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 +843 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: top_10_ranking_stackexchange
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# top_10_ranking_stackexchange
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.7844
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: top_10_ranking_stackexchange
|
|
|
|
| 16 |
|
| 17 |
# top_10_ranking_stackexchange
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/top_10_ranking_stackexchange dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.7844
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.998994974874372,
|
| 3 |
+
"eval_loss": 0.784430980682373,
|
| 4 |
+
"eval_runtime": 399.5634,
|
| 5 |
+
"eval_samples_per_second": 25.162,
|
| 6 |
+
"eval_steps_per_second": 0.395,
|
| 7 |
+
"total_flos": 1874157297991680.0,
|
| 8 |
+
"train_loss": 0.7673776837946369,
|
| 9 |
+
"train_runtime": 65939.4578,
|
| 10 |
+
"train_samples_per_second": 8.691,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.998994974874372,
|
| 3 |
+
"eval_loss": 0.784430980682373,
|
| 4 |
+
"eval_runtime": 399.5634,
|
| 5 |
+
"eval_samples_per_second": 25.162,
|
| 6 |
+
"eval_steps_per_second": 0.395
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.998994974874372,
|
| 3 |
+
"total_flos": 1874157297991680.0,
|
| 4 |
+
"train_loss": 0.7673776837946369,
|
| 5 |
+
"train_runtime": 65939.4578,
|
| 6 |
+
"train_samples_per_second": 8.691,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,843 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.998994974874372,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1119,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02680067001675042,
|
| 13 |
+
"grad_norm": 31.10676739208888,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.0442,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05360134003350084,
|
| 20 |
+
"grad_norm": 4.120159718355311,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.955,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08040201005025126,
|
| 27 |
+
"grad_norm": 2.339286993290118,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.9144,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.10720268006700168,
|
| 34 |
+
"grad_norm": 1.0759658796503169,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.8882,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.13400335008375208,
|
| 41 |
+
"grad_norm": 0.6453086287600575,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.8699,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.16080402010050251,
|
| 48 |
+
"grad_norm": 1.1160652028087201,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.8652,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.18760469011725292,
|
| 55 |
+
"grad_norm": 0.6258812701119981,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.848,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.21440536013400335,
|
| 62 |
+
"grad_norm": 0.5590720583080133,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.8463,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.24120603015075376,
|
| 69 |
+
"grad_norm": 0.6795899721647743,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.8393,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.26800670016750416,
|
| 76 |
+
"grad_norm": 1.1809098922748584,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.8335,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2948073701842546,
|
| 83 |
+
"grad_norm": 0.8420170258665194,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.8354,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.32160804020100503,
|
| 90 |
+
"grad_norm": 0.6851931492236875,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.8311,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.34840871021775544,
|
| 97 |
+
"grad_norm": 0.9823271515850558,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.8338,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.37520938023450584,
|
| 104 |
+
"grad_norm": 0.7764734742568185,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.8308,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4020100502512563,
|
| 111 |
+
"grad_norm": 0.8463569347395117,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.8223,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4288107202680067,
|
| 118 |
+
"grad_norm": 0.7229327877216101,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.8265,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.4556113902847571,
|
| 125 |
+
"grad_norm": 0.7406267992443841,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.8192,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.4824120603015075,
|
| 132 |
+
"grad_norm": 0.5245160572062765,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.8175,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.509212730318258,
|
| 139 |
+
"grad_norm": 0.5446187756240741,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.8173,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5360134003350083,
|
| 146 |
+
"grad_norm": 0.5387389341379448,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.8152,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5628140703517588,
|
| 153 |
+
"grad_norm": 0.5942914061122081,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.8158,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5896147403685092,
|
| 160 |
+
"grad_norm": 0.7289915117140335,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.8157,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6164154103852596,
|
| 167 |
+
"grad_norm": 0.6166043522729069,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.8154,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6432160804020101,
|
| 174 |
+
