Commit
•
07b3e60
1
Parent(s):
10ff823
Model save
Browse files- README.md +111 -0
- adapter_config.json +25 -0
- adapter_model.safetensors +3 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- runs/Jan08_21-52-00_c33a1a6d4547/events.out.tfevents.1704750734.c33a1a6d4547.2543.0 +3 -0
- runs/Jan08_21-52-00_c33a1a6d4547/events.out.tfevents.1704753133.c33a1a6d4547.2543.1 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
- train_results.json +8 -0
- trainer_state.json +494 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.1
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: mistral-instruct-adv-robust-50-sft-lora
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# mistral-instruct-adv-robust-50-sft-lora
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.8817
|
| 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: 0.0003
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 4
|
| 43 |
+
- gradient_accumulation_steps: 16
|
| 44 |
+
- total_train_batch_size: 256
|
| 45 |
+
- total_eval_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: cosine
|
| 48 |
+
- num_epochs: 50
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 54 |
+
| 3.1318 | 0.12 | 1 | 2.8355 |
|
| 55 |
+
| 3.1318 | 1.12 | 2 | 2.6364 |
|
| 56 |
+
| 3.1318 | 2.12 | 3 | 2.4945 |
|
| 57 |
+
| 3.1318 | 3.12 | 4 | 2.5339 |
|
| 58 |
+
| 2.7386 | 4.12 | 5 | 2.3352 |
|
| 59 |
+
| 2.7386 | 5.12 | 6 | 2.2137 |
|
| 60 |
+
| 2.7386 | 6.12 | 7 | 2.1641 |
|
| 61 |
+
| 2.7386 | 7.12 | 8 | 2.1051 |
|
| 62 |
+
| 2.7386 | 8.12 | 9 | 2.0842 |
|
| 63 |
+
| 2.269 | 9.12 | 10 | 2.0479 |
|
| 64 |
+
| 2.269 | 10.12 | 11 | 1.9554 |
|
| 65 |
+
| 2.269 | 11.12 | 12 | 1.8555 |
|
| 66 |
+
| 2.269 | 12.12 | 13 | 1.7736 |
|
| 67 |
+
| 2.269 | 13.12 | 14 | 1.7906 |
|
| 68 |
+
| 1.9451 | 14.12 | 15 | 1.7737 |
|
| 69 |
+
| 1.9451 | 15.12 | 16 | 1.6677 |
|
| 70 |
+
| 1.9451 | 16.12 | 17 | 1.6411 |
|
| 71 |
+
| 1.9451 | 17.12 | 18 | 1.5739 |
|
| 72 |
+
| 1.9451 | 18.12 | 19 | 1.5334 |
|
| 73 |
+
| 1.6568 | 19.12 | 20 | 1.4794 |
|
| 74 |
+
| 1.6568 | 20.12 | 21 | 1.4008 |
|
| 75 |
+
| 1.6568 | 21.12 | 22 | 1.3625 |
|
| 76 |
+
| 1.6568 | 22.12 | 23 | 1.2964 |
|
| 77 |
+
| 1.6568 | 23.12 | 24 | 1.2041 |
|
| 78 |
+
| 1.3674 | 24.12 | 25 | 1.1971 |
|
| 79 |
+
| 1.3674 | 25.12 | 26 | 1.1571 |
|
| 80 |
+
| 1.3674 | 26.12 | 27 | 1.1080 |
|
| 81 |
+
| 1.3674 | 27.12 | 28 | 1.1099 |
|
| 82 |
+
| 1.3674 | 28.12 | 29 | 1.0930 |
|
| 83 |
+
| 1.145 | 29.12 | 30 | 1.0333 |
|
| 84 |
+
| 1.145 | 30.12 | 31 | 1.0096 |
|
| 85 |
+
| 1.145 | 31.12 | 32 | 1.0012 |
|
| 86 |
+
| 1.145 | 32.12 | 33 | 0.9266 |
|
| 87 |
+
| 1.145 | 33.12 | 34 | 0.9624 |
|
| 88 |
+
| 0.9987 | 34.12 | 35 | 0.9425 |
|
| 89 |
+
| 0.9987 | 35.12 | 36 | 0.9354 |
|
| 90 |
+
| 0.9987 | 36.12 | 37 | 0.9091 |
|
| 91 |
+
| 0.9987 | 37.12 | 38 | 0.9007 |
|
| 92 |
+
| 0.9987 | 38.12 | 39 | 0.9649 |
|
| 93 |
+
| 0.9071 | 39.12 | 40 | 0.9199 |
|
| 94 |
+
| 0.9071 | 40.12 | 41 | 0.8651 |
|
| 95 |
+
| 0.9071 | 41.12 | 42 | 0.8727 |
|
| 96 |
+
| 0.9071 | 42.12 | 43 | 0.8559 |
|
| 97 |
+
