End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +780 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: hp_ablations_qwen_adambeta2_0.98_dcftv1.2
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# hp_ablations_qwen_adambeta2_0.98_dcftv1.2
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6330
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: hp_ablations_qwen_adambeta2_0.98_dcftv1.2
|
|
|
|
| 16 |
|
| 17 |
# hp_ablations_qwen_adambeta2_0.98_dcftv1.2
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6330
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9956108266276518,
|
| 3 |
+
"eval_loss": 0.6330468654632568,
|
| 4 |
+
"eval_runtime": 343.5038,
|
| 5 |
+
"eval_samples_per_second": 26.809,
|
| 6 |
+
"eval_steps_per_second": 0.419,
|
| 7 |
+
"total_flos": 2144987064041472.0,
|
| 8 |
+
"train_loss": 0.6152277645360923,
|
| 9 |
+
"train_runtime": 54853.139,
|
| 10 |
+
"train_samples_per_second": 9.569,
|
| 11 |
+
"train_steps_per_second": 0.019
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9956108266276518,
|
| 3 |
+
"eval_loss": 0.6330468654632568,
|
| 4 |
+
"eval_runtime": 343.5038,
|
| 5 |
+
"eval_samples_per_second": 26.809,
|
| 6 |
+
"eval_steps_per_second": 0.419
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9956108266276518,
|
| 3 |
+
"total_flos": 2144987064041472.0,
|
| 4 |
+
"train_loss": 0.6152277645360923,
|
| 5 |
+
"train_runtime": 54853.139,
|
| 6 |
+
"train_samples_per_second": 9.569,
|
| 7 |
+
"train_steps_per_second": 0.019
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,780 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9956108266276518,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1023,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.029261155815654718,
|
| 13 |
+
"grad_norm": 63.33159396582597,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7981,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.058522311631309436,
|
| 20 |
+
"grad_norm": 1.2985053942795166,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.7394,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08778346744696415,
|
| 27 |
+
"grad_norm": 1.2994972414920418,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.7076,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11704462326261887,
|
| 34 |
+
"grad_norm": 1.09154200562291,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6974,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.14630577907827358,
|
| 41 |
+
"grad_norm": 1.1635059184964134,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6882,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1755669348939283,
|
| 48 |
+
"grad_norm": 0.9663792155845926,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.6781,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.20482809070958302,
|
| 55 |
+
"grad_norm": 0.6939099177117586,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.6713,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.23408924652523774,
|
| 62 |
+
"grad_norm": 0.4554483136685933,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.6655,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.26335040234089246,
|
| 69 |
+
"grad_norm": 0.43998686977438867,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.6624,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.29261155815654716,
|
| 76 |
+
"grad_norm": 0.4681462289171194,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6547,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3218727139722019,
|
| 83 |
+
"grad_norm": 0.4088427127266188,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6635,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3511338697878566,
|
| 90 |
+
"grad_norm": 0.36705252012743494,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6683,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.38039502560351135,
|
| 97 |
+
"grad_norm": 0.374209969368988,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6522,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.40965618141916604,
|
| 104 |
+
"grad_norm": 0.3565722412862572,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6529,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4389173372348208,
|
| 111 |
+
"grad_norm": 0.34204106396539435,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6483,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4681784930504755,
|
| 118 |
+
"grad_norm": 0.38615414130675385,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6502,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.49743964886613024,
|
| 125 |
+
"grad_norm": 0.3634230078003702,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6552,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5267008046817849,
|
| 132 |
+
"grad_norm": 0.3340266332324882,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6549,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5559619604974396,
|
| 139 |
+
"grad_norm": 0.35590307178082214,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6434,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5852231163130943,
|
| 146 |
+
"grad_norm": 0.3448405016272299,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6446,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6144842721287491,
|
| 153 |
+
"grad_norm": 0.3385609115523372,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6511,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6437454279444038,
|
| 160 |
+
"grad_norm": 0.3534390098067362,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6392,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6730065837600585,
|
| 167 |
+
"grad_norm": 0.3619673231162035,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6391,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7022677395757132,
|
| 174 |
+
"grad_norm": 0.3367671267006255,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.646,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.731528895391368,
|
| 181 |
+
"grad_norm": 0.34227548100303745,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6443,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7607900512070227,
|
| 188 |
+
"grad_norm": 0.3408993257912956,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6469,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7900512070226774,
|
| 195 |
+
"grad_norm": 0.3790106895262509,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6492,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8193123628383321,
|
| 202 |
+
"grad_norm": 0.3429230463611281,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.648,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8485735186539868,
|
| 209 |
+
"grad_norm": 0.33672564322042764,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6402,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.8778346744696416,
|
| 216 |
+
"grad_norm": 0.34609131513685526,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6321,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9070958302852963,
|
| 223 |
+
"grad_norm": 0.34957045568901657,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6452,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.936356986100951,
