43 |
+
- total_train_batch_size: 16
|
| 44 |
+
- total_eval_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 48 |
+
- num_epochs: 5
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- Transformers 4.44.0
|
| 57 |
+
- Pytorch 2.1.2
|
| 58 |
+
- Datasets 3.0.0
|
| 59 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 1839624683520.0,
|
| 4 |
+
"train_loss": 0.2137949773788452,
|
| 5 |
+
"train_runtime": 9889.1554,
|
| 6 |
+
"train_samples": 2000,
|
| 7 |
+
"train_samples_per_second": 1.011,
|
| 8 |
+
"train_steps_per_second": 0.063
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128009
|
| 7 |
+
],
|
| 8 |
+
"max_length": 4096,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.44.0"
|
| 12 |
+
}
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4976698672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:272b6274a72292e5d990da83fa13a7bc59e47ffc4ee91e81406d8e153d73696b
|
| 3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4999802720
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:29c21a4b37eea83b147103c1d4916699673f61cf6e3cecdfeb23171f70573ebd
|
| 3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4915916176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:700ce9240863851f6b0ba86e8ee806a4db734b436e068f46c547b0073cfd4f30
|
| 3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1168138808
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:555d41fe13ccebe8e1883727fac4bee5a4e7127c52f784f6b810001225c741e8
|
| 3 |
size 1168138808
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"total_flos": 1839624683520.0,
|
| 4 |
+
"train_loss": 0.2137949773788452,
|
| 5 |
+
"train_runtime": 9889.1554,
|
| 6 |
+
"train_samples": 2000,
|
| 7 |
+
"train_samples_per_second": 1.011,
|
| 8 |
+
"train_steps_per_second": 0.063
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,924 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 625,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.008,
|
| 13 |
+
"grad_norm": 76.32773843110532,
|
| 14 |
+
"learning_rate": 1.5873015873015874e-07,
|
| 15 |
+
"loss": 4.4795,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.04,
|
| 20 |
+
"grad_norm": 71.81150350946773,
|
| 21 |
+
"learning_rate": 7.936507936507937e-07,
|
| 22 |
+
"loss": 4.307,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"grad_norm": 42.999152941442446,
|
| 28 |
+
"learning_rate": 1.5873015873015873e-06,
|
| 29 |
+
"loss": 3.4849,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12,
|
| 34 |
+
"grad_norm": 46.44864615552445,
|
| 35 |
+
"learning_rate": 2.380952380952381e-06,
|
| 36 |
+
"loss": 1.5332,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.16,
|
| 41 |
+
"grad_norm": 5.770504948547854,
|
| 42 |
+
"learning_rate": 3.1746031746031746e-06,
|
| 43 |
+
"loss": 0.3264,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2,
|
| 48 |
+
"grad_norm": 3.383097613641565,
|
| 49 |
+
"learning_rate": 3.968253968253968e-06,
|
| 50 |
+
"loss": 0.195,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.24,
|
| 55 |
+
"grad_norm": 2.543807204293022,
|
| 56 |
+
"learning_rate": 4.761904761904762e-06,
|
| 57 |
+
"loss": 0.152,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.28,
|
| 62 |
+
"grad_norm": 2.071517230467083,
|
| 63 |
+
"learning_rate": 5.555555555555557e-06,
|
| 64 |
+
"loss": 0.1464,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.32,
|
| 69 |
+
"grad_norm": 3.1880730134020405,
|
| 70 |
+
"learning_rate": 6.349206349206349e-06,
|
| 71 |
+
"loss": 0.1532,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.36,
|
| 76 |
+
"grad_norm": 2.273945566819242,
|
| 77 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 78 |
+
"loss": 0.1477,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4,
|
| 83 |
+
"grad_norm": 2.8908492033026,