| 0.9071 | 43.12 | 44 | 0.8499 |
|
| 98 |
+
| 0.8522 | 44.12 | 45 | 0.8547 |
|
| 99 |
+
| 0.8522 | 45.12 | 46 | 0.8880 |
|
| 100 |
+
| 0.8522 | 46.12 | 47 | 0.8678 |
|
| 101 |
+
| 0.8522 | 47.12 | 48 | 0.8565 |
|
| 102 |
+
| 0.8522 | 48.12 | 49 | 0.8197 |
|
| 103 |
+
| 0.8153 | 49.12 | 50 | 0.8439 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- Transformers 4.35.0
|
| 109 |
+
- Pytorch 2.1.0a0+32f93b1
|
| 110 |
+
- Datasets 2.14.6
|
| 111 |
+
- Tokenizers 0.14.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 16,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 64,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj",
|
| 20 |
+
"o_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"v_proj"
|
| 23 |
+
],
|
| 24 |
+
"task_type": "CAUSAL_LM"
|
| 25 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8b8fb882c6507996dc92444210aadcbd379803735a95c8abe09cdc9cf4e6064
|
| 3 |
+
size 109086672
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.12,
|
| 3 |
+
"eval_loss": 0.8817058205604553,
|
| 4 |
+
"eval_runtime": 1.5268,
|
| 5 |
+
"eval_samples": 234,
|
| 6 |
+
"eval_samples_per_second": 153.259,
|
| 7 |
+
"eval_steps_per_second": 5.24,
|
| 8 |
+
"train_loss": 1.4773838996887207,
|
| 9 |
+
"train_runtime": 2397.7837,
|
| 10 |
+
"train_samples": 2097,
|
| 11 |
+
"train_samples_per_second": 43.728,
|
| 12 |
+
"train_steps_per_second": 0.167
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.12,
|
| 3 |
+
"eval_loss": 0.8817058205604553,
|
| 4 |
+
"eval_runtime": 1.5268,
|
| 5 |
+
"eval_samples": 234,
|
| 6 |
+
"eval_samples_per_second": 153.259,
|
| 7 |
+
"eval_steps_per_second": 5.24
|
| 8 |
+
}
|
runs/Jan08_21-52-00_c33a1a6d4547/events.out.tfevents.1704750734.c33a1a6d4547.2543.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:981f9a9e965b6b29c66f22c5fae8ebd41450651131f52be8d587ebd76088a903
|
| 3 |
+
size 19648
|
runs/Jan08_21-52-00_c33a1a6d4547/events.out.tfevents.1704753133.c33a1a6d4547.2543.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:631ec612be7427f241eb354776d8d14b9e78f42f4de5df304457d245e388214a
|
| 3 |
+
size 306
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"bos_token": "<s>",
|
| 30 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
| 31 |
+
"clean_up_tokenization_spaces": false,
|
| 32 |
+
"eos_token": "</s>",
|
| 33 |
+
"legacy": true,
|
| 34 |
+
"model_max_length": 2048,
|
| 35 |
+
"pad_token": "</s>",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"spaces_between_special_tokens": false,
|
| 38 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 39 |
+
"unk_token": "<unk>",
|
| 40 |
+
"use_default_system_prompt": false
|
| 41 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 49.12,
|
| 3 |
+
"train_loss": 1.4773838996887207,
|
| 4 |
+
"train_runtime": 2397.7837,
|
| 5 |
+
"train_samples": 2097,
|
| 6 |
+
"train_samples_per_second": 43.728,
|
| 7 |
+
"train_steps_per_second": 0.167
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,494 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.121212121212125,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 50,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.12,