|
| 230 |
+
"grad_norm": 0.33437406171376016,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6372,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9656181419166057,
|
| 237 |
+
"grad_norm": 0.371533848542589,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.6404,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.9948792977322605,
|
| 244 |
+
"grad_norm": 0.35130336452701355,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.6364,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9978054133138259,
|
| 251 |
+
"eval_loss": 0.640914797782898,
|
| 252 |
+
"eval_runtime": 345.6005,
|
| 253 |
+
"eval_samples_per_second": 26.646,
|
| 254 |
+
"eval_steps_per_second": 0.417,
|
| 255 |
+
"step": 341
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.025237746891002,
|
| 259 |
+
"grad_norm": 0.3692130458298124,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.6524,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.054498902706657,
|
| 266 |
+
"grad_norm": 0.3553119811115944,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.6067,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.0837600585223117,
|
| 273 |
+
"grad_norm": 0.40346799763343727,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.6101,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1130212143379663,
|
| 280 |
+
"grad_norm": 0.3197358067569843,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.6075,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.142282370153621,
|
| 287 |
+
"grad_norm": 0.40727251989734975,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.6127,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.1715435259692757,
|
| 294 |
+
"grad_norm": 0.3623259217407185,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.6142,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2008046817849305,
|
| 301 |
+
"grad_norm": 0.3581625285849574,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.6139,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2300658376005853,
|
| 308 |
+
"grad_norm": 0.36695340881733157,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.6021,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.2593269934162399,
|
| 315 |
+
"grad_norm": 0.3572031445012923,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.6122,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.2885881492318947,
|
| 322 |
+
"grad_norm": 0.34962802000050813,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.6048,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3178493050475493,
|
| 329 |
+
"grad_norm": 0.35755536354001544,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.6086,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.347110460863204,
|
| 336 |
+
"grad_norm": 0.37570399727715037,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.6062,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.3763716166788589,
|
| 343 |
+
"grad_norm": 0.3228789388457264,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.6035,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4056327724945135,
|
| 350 |
+
"grad_norm": 0.3634169062758459,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.6044,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.4348939283101683,
|
| 357 |
+
"grad_norm": 0.3502861798040734,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.6108,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.464155084125823,
|
| 364 |
+
"grad_norm": 0.34093533114824826,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5991,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.4934162399414777,
|
| 371 |
+
"grad_norm": 0.3463701037893924,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.6071,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.5226773957571325,
|
| 378 |
+
"grad_norm": 0.38931672754338176,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.6095,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.5519385515727873,
|
| 385 |
+
"grad_norm": 0.34906068590167777,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.608,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.5811997073884418,
|
| 392 |
+
"grad_norm": 0.3701456606885589,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.6146,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.6104608632040964,
|
| 399 |
+
"grad_norm": 0.3506849233715239,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6056,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.6397220190197512,
|
| 406 |
+
"grad_norm": 0.35747637775205837,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.6074,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.668983174835406,
|
| 413 |
+
"grad_norm": 0.32158800583674974,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.5979,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.6982443306510606,
|
| 420 |
+
"grad_norm": 0.3528344876208815,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.6072,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.7275054864667154,
|
| 427 |
+
"grad_norm": 0.41985622969098957,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.6075,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.7567666422823702,
|
| 434 |
+
"grad_norm": 0.34105125625368893,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.6044,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.7860277980980248,
|
| 441 |
+
"grad_norm": 0.34589478838024207,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.6069,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.8152889539136796,
|
| 448 |
+
"grad_norm": 0.32553452148702333,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.6073,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.8445501097293344,
|
| 455 |
+
"grad_norm": 0.3583629997971789,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.6063,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.873811265544989,
|
| 462 |
+
"grad_norm": 0.3258762553733896,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.6012,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.9030724213606436,
|
| 469 |
+
"grad_norm": 0.36542172455522237,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.6068,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.9323335771762986,
|
| 476 |
+
"grad_norm": 0.3468540827688793,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.6074,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.9615947329919532,
|
| 483 |
+
"grad_norm": 0.3301547297982186,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.5962,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.9908558888076078,
|
| 490 |
+
"grad_norm": 0.353549889665131,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.6107,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.9967081199707388,
|
| 497 |
+
"eval_loss": 0.6333796381950378,
|
| 498 |
+
"eval_runtime": 344.9128,
|
| 499 |
+
"eval_samples_per_second": 26.699,
|
| 500 |
+
"eval_steps_per_second": 0.417,
|
| 501 |
+
"step": 682
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.0212143379663496,
|
| 505 |
+
"grad_norm": 0.38522584628732043,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.6214,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.050475493782004,