|
| 84 |
+
"learning_rate": 7.936507936507936e-06,
|
| 85 |
+
"loss": 0.1655,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.44,
|
| 90 |
+
"grad_norm": 1.408828965452355,
|
| 91 |
+
"learning_rate": 8.730158730158731e-06,
|
| 92 |
+
"loss": 0.163,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.48,
|
| 97 |
+
"grad_norm": 1.7147558780209895,
|
| 98 |
+
"learning_rate": 9.523809523809525e-06,
|
| 99 |
+
"loss": 0.1581,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.52,
|
| 104 |
+
"grad_norm": 2.3248153460703316,
|
| 105 |
+
"learning_rate": 9.999687519737639e-06,
|
| 106 |
+
"loss": 0.1587,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.56,
|
| 111 |
+
"grad_norm": 3.19958218992742,
|
| 112 |
+
"learning_rate": 9.996172565322375e-06,
|
| 113 |
+
"loss": 0.1782,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6,
|
| 118 |
+
"grad_norm": 2.3598525259461014,
|
| 119 |
+
"learning_rate": 9.988754811052616e-06,
|
| 120 |
+
"loss": 0.1708,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.64,
|
| 125 |
+
"grad_norm": 2.350384753086168,
|
| 126 |
+
"learning_rate": 9.97744005136599e-06,
|
| 127 |
+
"loss": 0.1676,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.68,
|
| 132 |
+
"grad_norm": 1.8952757818976034,
|
| 133 |
+
"learning_rate": 9.962237124876828e-06,
|
| 134 |
+
"loss": 0.1709,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.72,
|
| 139 |
+
"grad_norm": 1.7959529824065594,
|
| 140 |
+
"learning_rate": 9.943157907471825e-06,
|
| 141 |
+
"loss": 0.1818,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.76,
|
| 146 |
+
"grad_norm": 3.148673436638757,
|
| 147 |
+
"learning_rate": 9.920217303033091e-06,
|
| 148 |
+
"loss": 0.1868,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8,
|
| 153 |
+
"grad_norm": 2.6291492953956035,
|
| 154 |
+
"learning_rate": 9.893433231795864e-06,
|
| 155 |
+
"loss": 0.1802,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.84,
|
| 160 |
+
"grad_norm": 2.116086213452932,
|
| 161 |
+
"learning_rate": 9.862826616349981e-06,
|
| 162 |
+
"loss": 0.1963,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.88,
|
| 167 |
+
"grad_norm": 2.590351057974938,
|
| 168 |
+
"learning_rate": 9.828421365296023e-06,
|
| 169 |
+
"loss": 0.1884,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.92,
|
| 174 |
+
"grad_norm": 2.2826587299690297,
|
| 175 |
+
"learning_rate": 9.79024435456893e-06,
|
| 176 |
+
"loss": 0.194,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.96,
|
| 181 |
+
"grad_norm": 1.7617227651937795,
|
| 182 |
+
"learning_rate": 9.748325406443647e-06,
|
| 183 |
+
"loss": 0.1814,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.0,
|
| 188 |
+
"grad_norm": 2.7640313184450886,
|
| 189 |
+
"learning_rate": 9.702697266239211e-06,
|
| 190 |
+
"loss": 0.18,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.04,
|
| 195 |
+
"grad_norm": 13.383134400696948,
|
| 196 |
+
"learning_rate": 9.653395576739504e-06,
|
| 197 |
+
"loss": 0.1596,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.08,
|
| 202 |
+
"grad_norm": 1.960084286202522,
|
| 203 |
+
"learning_rate": 9.600458850350588e-06,
|
| 204 |
+
"loss": 0.163,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.12,
|
| 209 |
+
"grad_norm": 1.6888079694486844,
|
| 210 |
+
"learning_rate": 9.543928439016445e-06,
|
| 211 |
+
"loss": 0.1712,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.16,
|
| 216 |
+
"grad_norm": 2.5101725396253265,
|
| 217 |
+
"learning_rate": 9.483848501916578e-06,
|
| 218 |
+
"loss": 0.1667,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.2,
|
| 223 |
+
"grad_norm": 1.7853092667274246,
|
| 224 |
+
"learning_rate": 9.42026597097071e-06,
|
| 225 |
+
"loss": 0.17,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.24,
|
| 230 |
+