|
| 13 |
+
"learning_rate": 0.00029999537364671844,
|
| 14 |
+
"loss": 3.1318,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"eval_loss": 2.835486888885498,
|
| 20 |
+
"eval_runtime": 2.1688,
|
| 21 |
+
"eval_samples_per_second": 107.896,
|
| 22 |
+
"eval_steps_per_second": 3.689,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.12,
|
| 27 |
+
"eval_loss": 2.6363508701324463,
|
| 28 |
+
"eval_runtime": 1.538,
|
| 29 |
+
"eval_samples_per_second": 152.15,
|
| 30 |
+
"eval_steps_per_second": 5.202,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 2.12,
|
| 35 |
+
"eval_loss": 2.4945499897003174,
|
| 36 |
+
"eval_runtime": 1.526,
|
| 37 |
+
"eval_samples_per_second": 153.347,
|
| 38 |
+
"eval_steps_per_second": 5.243,
|
| 39 |
+
"step": 3
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 3.12,
|
| 43 |
+
"eval_loss": 2.5338640213012695,
|
| 44 |
+
"eval_runtime": 1.5296,
|
| 45 |
+
"eval_samples_per_second": 152.982,
|
| 46 |
+
"eval_steps_per_second": 5.23,
|
| 47 |
+
"step": 4
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 4.12,
|
| 51 |
+
"learning_rate": 0.00029988435543610843,
|
| 52 |
+
"loss": 2.7386,
|
| 53 |
+
"step": 5
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 4.12,
|
| 57 |
+
"eval_loss": 2.3351666927337646,
|
| 58 |
+
"eval_runtime": 1.5386,
|
| 59 |
+
"eval_samples_per_second": 152.088,
|
| 60 |
+
"eval_steps_per_second": 5.2,
|
| 61 |
+
"step": 5
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 5.12,
|
| 65 |
+
"eval_loss": 2.2136902809143066,
|
| 66 |
+
"eval_runtime": 1.517,
|
| 67 |
+
"eval_samples_per_second": 154.247,
|
| 68 |
+
"eval_steps_per_second": 5.273,
|
| 69 |
+
"step": 6
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 6.12,
|
| 73 |
+
"eval_loss": 2.164069652557373,
|
| 74 |
+
"eval_runtime": 1.5148,
|
| 75 |
+
"eval_samples_per_second": 154.475,
|
| 76 |
+
"eval_steps_per_second": 5.281,
|
| 77 |
+
"step": 7
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 7.12,
|
| 81 |
+
"eval_loss": 2.105088710784912,
|
| 82 |
+
"eval_runtime": 1.5384,
|
| 83 |
+
"eval_samples_per_second": 152.111,
|
| 84 |
+
"eval_steps_per_second": 5.2,
|
| 85 |
+
"step": 8
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 8.12,
|
| 89 |
+
"eval_loss": 2.0841920375823975,
|
| 90 |
+
"eval_runtime": 1.6789,
|
| 91 |
+
"eval_samples_per_second": 139.374,
|
| 92 |
+
"eval_steps_per_second": 4.765,
|
| 93 |
+
"step": 9
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 9.12,
|
| 97 |
+
"learning_rate": 0.00029953760005996916,
|
| 98 |
+
"loss": 2.269,
|
| 99 |
+
"step": 10
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 9.12,
|
| 103 |
+
"eval_loss": 2.047882556915283,
|
| 104 |
+
"eval_runtime": 1.5168,
|
| 105 |
+
"eval_samples_per_second": 154.272,
|
| 106 |
+
"eval_steps_per_second": 5.274,
|
| 107 |
+
"step": 10
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 10.12,
|
| 111 |
+
"eval_loss": 1.9553548097610474,
|
| 112 |
+
"eval_runtime": 1.5263,