"grad_norm": 0.5402182876037194,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.81,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6700167504187605,
|
| 181 |
+
"grad_norm": 0.702136667602188,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.8086,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6968174204355109,
|
| 188 |
+
"grad_norm": 0.5548041175483877,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.8067,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7236180904522613,
|
| 195 |
+
"grad_norm": 0.5933880054884063,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.8046,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7504187604690117,
|
| 202 |
+
"grad_norm": 0.6218650700836093,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.8045,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.7772194304857621,
|
| 209 |
+
"grad_norm": 0.6636079178178366,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.8029,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.8040201005025126,
|
| 216 |
+
"grad_norm": 0.7578337185188113,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.8017,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.830820770519263,
|
| 223 |
+
"grad_norm": 0.5964607129683942,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.8039,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8576214405360134,
|
| 230 |
+
"grad_norm": 0.5731797399351095,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.8018,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.8844221105527639,
|
| 237 |
+
"grad_norm": 1.2550493135376506,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.7994,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.9112227805695142,
|
| 244 |
+
"grad_norm": 0.9368889967347727,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.8074,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.9380234505862647,
|
| 251 |
+
"grad_norm": 0.5921834072388994,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.8049,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.964824120603015,
|
| 258 |
+
"grad_norm": 0.5216457733637546,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.8019,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.9916247906197655,
|
| 265 |
+
"grad_norm": 0.6220842275028926,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.7989,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.9996649916247906,
|
| 272 |
+
"eval_loss": 0.7980747222900391,
|
| 273 |
+
"eval_runtime": 396.9204,
|
| 274 |
+
"eval_samples_per_second": 25.33,
|
| 275 |
+
"eval_steps_per_second": 0.398,
|
| 276 |
+
"step": 373
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.018425460636516,
|
| 280 |
+
"grad_norm": 0.8379563173937747,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.846,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.0452261306532664,
|
| 287 |
+
"grad_norm": 0.7007106059150332,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.7553,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.0720268006700167,
|
| 294 |
+
"grad_norm": 0.6985327962246497,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.7609,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.0988274706867671,
|
| 301 |
+
"grad_norm": 0.8231254452075508,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.7594,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.1256281407035176,
|
| 308 |
+
"grad_norm": 0.5396289186374543,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.7555,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.152428810720268,
|
| 315 |
+
"grad_norm": 0.5275185306049085,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.7554,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1792294807370185,
|
| 322 |
+
"grad_norm": 0.5322161709304825,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.7592,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.2060301507537687,
|
| 329 |
+
"grad_norm": 0.6335605844571386,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.7569,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.2328308207705192,
|
| 336 |
+
"grad_norm": 0.6175137584423412,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.7545,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.2596314907872697,
|
| 343 |
+
"grad_norm": 0.5525760530230355,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.755,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2864321608040201,
|
| 350 |
+
"grad_norm": 0.8168923150097971,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.7546,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.3132328308207706,
|
| 357 |
+
"grad_norm": 0.576393540227948,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.7613,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.3400335008375208,
|
| 364 |
+
"grad_norm": 0.5454484709306812,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.7558,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.3668341708542713,
|
| 371 |
+
"grad_norm": 0.519519630849878,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.7513,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3936348408710217,
|
| 378 |
+
"grad_norm": 0.5412825055890007,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.757,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.4204355108877722,
|
| 385 |
+
"grad_norm": 0.6663985833801256,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.7549,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.4472361809045227,
|
| 392 |
+
"grad_norm": 0.5433262572367299,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.7546,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.474036850921273,
|
| 399 |
+