"grad_norm": 1.9741842768861118,
|
| 231 |
+
"learning_rate": 9.353230514177553e-06,
|
| 232 |
+
"loss": 0.1679,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.28,
|
| 237 |
+
"grad_norm": 2.4658963041094615,
|
| 238 |
+
"learning_rate": 9.282794496816244e-06,
|
| 239 |
+
"loss": 0.1731,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.32,
|
| 244 |
+
"grad_norm": 2.923478442896321,
|
| 245 |
+
"learning_rate": 9.209012940540806e-06,
|
| 246 |
+
"loss": 0.1708,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.3599999999999999,
|
| 251 |
+
"grad_norm": 3.19217673963713,
|
| 252 |
+
"learning_rate": 9.131943480399531e-06,
|
| 253 |
+
"loss": 0.1752,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.4,
|
| 258 |
+
"grad_norm": 2.2076768543351575,
|
| 259 |
+
"learning_rate": 9.05164631981292e-06,
|
| 260 |
+
"loss": 0.1646,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.44,
|
| 265 |
+
"grad_norm": 1.5911362670253353,
|
| 266 |
+
"learning_rate": 8.968184183545285e-06,
|
| 267 |
+
"loss": 0.1558,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.48,
|
| 272 |
+
"grad_norm": 2.438333228986101,
|
| 273 |
+
"learning_rate": 8.881622268706825e-06,
|
| 274 |
+
"loss": 0.1639,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.52,
|
| 279 |
+
"grad_norm": 1.8709425955134034,
|
| 280 |
+
"learning_rate": 8.792028193824364e-06,
|
| 281 |
+
"loss": 0.1566,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.56,
|
| 286 |
+
"grad_norm": 2.273561130366255,
|
| 287 |
+
"learning_rate": 8.699471946020612e-06,
|
| 288 |
+
"loss": 0.1743,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6,
|
| 293 |
+
"grad_norm": 2.2532334985776963,
|
| 294 |
+
"learning_rate": 8.604025826343167e-06,
|
| 295 |
+
"loss": 0.1614,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.6400000000000001,
|
| 300 |
+
"grad_norm": 2.8000291867854368,
|
| 301 |
+
"learning_rate": 8.505764393285985e-06,
|
| 302 |
+
"loss": 0.1688,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.6800000000000002,
|
| 307 |
+
"grad_norm": 3.5386862233237553,
|
| 308 |
+
"learning_rate": 8.404764404547404e-06,
|
| 309 |
+
"loss": 0.1736,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.72,
|
| 314 |
+
"grad_norm": 2.1915281083973475,
|
| 315 |
+
"learning_rate": 8.301104757070276e-06,
|
| 316 |
+
"loss": 0.1655,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.76,
|
| 321 |
+
"grad_norm": 1.735218330228595,
|
| 322 |
+
"learning_rate": 8.194866425410984e-06,
|
| 323 |
+
"loss": 0.1511,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.8,
|
| 328 |
+
"grad_norm": 2.0251426912636514,
|
| 329 |
+
"learning_rate": 8.086132398485525e-06,
|
| 330 |
+
"loss": 0.1499,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.8399999999999999,
|
| 335 |
+
"grad_norm": 2.595962962052259,
|
| 336 |
+
"learning_rate": 7.974987614742066e-06,
|
| 337 |
+
"loss": 0.1696,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.88,
|
| 342 |
+
"grad_norm": 1.8465107375877872,
|
| 343 |
+
"learning_rate": 7.861518895810597e-06,
|
| 344 |
+
"loss": 0.1645,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.92,
|
| 349 |
+
"grad_norm": 1.7181169308567998,
|
| 350 |
+
"learning_rate": 7.745814878681516e-06,
|
| 351 |
+
"loss": 0.1628,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.96,
|
| 356 |
+
"grad_norm": 1.914333923678904,
|
| 357 |
+
"learning_rate": 7.627965946466167e-06,
|
| 358 |
+
"loss": 0.1453,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.0,
|
| 363 |
+
"grad_norm": 1.6246422019481361,
|
| 364 |
+
"learning_rate": 7.50806415779332e-06,
|
| 365 |
+
"loss": 0.1489,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.04,
|
| 370 |
+
"grad_norm": 1.5381806636260356,
|
| 371 |
+
"learning_rate": 7.386203174896872e-06,