|
| 113 |
+
"eval_samples_per_second": 153.317,
|
| 114 |
+
"eval_steps_per_second": 5.242,
|
| 115 |
+
"step": 11
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 11.12,
|
| 119 |
+
"eval_loss": 1.8555233478546143,
|
| 120 |
+
"eval_runtime": 1.527,
|
| 121 |
+
"eval_samples_per_second": 153.245,
|
| 122 |
+
"eval_steps_per_second": 5.239,
|
| 123 |
+
"step": 12
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 12.12,
|
| 127 |
+
"eval_loss": 1.7735551595687866,
|
| 128 |
+
"eval_runtime": 1.5194,
|
| 129 |
+
"eval_samples_per_second": 154.009,
|
| 130 |
+
"eval_steps_per_second": 5.265,
|
| 131 |
+
"step": 13
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 13.12,
|
| 135 |
+
"eval_loss": 1.7906467914581299,
|
| 136 |
+
"eval_runtime": 1.5217,
|
| 137 |
+
"eval_samples_per_second": 153.779,
|
| 138 |
+
"eval_steps_per_second": 5.257,
|
| 139 |
+
"step": 14
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 14.12,
|
| 143 |
+
"learning_rate": 0.00029896026854323894,
|
| 144 |
+
"loss": 1.9451,
|
| 145 |
+
"step": 15
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 14.12,
|
| 149 |
+
"eval_loss": 1.7737478017807007,
|
| 150 |
+
"eval_runtime": 1.5139,
|
| 151 |
+
"eval_samples_per_second": 154.563,
|
| 152 |
+
"eval_steps_per_second": 5.284,
|
| 153 |
+
"step": 15
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 15.12,
|
| 157 |
+
"eval_loss": 1.6676586866378784,
|
| 158 |
+
"eval_runtime": 1.5263,
|
| 159 |
+
"eval_samples_per_second": 153.316,
|
| 160 |
+
"eval_steps_per_second": 5.242,
|
| 161 |
+
"step": 16
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 16.12,
|
| 165 |
+
"eval_loss": 1.6410826444625854,
|
| 166 |
+
"eval_runtime": 1.5192,
|
| 167 |
+
"eval_samples_per_second": 154.025,
|
| 168 |
+
"eval_steps_per_second": 5.266,
|
| 169 |
+
"step": 17
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 17.12,
|
| 173 |
+
"eval_loss": 1.5739473104476929,
|
| 174 |
+
"eval_runtime": 1.5309,
|
| 175 |
+
"eval_samples_per_second": 152.855,
|
| 176 |
+
"eval_steps_per_second": 5.226,
|
| 177 |
+
"step": 18
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 18.12,
|
| 181 |
+
"eval_loss": 1.5334192514419556,
|
| 182 |
+
"eval_runtime": 1.5271,
|
| 183 |
+
"eval_samples_per_second": 153.235,
|
| 184 |
+
"eval_steps_per_second": 5.239,
|
| 185 |
+
"step": 19
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 19.12,
|
| 189 |
+
"learning_rate": 0.00029815325108927063,
|
| 190 |
+
"loss": 1.6568,
|
| 191 |
+
"step": 20
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 19.12,
|
| 195 |
+
"eval_loss": 1.47941255569458,
|
| 196 |
+
"eval_runtime": 1.5335,
|
| 197 |
+
"eval_samples_per_second": 152.593,
|
| 198 |
+
"eval_steps_per_second": 5.217,
|
| 199 |
+
"step": 20
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 20.12,
|
| 203 |
+
"eval_loss": 1.4007827043533325,
|
| 204 |
+
"eval_runtime": 1.5222,
|
| 205 |
+
"eval_samples_per_second": 153.722,
|
| 206 |
+
"eval_steps_per_second": 5.255,
|
| 207 |
+
"step": 21