"grad_norm": 0.4990591351939153,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.7483,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.5008375209380236,
|
| 406 |
+
"grad_norm": 0.5826918311899233,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.7554,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.5276381909547738,
|
| 413 |
+
"grad_norm": 0.5498876689910938,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.747,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.5544388609715243,
|
| 420 |
+
"grad_norm": 0.5033534721843692,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.7563,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.5812395309882747,
|
| 427 |
+
"grad_norm": 0.5475928059702524,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.7597,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.608040201005025,
|
| 434 |
+
"grad_norm": 0.5483658876220942,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.7538,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.6348408710217757,
|
| 441 |
+
"grad_norm": 0.550772312369244,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.7552,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.661641541038526,
|
| 448 |
+
"grad_norm": 0.541814614413297,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.7556,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.6884422110552764,
|
| 455 |
+
"grad_norm": 0.5623412222166373,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.7523,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.7152428810720268,
|
| 462 |
+
"grad_norm": 0.5486383001151054,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.7548,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.742043551088777,
|
| 469 |
+
"grad_norm": 0.6450442334835524,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.7506,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.7688442211055277,
|
| 476 |
+
"grad_norm": 0.5093346834442244,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.7526,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.795644891122278,
|
| 483 |
+
"grad_norm": 0.5882959805663536,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.756,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.8224455611390284,
|
| 490 |
+
"grad_norm": 0.6121773592899815,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.7516,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.849246231155779,
|
| 497 |
+
"grad_norm": 0.5053865601023015,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.7552,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.8760469011725294,
|
| 504 |
+
"grad_norm": 0.49653124526114595,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.7506,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.9028475711892798,
|
| 511 |
+
"grad_norm": 0.5356438120020067,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.7512,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.92964824120603,
|
| 518 |
+
"grad_norm": 0.4792312103436412,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.7523,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.9564489112227805,
|
| 525 |
+
"grad_norm": 0.5887442908787863,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.7489,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.983249581239531,
|
| 532 |
+
"grad_norm": 0.6013288648401325,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.7568,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.9993299832495812,
|
| 539 |
+
"eval_loss": 0.7848142385482788,
|
| 540 |
+
"eval_runtime": 399.6688,
|
| 541 |
+
"eval_samples_per_second": 25.156,
|
| 542 |
+
"eval_steps_per_second": 0.395,
|
| 543 |
+
"step": 746
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.0100502512562812,
|
| 547 |
+
"grad_norm": 0.7899358115042834,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.806,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.036850921273032,
|
| 554 |
+
"grad_norm": 0.5438655957140969,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.7051,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.063651591289782,
|
| 561 |
+
"grad_norm": 0.5954978197528383,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.7054,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.090452261306533,
|
| 568 |
+
"grad_norm": 0.5330734638287157,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.7057,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.117252931323283,
|
| 575 |
+
"grad_norm": 0.5719591031814022,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.7074,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.1440536013400333,
|
| 582 |
+
"grad_norm": 0.5749015032749988,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.7035,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.170854271356784,
|
| 589 |
+
"grad_norm": 0.7000012184675283,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.7045,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.1976549413735342,
|
| 596 |
+
"grad_norm": 0.5221545575547275,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.7085,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.224455611390285,
|
| 603 |
+
"grad_norm": 0.5590282858104586,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.7067,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.251256281407035,
|
| 610 |
+
"grad_norm": 0.680247988597194,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.712,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.2780569514237854,
|
| 617 |
+
"grad_norm": 0.5724224597541392,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.7132,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.304857621440536,
|
| 624 |
+
"grad_norm": 0.5890303699337465,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.7126,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.3316582914572863,