|
| 372 |
+
"loss": 0.1361,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.08,
|
| 377 |
+
"grad_norm": 1.6845512041994002,
|
| 378 |
+
"learning_rate": 7.262478190450834e-06,
|
| 379 |
+
"loss": 0.1332,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.12,
|
| 384 |
+
"grad_norm": 2.367964043590009,
|
| 385 |
+
"learning_rate": 7.136985853208824e-06,
|
| 386 |
+
"loss": 0.1426,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.16,
|
| 391 |
+
"grad_norm": 1.7353039468487315,
|
| 392 |
+
"learning_rate": 7.0098241925061215e-06,
|
| 393 |
+
"loss": 0.1348,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.2,
|
| 398 |
+
"grad_norm": 1.8745427410009357,
|
| 399 |
+
"learning_rate": 6.881092541683279e-06,
|
| 400 |
+
"loss": 0.1367,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.24,
|
| 405 |
+
"grad_norm": 1.7486606607428097,
|
| 406 |
+
"learning_rate": 6.750891460491093e-06,
|
| 407 |
+
"loss": 0.1432,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.2800000000000002,
|
| 412 |
+
"grad_norm": 2.7256153449292957,
|
| 413 |
+
"learning_rate": 6.619322656537552e-06,
|
| 414 |
+
"loss": 0.1327,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.32,
|
| 419 |
+
"grad_norm": 2.011781932169801,
|
| 420 |
+
"learning_rate": 6.486488905838143e-06,
|
| 421 |
+
"loss": 0.1471,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.36,
|
| 426 |
+
"grad_norm": 1.958955631206453,
|
| 427 |
+
"learning_rate": 6.352493972531535e-06,
|
| 428 |
+
"loss": 0.146,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.4,
|
| 433 |
+
"grad_norm": 2.125212212501986,
|
| 434 |
+
"learning_rate": 6.2174425278234115e-06,
|
| 435 |
+
"loss": 0.1439,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.44,
|
| 440 |
+
"grad_norm": 1.7405119151293693,
|
| 441 |
+
"learning_rate": 6.0814400682217236e-06,
|
| 442 |
+
"loss": 0.1345,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.48,
|
| 447 |
+
"grad_norm": 1.307904513904714,
|
| 448 |
+
"learning_rate": 5.944592833127253e-06,
|
| 449 |
+
"loss": 0.1412,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.52,
|
| 454 |
+
"grad_norm": 1.5618909410769424,
|
| 455 |
+
"learning_rate": 5.807007721843862e-06,
|
| 456 |
+
"loss": 0.1396,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.56,
|
| 461 |
+
"grad_norm": 1.6001114294946008,
|
| 462 |
+
"learning_rate": 5.668792210073255e-06,
|
| 463 |
+
"loss": 0.1381,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.6,
|
| 468 |
+
"grad_norm": 2.0825376870245433,
|
| 469 |
+
"learning_rate": 5.530054265959486e-06,
|
| 470 |
+
"loss": 0.1279,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.64,
|
| 475 |
+
"grad_norm": 1.4899012611449984,
|
| 476 |
+
"learning_rate": 5.39090226574877e-06,
|
| 477 |
+
"loss": 0.1273,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.68,
|
| 482 |
+
"grad_norm": 1.3587693779949943,
|
| 483 |
+
"learning_rate": 5.2514449091305375e-06,
|
| 484 |
+
"loss": 0.139,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.7199999999999998,
|
| 489 |
+
"grad_norm": 1.3905248184940833,
|
| 490 |
+
"learning_rate": 5.111791134325793e-06,
|
| 491 |
+
"loss": 0.1337,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.76,
|
| 496 |
+
"grad_norm": 1.7261472057985348,
|
| 497 |
+
"learning_rate": 4.9720500329891755e-06,
|
| 498 |
+
"loss": 0.1419,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.8,
|
| 503 |
+
"grad_norm": 1.5882220461692291,
|
| 504 |
+
"learning_rate": 4.832330764991131e-06,
|
| 505 |
+
"loss": 0.129,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.84,
|
| 510 |
+
"grad_norm": 33.74153723265867,
|
| 511 |
+
"learning_rate": 4.692742473146818e-06,
|
| 512 |
+
"loss": 0.182,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.88,
|
| 517 |
+