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 21.12,
|
| 211 |
+
"eval_loss": 1.3624812364578247,
|
| 212 |
+
"eval_runtime": 1.5197,
|
| 213 |
+
"eval_samples_per_second": 153.982,
|
| 214 |
+
"eval_steps_per_second": 5.264,
|
| 215 |
+
"step": 22
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 22.12,
|
| 219 |
+
"eval_loss": 1.2963740825653076,
|
| 220 |
+
"eval_runtime": 1.5258,
|
| 221 |
+
"eval_samples_per_second": 153.363,
|
| 222 |
+
"eval_steps_per_second": 5.243,
|
| 223 |
+
"step": 23
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 23.12,
|
| 227 |
+
"eval_loss": 1.2041164636611938,
|
| 228 |
+
"eval_runtime": 1.5251,
|
| 229 |
+
"eval_samples_per_second": 153.434,
|
| 230 |
+
"eval_steps_per_second": 5.246,
|
| 231 |
+
"step": 24
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 24.12,
|
| 235 |
+
"learning_rate": 0.00029711779206048454,
|
| 236 |
+
"loss": 1.3674,
|
| 237 |
+
"step": 25
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 24.12,
|
| 241 |
+
"eval_loss": 1.1971029043197632,
|
| 242 |
+
"eval_runtime": 1.535,
|
| 243 |
+
"eval_samples_per_second": 152.446,
|
| 244 |
+
"eval_steps_per_second": 5.212,
|
| 245 |
+
"step": 25
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 25.12,
|
| 249 |
+
"eval_loss": 1.1571109294891357,
|
| 250 |
+
"eval_runtime": 1.5213,
|
| 251 |
+
"eval_samples_per_second": 153.815,
|
| 252 |
+
"eval_steps_per_second": 5.259,
|
| 253 |
+
"step": 26
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 26.12,
|
| 257 |
+
"eval_loss": 1.1079976558685303,
|
| 258 |
+
"eval_runtime": 1.5286,
|
| 259 |
+
"eval_samples_per_second": 153.079,
|
| 260 |
+
"eval_steps_per_second": 5.233,
|
| 261 |
+
"step": 27
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 27.12,
|
| 265 |
+
"eval_loss": 1.109868049621582,
|
| 266 |
+
"eval_runtime": 1.5388,
|
| 267 |
+
"eval_samples_per_second": 152.068,
|
| 268 |
+
"eval_steps_per_second": 5.199,
|
| 269 |
+
"step": 28
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 28.12,
|
| 273 |
+
"eval_loss": 1.0929827690124512,
|
| 274 |
+
"eval_runtime": 1.5243,
|
| 275 |
+
"eval_samples_per_second": 153.513,
|
| 276 |
+
"eval_steps_per_second": 5.248,
|
| 277 |
+
"step": 29
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 29.12,
|
| 281 |
+
"learning_rate": 0.0002958554880596515,
|
| 282 |
+
"loss": 1.145,
|
| 283 |
+
"step": 30
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 29.12,
|
| 287 |
+
"eval_loss": 1.0333445072174072,
|
| 288 |
+
"eval_runtime": 1.528,
|
| 289 |
+
"eval_samples_per_second": 153.138,
|
| 290 |
+
"eval_steps_per_second": 5.235,
|
| 291 |
+
"step": 30
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 30.12,
|
| 295 |
+
"eval_loss": 1.009576678276062,
|
| 296 |
+
"eval_runtime": 1.5222,
|
| 297 |
+
"eval_samples_per_second": 153.722,
|
| 298 |
+
"eval_steps_per_second": 5.255,
|
| 299 |
+
"step": 31
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 31.12,
|
| 303 |
+
"eval_loss": 1.0011868476867676,
|
| 304 |
+
"eval_runtime": 1.5185,
|
| 305 |
+