|
| 631 |
+
"grad_norm": 0.7060913656445702,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.71,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.358458961474037,
|
| 638 |
+
"grad_norm": 0.5199319551859399,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.7095,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.3852596314907872,
|
| 645 |
+
"grad_norm": 0.5667231972196302,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.7091,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.4120603015075375,
|
| 652 |
+
"grad_norm": 0.5776579179225979,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.7061,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.438860971524288,
|
| 659 |
+
"grad_norm": 0.5068031699453062,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.709,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.4656616415410384,
|
| 666 |
+
"grad_norm": 0.5622723362640956,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.7092,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.492462311557789,
|
| 673 |
+
"grad_norm": 0.6678938168210493,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.7074,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.5192629815745393,
|
| 680 |
+
"grad_norm": 0.7495016986714225,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.7123,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.5460636515912896,
|
| 687 |
+
"grad_norm": 0.5890832065298138,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.7117,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.5728643216080402,
|
| 694 |
+
"grad_norm": 0.5358789200826624,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.7123,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.5996649916247905,
|
| 701 |
+
"grad_norm": 0.7046518448288711,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.7124,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.626465661641541,
|
| 708 |
+
"grad_norm": 0.5598275583119999,
|
| 709 |
+
"learning_rate": 5e-06,
|
| 710 |
+
"loss": 0.7095,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.6532663316582914,
|
| 715 |
+
"grad_norm": 0.6175269384061102,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.7098,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.6800670016750416,
|
| 722 |
+
"grad_norm": 0.5833546621317353,
|
| 723 |
+
"learning_rate": 5e-06,
|
| 724 |
+
"loss": 0.7114,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.7068676716917923,
|
| 729 |
+
"grad_norm": 0.5577868241277573,
|
| 730 |
+
"learning_rate": 5e-06,
|
| 731 |
+
"loss": 0.7126,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.7336683417085426,
|
| 736 |
+
"grad_norm": 0.5384748297588693,
|
| 737 |
+
"learning_rate": 5e-06,
|
| 738 |
+
"loss": 0.7107,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.7604690117252932,
|
| 743 |
+
"grad_norm": 0.6077432046061476,
|
| 744 |
+
"learning_rate": 5e-06,
|
| 745 |
+
"loss": 0.708,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.7872696817420435,
|
| 750 |
+
"grad_norm": 0.5845658826184227,
|
| 751 |
+
"learning_rate": 5e-06,
|
| 752 |
+
"loss": 0.7166,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.8140703517587937,
|
| 757 |
+
"grad_norm": 0.5139932571124606,
|
| 758 |
+
"learning_rate": 5e-06,
|
| 759 |
+
"loss": 0.7112,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.8408710217755444,
|
| 764 |
+
"grad_norm": 0.5214647759988249,
|
| 765 |
+
"learning_rate": 5e-06,
|
| 766 |
+
"loss": 0.7083,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.8676716917922946,
|
| 771 |
+
"grad_norm": 0.6459251681734683,
|
| 772 |
+
"learning_rate": 5e-06,
|
| 773 |
+
"loss": 0.7165,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.8944723618090453,
|
| 778 |
+
"grad_norm": 0.6289426280816557,
|
| 779 |
+
"learning_rate": 5e-06,
|
| 780 |
+
"loss": 0.7126,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.9212730318257956,
|
| 785 |
+
"grad_norm": 0.4931010807851759,
|
| 786 |
+
"learning_rate": 5e-06,
|
| 787 |
+
"loss": 0.709,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.948073701842546,
|
| 792 |
+
"grad_norm": 0.5257070901798452,
|
| 793 |
+
"learning_rate": 5e-06,
|
| 794 |
+
"loss": 0.7131,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.9748743718592965,
|
| 799 |
+
"grad_norm": 0.5735309103540566,
|
| 800 |
+
"learning_rate": 5e-06,
|
| 801 |
+
"loss": 0.7167,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.998994974874372,
|
| 806 |
+
"eval_loss": 0.784430980682373,
|
| 807 |
+
"eval_runtime": 398.3496,
|
| 808 |
+
"eval_samples_per_second": 25.239,
|
| 809 |
+
"eval_steps_per_second": 0.397,
|
| 810 |
+
"step": 1119
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.998994974874372,
|
| 814 |
+
"step": 1119,
|
| 815 |
+
"total_flos": 1874157297991680.0,
|
| 816 |
+
"train_loss": 0.7673776837946369,
|
| 817 |
+
"train_runtime": 65939.4578,
|
| 818 |
+
"train_samples_per_second": 8.691,
|
| 819 |
+
"train_steps_per_second": 0.017
|
| 820 |
+
}
|
| 821 |
+
],
|
| 822 |
+
"logging_steps": 10,
|
| 823 |
+
"max_steps": 1119,
|
| 824 |
+
"num_input_tokens_seen": 0,
|
| 825 |
+
"num_train_epochs": 3,
|
| 826 |
+
"save_steps": 500,
|
| 827 |
+
"stateful_callbacks": {
|
| 828 |
+
"TrainerControl": {
|
| 829 |
+
"args": {
|
| 830 |
+
"should_epoch_stop": false,
|
| 831 |
+
"should_evaluate": false,
|
| 832 |
+
"should_log": false,
|
| 833 |
+
"should_save": true,
|
| 834 |
+
"should_training_stop": true
|
| 835 |
+
},
|
| 836 |
+
"attributes": {}
|
| 837 |
+
}
|
| 838 |
+
},
|
| 839 |
+
"total_flos": 1874157297991680.0,
|
| 840 |
+
"train_batch_size": 8,
|
| 841 |
+
"trial_name": null,
|
| 842 |
+
"trial_params": null
|
| 843 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|