"grad_norm": 1.2964424054104968,
|
| 518 |
+
"learning_rate": 4.553394197958339e-06,
|
| 519 |
+
"loss": 0.1353,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.92,
|
| 524 |
+
"grad_norm": 1.203808822414652,
|
| 525 |
+
"learning_rate": 4.414394792436877e-06,
|
| 526 |
+
"loss": 0.1394,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.96,
|
| 531 |
+
"grad_norm": 1.2806702384421942,
|
| 532 |
+
"learning_rate": 4.275852837071309e-06,
|
| 533 |
+
"loss": 0.1251,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 3.0,
|
| 538 |
+
"grad_norm": 1.337023723464791,
|
| 539 |
+
"learning_rate": 4.137876555009684e-06,
|
| 540 |
+
"loss": 0.1376,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 3.04,
|
| 545 |
+
"grad_norm": 1.12357649083518,
|
| 546 |
+
"learning_rate": 4.000573727519868e-06,
|
| 547 |
+
"loss": 0.12,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.08,
|
| 552 |
+
"grad_norm": 1.1261752050608114,
|
| 553 |
+
"learning_rate": 3.86405160979534e-06,
|
| 554 |
+
"loss": 0.12,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 3.12,
|
| 559 |
+
"grad_norm": 1.31280326818583,
|
| 560 |
+
"learning_rate": 3.7284168471719527e-06,
|
| 561 |
+
"loss": 0.1153,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 3.16,
|
| 566 |
+
"grad_norm": 1.3340360591201343,
|
| 567 |
+
"learning_rate": 3.5937753918210705e-06,
|
| 568 |
+
"loss": 0.125,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.2,
|
| 573 |
+
"grad_norm": 1.074093734063287,
|
| 574 |
+
"learning_rate": 3.4602324199842026e-06,
|
| 575 |
+
"loss": 0.1201,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.24,
|
| 580 |
+
"grad_norm": 1.3868574560188593,
|
| 581 |
+
"learning_rate": 3.3278922498137455e-06,
|
| 582 |
+
"loss": 0.1165,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 3.2800000000000002,
|
| 587 |
+
"grad_norm": 1.5476889671334009,
|
| 588 |
+
"learning_rate": 3.1968582598840234e-06,
|
| 589 |
+
"loss": 0.1348,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.32,
|
| 594 |
+
"grad_norm": 2.2098782619120945,
|
| 595 |
+
"learning_rate": 3.067232808436299e-06,
|
| 596 |
+
"loss": 0.1264,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 3.36,
|
| 601 |
+
"grad_norm": 1.4042367103273385,
|
| 602 |
+
"learning_rate": 2.9391171534208185e-06,
|
| 603 |
+
"loss": 0.1254,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 3.4,
|
| 608 |
+
"grad_norm": 0.9517570079120965,
|
| 609 |
+
"learning_rate": 2.812611373398365e-06,
|
| 610 |
+
"loss": 0.1196,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 3.44,
|
| 615 |
+
"grad_norm": 1.411957760122345,
|
| 616 |
+
"learning_rate": 2.6878142893630904e-06,
|
| 617 |
+
"loss": 0.1237,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 3.48,
|
| 622 |
+
"grad_norm": 1.0469263122557906,
|
| 623 |
+
"learning_rate": 2.564823387547716e-06,
|
| 624 |
+
"loss": 0.1234,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 3.52,
|
| 629 |
+
"grad_norm": 1.0880117862903047,
|
| 630 |
+
"learning_rate": 2.4437347432713838e-06,
|
| 631 |
+
"loss": 0.1281,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.56,
|
| 636 |
+
"grad_norm": 1.4980302601520634,
|
| 637 |
+
"learning_rate": 2.3246429458896637e-06,
|
| 638 |
+
"loss": 0.1196,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 3.6,
|
| 643 |
+
"grad_norm": 1.0217971404002908,
|
| 644 |
+
"learning_rate": 2.207641024905322e-06,
|
| 645 |
+
"loss": 0.1224,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.64,
|
| 650 |
+
"grad_norm": 1.1671521628697192,
|
| 651 |
+
"learning_rate": 2.0928203772975917e-06,
|
| 652 |
+
"loss": 0.119,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.68,
|
| 657 |
+
"grad_norm": 1.107501819947676,
|
| 658 |
+
"learning_rate": 1.9802706961266936e-06,
|
| 659 |