"eval_samples_per_second": 154.104,
|
| 306 |
+
"eval_steps_per_second": 5.269,
|
| 307 |
+
"step": 32
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 32.12,
|
| 311 |
+
"eval_loss": 0.9265638589859009,
|
| 312 |
+
"eval_runtime": 1.5235,
|
| 313 |
+
"eval_samples_per_second": 153.589,
|
| 314 |
+
"eval_steps_per_second": 5.251,
|
| 315 |
+
"step": 33
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 33.12,
|
| 319 |
+
"eval_loss": 0.962448239326477,
|
| 320 |
+
"eval_runtime": 1.5219,
|
| 321 |
+
"eval_samples_per_second": 153.758,
|
| 322 |
+
"eval_steps_per_second": 5.257,
|
| 323 |
+
"step": 34
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 34.12,
|
| 327 |
+
"learning_rate": 0.000294368285468047,
|
| 328 |
+
"loss": 0.9987,
|
| 329 |
+
"step": 35
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 34.12,
|
| 333 |
+
"eval_loss": 0.9425073862075806,
|
| 334 |
+
"eval_runtime": 1.5206,
|
| 335 |
+
"eval_samples_per_second": 153.885,
|
| 336 |
+
"eval_steps_per_second": 5.261,
|
| 337 |
+
"step": 35
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 35.12,
|
| 341 |
+
"eval_loss": 0.9353674650192261,
|
| 342 |
+
"eval_runtime": 1.5211,
|
| 343 |
+
"eval_samples_per_second": 153.831,
|
| 344 |
+
"eval_steps_per_second": 5.259,
|
| 345 |
+
"step": 36
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 36.12,
|
| 349 |
+
"eval_loss": 0.9090538024902344,
|
| 350 |
+
"eval_runtime": 1.5239,
|
| 351 |
+
"eval_samples_per_second": 153.554,
|
| 352 |
+
"eval_steps_per_second": 5.25,
|
| 353 |
+
"step": 37
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 37.12,
|
| 357 |
+
"eval_loss": 0.9006912708282471,
|
| 358 |
+
"eval_runtime": 1.6666,
|
| 359 |
+
"eval_samples_per_second": 140.404,
|
| 360 |
+
"eval_steps_per_second": 4.8,
|
| 361 |
+
"step": 38
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 38.12,
|
| 365 |
+
"eval_loss": 0.9648869037628174,
|
| 366 |
+
"eval_runtime": 1.5236,
|
| 367 |
+
"eval_samples_per_second": 153.587,
|
| 368 |
+
"eval_steps_per_second": 5.251,
|
| 369 |
+
"step": 39
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 39.12,
|
| 373 |
+
"learning_rate": 0.00029265847744427303,
|
| 374 |
+
"loss": 0.9071,
|
| 375 |
+
"step": 40
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 39.12,
|
| 379 |
+
"eval_loss": 0.9199429154396057,
|
| 380 |
+
"eval_runtime": 1.526,
|
| 381 |
+
"eval_samples_per_second": 153.343,
|
| 382 |
+
"eval_steps_per_second": 5.242,
|
| 383 |
+
"step": 40
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 40.12,
|
| 387 |
+
"eval_loss": 0.8650604486465454,
|
| 388 |
+
"eval_runtime": 1.5281,
|
| 389 |
+
"eval_samples_per_second": 153.127,
|
| 390 |
+
"eval_steps_per_second": 5.235,
|
| 391 |
+
"step": 41
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 41.12,
|
| 395 |
+
"eval_loss": 0.8727077841758728,
|
| 396 |
+
"eval_runtime": 1.5186,
|
| 397 |
+
"eval_samples_per_second": 154.087,
|
| 398 |
+
"eval_steps_per_second": 5.268,
|
| 399 |
+
"step": 42
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 42.12,
|