|
| 512 |
+
"grad_norm": 0.4092650769853219,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.5693,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.0797366495976592,
|
| 519 |
+
"grad_norm": 0.36395160858693937,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.5712,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.108997805413314,
|
| 526 |
+
"grad_norm": 0.36987210556495065,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.5723,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.1382589612289684,
|
| 533 |
+
"grad_norm": 0.3530004884029566,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.5741,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.1675201170446234,
|
| 540 |
+
"grad_norm": 0.3474755062723768,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.5794,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.196781272860278,
|
| 547 |
+
"grad_norm": 0.3203177683782767,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.5781,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.2260424286759326,
|
| 554 |
+
"grad_norm": 0.3661319457012291,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.5755,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.255303584491587,
|
| 561 |
+
"grad_norm": 0.3359421587293624,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.5742,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.284564740307242,
|
| 568 |
+
"grad_norm": 0.3332624185731929,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.5733,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.313825896122897,
|
| 575 |
+
"grad_norm": 0.3326965713448184,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.5716,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.3430870519385514,
|
| 582 |
+
"grad_norm": 0.3617619945788122,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.5794,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.3723482077542064,
|
| 589 |
+
"grad_norm": 0.3298127671828895,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.5746,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.401609363569861,
|
| 596 |
+
"grad_norm": 0.332422697888563,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.5808,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.4308705193855156,
|
| 603 |
+
"grad_norm": 0.3196015454900321,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.5731,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.4601316752011706,
|
| 610 |
+
"grad_norm": 0.35331559179835964,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5736,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.489392831016825,
|
| 617 |
+
"grad_norm": 0.3392297184730635,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5758,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.5186539868324798,
|
| 624 |
+
"grad_norm": 0.34620746539815944,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5688,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.547915142648135,
|
| 631 |
+
"grad_norm": 0.4023501023219655,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.5712,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.5771762984637894,
|
| 638 |
+
"grad_norm": 0.34088303079875626,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5754,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.606437454279444,
|
| 645 |
+
"grad_norm": 0.36405494880778144,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.5748,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.6356986100950985,
|
| 652 |
+
"grad_norm": 0.34721347207329656,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5794,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.6649597659107536,
|
| 659 |
+
"grad_norm": 0.3546551945507394,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.5795,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.694220921726408,
|
| 666 |
+
"grad_norm": 0.36027986998179906,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.5738,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.723482077542063,
|
| 673 |
+
"grad_norm": 0.35159220496145294,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.5775,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.7527432333577178,
|
| 680 |
+
"grad_norm": 0.3504714185096239,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.5764,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.7820043891733723,
|
| 687 |
+
"grad_norm": 0.3284737703409318,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.5751,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.811265544989027,
|
| 694 |
+
"grad_norm": 0.37305249319315187,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.5789,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.840526700804682,
|
| 701 |
+
"grad_norm": 0.33884604095107257,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.5747,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.8697878566203365,
|
| 708 |
+
"grad_norm": 0.37958678053577166,
|
| 709 |
+
"learning_rate": 5e-06,
|
| 710 |
+
"loss": 0.5745,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.899049012435991,
|
| 715 |
+
"grad_norm": 0.34410472212682797,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.5675,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.928310168251646,
|
| 722 |
+
"grad_norm": 0.3222728501974356,
|
| 723 |
+
"learning_rate": 5e-06,
|
| 724 |
+
"loss": 0.5753,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.9575713240673007,
|
| 729 |
+
"grad_norm": 0.3391773666930332,
|
| 730 |
+
"learning_rate": 5e-06,
|
| 731 |
+
"loss": 0.567,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.9868324798829553,
|
| 736 |
+
"grad_norm": 0.33304266357077267,
|
| 737 |
+
"learning_rate": 5e-06,
|
| 738 |
+
"loss": 0.5787,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.9956108266276518,
|
| 743 |
+
"eval_loss": 0.6330468654632568,
|
| 744 |
+
"eval_runtime": 344.0095,
|
| 745 |
+
"eval_samples_per_second": 26.77,
|
| 746 |
+
"eval_steps_per_second": 0.419,
|
| 747 |
+
"step": 1023
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.9956108266276518,
|
| 751 |
+
"step": 1023,
|
| 752 |
+
"total_flos": 2144987064041472.0,
|
| 753 |
+
"train_loss": 0.6152277645360923,
|
| 754 |
+
"train_runtime": 54853.139,
|
| 755 |
+
"train_samples_per_second": 9.569,
|
| 756 |
+
"train_steps_per_second": 0.019
|
| 757 |
+
}
|
| 758 |
+
],
|
| 759 |
+
"logging_steps": 10,
|
| 760 |
+
"max_steps": 1023,
|
| 761 |
+
"num_input_tokens_seen": 0,
|
| 762 |
+
"num_train_epochs": 3,
|
| 763 |
+
"save_steps": 500,
|
| 764 |
+
"stateful_callbacks": {
|
| 765 |
+
"TrainerControl": {
|
| 766 |
+
"args": {
|
| 767 |
+
"should_epoch_stop": false,
|
| 768 |
+
"should_evaluate": false,
|
| 769 |
+
"should_log": false,
|
| 770 |
+
"should_save": true,
|
| 771 |
+
"should_training_stop": true
|
| 772 |
+
},
|
| 773 |
+
"attributes": {}
|
| 774 |
+
}
|
| 775 |
+
},
|
| 776 |
+
"total_flos": 2144987064041472.0,
|
| 777 |
+
"train_batch_size": 8,
|
| 778 |
+
"trial_name": null,
|
| 779 |
+
"trial_params": null
|
| 780 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|