+
"loss": 0.1201,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 3.7199999999999998,
|
| 664 |
+
"grad_norm": 0.9124789903191979,
|
| 665 |
+
"learning_rate": 1.870079900469392e-06,
|
| 666 |
+
"loss": 0.1204,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 3.76,
|
| 671 |
+
"grad_norm": 1.4405450223921223,
|
| 672 |
+
"learning_rate": 1.7623340667403089e-06,
|
| 673 |
+
"loss": 0.1173,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.8,
|
| 678 |
+
"grad_norm": 1.2383539174028362,
|
| 679 |
+
"learning_rate": 1.657117361452651e-06,
|
| 680 |
+
"loss": 0.123,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 3.84,
|
| 685 |
+
"grad_norm": 1.5492361002489776,
|
| 686 |
+
"learning_rate": 1.5545119754708682e-06,
|
| 687 |
+
"loss": 0.1213,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 3.88,
|
| 692 |
+
"grad_norm": 0.9688910602285367,
|
| 693 |
+
"learning_rate": 1.454598059806609e-06,
|
| 694 |
+
"loss": 0.1244,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.92,
|
| 699 |
+
"grad_norm": 1.2497049971642828,
|
| 700 |
+
"learning_rate": 1.3574536630081208e-06,
|
| 701 |
+
"loss": 0.1266,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 3.96,
|
| 706 |
+
"grad_norm": 1.4359900705563882,
|
| 707 |
+
"learning_rate": 1.2631546701920073e-06,
|
| 708 |
+
"loss": 0.1196,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 4.0,
|
| 713 |
+
"grad_norm": 1.013179470712264,
|
| 714 |
+
"learning_rate": 1.1717747437649657e-06,
|
| 715 |
+
"loss": 0.1186,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 4.04,
|
| 720 |
+
"grad_norm": 1.128971555703373,
|
| 721 |
+
"learning_rate": 1.0833852658818167e-06,
|
| 722 |
+
"loss": 0.1077,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 4.08,
|
| 727 |
+
"grad_norm": 0.8064418108816587,
|
| 728 |
+
"learning_rate": 9.980552826847635e-07,
|
| 729 |
+
"loss": 0.1099,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 4.12,
|
| 734 |
+
"grad_norm": 0.8053995942309401,
|
| 735 |
+
"learning_rate": 9.158514503674543e-07,
|
| 736 |
+
"loss": 0.1122,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 4.16,
|
| 741 |
+
"grad_norm": 1.0137589959248894,
|
| 742 |
+
"learning_rate": 8.368379831059592e-07,
|
| 743 |
+
"loss": 0.1108,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 4.2,
|
| 748 |
+
"grad_norm": 1.179886916033213,
|
| 749 |
+
"learning_rate": 7.61076602897371e-07,
|
| 750 |
+
"loss": 0.1168,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 4.24,
|
| 755 |
+
"grad_norm": 1.1023307485760356,
|
| 756 |
+
"learning_rate": 6.886264913451635e-07,
|
| 757 |
+
"loss": 0.111,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 4.28,
|
| 762 |
+
"grad_norm": 0.8911248731367788,
|
| 763 |
+
"learning_rate": 6.1954424342902e-07,
|
| 764 |
+
"loss": 0.114,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 4.32,
|
| 769 |
+
"grad_norm": 0.9031682796275837,
|
| 770 |
+
"learning_rate": 5.538838232952104e-07,
|
| 771 |
+
"loss": 0.1099,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 4.36,
|
| 776 |
+
"grad_norm": 0.9777576873311943,
|
| 777 |
+
"learning_rate": 4.916965221020753e-07,
|
| 778 |
+
"loss": 0.1149,
|
| 779 |
+
"step": 545
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 4.4,
|
| 783 |
+
"grad_norm": 0.794466996633541,
|
| 784 |
+
"learning_rate": 4.3303091795353024e-07,
|
| 785 |
+
"loss": 0.109,
|
| 786 |
+
"step": 550
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 4.44,
|
| 790 |
+
"grad_norm": 1.1715360106229433,
|
| 791 |
+
"learning_rate": 3.779328379518898e-07,
|
| 792 |
+
"loss": 0.119,
|
| 793 |
+
"step": 555
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 4.48,
|
| 797 |
+
"grad_norm": 0.9196816880764788,
|
| 798 |
+
"learning_rate": 3.2644532239966444e-07,
|
| 799 |