| 403 |
+
"eval_loss": 0.8558970093727112,
|
| 404 |
+
"eval_runtime": 1.5297,
|
| 405 |
+
"eval_samples_per_second": 152.968,
|
| 406 |
+
"eval_steps_per_second": 5.23,
|
| 407 |
+
"step": 43
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 43.12,
|
| 411 |
+
"eval_loss": 0.8499311804771423,
|
| 412 |
+
"eval_runtime": 1.5225,
|
| 413 |
+
"eval_samples_per_second": 153.692,
|
| 414 |
+
"eval_steps_per_second": 5.254,
|
| 415 |
+
"step": 44
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 44.12,
|
| 419 |
+
"learning_rate": 0.0002907287003883726,
|
| 420 |
+
"loss": 0.8522,
|
| 421 |
+
"step": 45
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 44.12,
|
| 425 |
+
"eval_loss": 0.8547362089157104,
|
| 426 |
+
"eval_runtime": 1.5331,
|
| 427 |
+
"eval_samples_per_second": 152.637,
|
| 428 |
+
"eval_steps_per_second": 5.218,
|
| 429 |
+
"step": 45
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 45.12,
|
| 433 |
+
"eval_loss": 0.8880292177200317,
|
| 434 |
+
"eval_runtime": 1.5217,
|
| 435 |
+
"eval_samples_per_second": 153.771,
|
| 436 |
+
"eval_steps_per_second": 5.257,
|
| 437 |
+
"step": 46
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 46.12,
|
| 441 |
+
"eval_loss": 0.8677502870559692,
|
| 442 |
+
"eval_runtime": 1.5273,
|
| 443 |
+
"eval_samples_per_second": 153.214,
|
| 444 |
+
"eval_steps_per_second": 5.238,
|
| 445 |
+
"step": 47
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 47.12,
|
| 449 |
+
"eval_loss": 0.8565409183502197,
|
| 450 |
+
"eval_runtime": 1.5222,
|
| 451 |
+
"eval_samples_per_second": 153.723,
|
| 452 |
+
"eval_steps_per_second": 5.255,
|
| 453 |
+
"step": 48
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 48.12,
|
| 457 |
+
"eval_loss": 0.8197174072265625,
|
| 458 |
+
"eval_runtime": 1.5188,
|
| 459 |
+
"eval_samples_per_second": 154.07,
|
| 460 |
+
"eval_steps_per_second": 5.267,
|
| 461 |
+
"step": 49
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 49.12,
|
| 465 |
+
"learning_rate": 0.000288581929876693,
|
| 466 |
+
"loss": 0.8153,
|
| 467 |
+
"step": 50
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 49.12,
|
| 471 |
+
"eval_loss": 0.8439480662345886,
|
| 472 |
+
"eval_runtime": 1.5245,
|
| 473 |
+
"eval_samples_per_second": 153.497,
|
| 474 |
+
"eval_steps_per_second": 5.248,
|
| 475 |
+
"step": 50
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 49.12,
|
| 479 |
+
"step": 50,
|
| 480 |
+
"total_flos": 4527521789902848.0,
|
| 481 |
+
"train_loss": 1.4773838996887207,
|
| 482 |
+
"train_runtime": 2397.7837,
|
| 483 |
+
"train_samples_per_second": 43.728,
|
| 484 |
+
"train_steps_per_second": 0.167
|
| 485 |
+
}
|
| 486 |
+
],
|
| 487 |
+
"logging_steps": 5,
|
| 488 |
+
"max_steps": 400,
|
| 489 |
+
"num_train_epochs": 50,
|
| 490 |
+
"save_steps": 500,
|
| 491 |
+
"total_flos": 4527521789902848.0,
|
| 492 |
+
"trial_name": null,
|
| 493 |
+
"trial_params": null
|
| 494 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a81458bbf3b08b77cd58016c15a52a8b576953f0dd41f6b8585e6b3ee4d7bbb1
|
| 3 |
+
size 5688
|