+
"loss": 0.1107,
|
| 800 |
+
"step": 560
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 4.52,
|
| 804 |
+
"grad_norm": 0.8511671131233757,
|
| 805 |
+
"learning_rate": 2.7860859117828985e-07,
|
| 806 |
+
"loss": 0.1106,
|
| 807 |
+
"step": 565
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 4.5600000000000005,
|
| 811 |
+
"grad_norm": 1.0226582223355896,
|
| 812 |
+
"learning_rate": 2.3446001233004333e-07,
|
| 813 |
+
"loss": 0.1176,
|
| 814 |
+
"step": 570
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 4.6,
|
| 818 |
+
"grad_norm": 0.8883730009317985,
|
| 819 |
+
"learning_rate": 1.9403407286770592e-07,
|
| 820 |
+
"loss": 0.1122,
|
| 821 |
+
"step": 575
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 4.64,
|
| 825 |
+
"grad_norm": 0.9879760794050276,
|
| 826 |
+
"learning_rate": 1.573623518347517e-07,
|
| 827 |
+
"loss": 0.1122,
|
| 828 |
+
"step": 580
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 4.68,
|
| 832 |
+
"grad_norm": 0.8638827655369075,
|
| 833 |
+
"learning_rate": 1.2447349563713186e-07,
|
| 834 |
+
"loss": 0.1144,
|
| 835 |
+
"step": 585
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 4.72,
|
| 839 |
+
"grad_norm": 0.8402422894300282,
|
| 840 |
+
"learning_rate": 9.539319566590766e-08,
|
| 841 |
+
"loss": 0.1108,
|
| 842 |
+
"step": 590
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 4.76,
|
| 846 |
+
"grad_norm": 1.173156707092929,
|
| 847 |
+
"learning_rate": 7.014416822821557e-08,
|
| 848 |
+
"loss": 0.1186,
|
| 849 |
+
"step": 595
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 4.8,
|
| 853 |
+
"grad_norm": 1.0955817536201944,
|
| 854 |
+
"learning_rate": 4.8746136802240716e-08,
|
| 855 |
+
"loss": 0.1115,
|
| 856 |
+
"step": 600
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 4.84,
|
| 860 |
+
"grad_norm": 0.9330940788218187,
|
| 861 |
+
"learning_rate": 3.121581663007134e-08,
|
| 862 |
+
"loss": 0.1157,
|
| 863 |
+
"step": 605
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 4.88,
|
| 867 |
+
"grad_norm": 1.1560897368741774,
|
| 868 |
+
"learning_rate": 1.75669016604485e-08,
|
| 869 |
+
"loss": 0.1035,
|
| 870 |
+
"step": 610
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 4.92,
|
| 874 |
+
"grad_norm": 1.0534577947172947,
|
| 875 |
+
"learning_rate": 7.81005385163458e-09,
|
| 876 |
+
"loss": 0.1134,
|
| 877 |
+
"step": 615
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 4.96,
|
| 881 |
+
"grad_norm": 0.893194596809323,
|
| 882 |
+
"learning_rate": 1.952894842735531e-09,
|
| 883 |
+
"loss": 0.1145,
|
| 884 |
+
"step": 620
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 5.0,
|
| 888 |
+
"grad_norm": 0.84002664295751,
|
| 889 |
+
"learning_rate": 0.0,
|
| 890 |
+
"loss": 0.1091,
|
| 891 |
+
"step": 625
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 5.0,
|
| 895 |
+
"step": 625,
|
| 896 |
+
"total_flos": 1839624683520.0,
|
| 897 |
+
"train_loss": 0.2137949773788452,
|
| 898 |
+
"train_runtime": 9889.1554,
|
| 899 |
+
"train_samples_per_second": 1.011,
|
| 900 |
+
"train_steps_per_second": 0.063
|
| 901 |
+
}
|
| 902 |
+
],
|
| 903 |
+
"logging_steps": 5,
|
| 904 |
+
"max_steps": 625,
|
| 905 |
+
"num_input_tokens_seen": 0,
|
| 906 |
+
"num_train_epochs": 5,
|
| 907 |
+
"save_steps": 100,
|
| 908 |
+
"stateful_callbacks": {
|
| 909 |
+
"TrainerControl": {
|
| 910 |
+
"args": {
|
| 911 |
+
"should_epoch_stop": false,
|
| 912 |
+
"should_evaluate": false,
|
| 913 |
+
"should_log": false,
|
| 914 |
+
"should_save": true,
|
| 915 |
+
"should_training_stop": true
|
| 916 |
+
},
|
| 917 |
+
"attributes": {}
|
| 918 |
+
}
|
| 919 |
+
},
|
| 920 |
+
"total_flos": 1839624683520.0,
|
| 921 |
+
"train_batch_size": 4,
|
| 922 |
+
"trial_name": null,
|
| 923 |
+
"trial_params": null
|
| 924 |
+
}
|