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 +892 -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/Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: oh_v1_w_v3_camel_math_gpt-4o-mini
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# oh_v1_w_v3_camel_math_gpt-4o-mini
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.5828
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: oh_v1_w_v3_camel_math_gpt-4o-mini
|
|
|
|
| 16 |
|
| 17 |
# oh_v1_w_v3_camel_math_gpt-4o-mini
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the mlfoundations-dev/oh_v1_w_v3_camel_math_gpt-4o-mini dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.5828
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9943289224952743,
|
| 3 |
+
"eval_loss": 0.58283931016922,
|
| 4 |
+
"eval_runtime": 212.0781,
|
| 5 |
+
"eval_samples_per_second": 50.411,
|
| 6 |
+
"eval_steps_per_second": 0.396,
|
| 7 |
+
"total_flos": 1989525488271360.0,
|
| 8 |
+
"train_loss": 0.5829599999418162,
|
| 9 |
+
"train_runtime": 35401.3525,
|
| 10 |
+
"train_samples_per_second": 17.213,
|
| 11 |
+
"train_steps_per_second": 0.034
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9943289224952743,
|
| 3 |
+
"eval_loss": 0.58283931016922,
|
| 4 |
+
"eval_runtime": 212.0781,
|
| 5 |
+
"eval_samples_per_second": 50.411,
|
| 6 |
+
"eval_steps_per_second": 0.396
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9943289224952743,
|
| 3 |
+
"total_flos": 1989525488271360.0,
|
| 4 |
+
"train_loss": 0.5829599999418162,
|
| 5 |
+
"train_runtime": 35401.3525,
|
| 6 |
+
"train_samples_per_second": 17.213,
|
| 7 |
+
"train_steps_per_second": 0.034
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,892 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9943289224952743,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1188,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02520478890989288,
|
| 13 |
+
"grad_norm": 9.633888402845015,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.9444,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05040957781978576,
|
| 20 |
+
"grad_norm": 1.6254228664238897,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.8095,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07561436672967864,
|
| 27 |
+
"grad_norm": 0.8936028314003451,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.7596,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.10081915563957151,
|
| 34 |
+
"grad_norm": 0.9708205238462188,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.7334,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1260239445494644,
|
| 41 |
+
"grad_norm": 0.8882056031134592,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.7166,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15122873345935728,
|
| 48 |
+
"grad_norm": 0.8542020955227222,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.7004,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.17643352236925017,
|
| 55 |
+
"grad_norm": 0.719450185402131,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.6877,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.20163831127914303,
|
| 62 |
+
"grad_norm": 0.6838086991132964,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.676,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.22684310018903592,
|
| 69 |
+
"grad_norm": 0.6199036833773371,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.6754,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2520478890989288,
|
| 76 |
+
"grad_norm": 0.5787703367375647,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6562,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2772526780088217,
|
| 83 |
+
"grad_norm": 0.633249705700733,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.665,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.30245746691871456,
|
| 90 |
+
"grad_norm": 0.6304627866586173,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6634,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3276622558286074,
|
| 97 |
+
"grad_norm": 0.5506728721157861,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6549,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.35286704473850034,
|
| 104 |
+
"grad_norm": 0.5151002955744762,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6522,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3780718336483932,
|
| 111 |
+
"grad_norm": 0.5992082289679086,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6528,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.40327662255828606,
|
| 118 |
+
"grad_norm": 0.4663777253829188,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.642,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.428481411468179,
|
| 125 |
+
"grad_norm": 0.5785034175448459,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6469,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.45368620037807184,
|
| 132 |
+
"grad_norm": 0.6585860693219876,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.646,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4788909892879647,
|
| 139 |
+
"grad_norm": 0.6722487645620258,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6403,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5040957781978576,
|
| 146 |
+
"grad_norm": 0.5254154176523609,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6387,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5293005671077504,
|
| 153 |
+
"grad_norm": 0.5128942747923588,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6379,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5545053560176434,
|
| 160 |
+
"grad_norm": 0.5642956436475494,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6393,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5797101449275363,
|
| 167 |
+
"grad_norm": 0.6837039476741191,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6359,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6049149338374291,
|
| 174 |
+
"grad_norm": 0.6667359902635842,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6351,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.630119722747322,
|
| 181 |
+
"grad_norm": 0.6627848973706361,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6343,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6553245116572148,
|
| 188 |
+
"grad_norm": 0.5241036221432155,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6279,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6805293005671077,
|
| 195 |
+
"grad_norm": 0.576211583526909,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6258,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7057340894770007,
|
| 202 |
+
"grad_norm": 0.5136516604177849,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6322,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.7309388783868935,
|
| 209 |
+
"grad_norm": 0.5270426246043673,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6243,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7561436672967864,
|
| 216 |
+
"grad_norm": 0.5453025715363531,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6224,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7813484562066793,
|
| 223 |
+
"grad_norm": 0.5116409906154713,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6155,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8065532451165721,
|
| 230 |
+
"grad_norm": 0.5849562966179552,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6212,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.831758034026465,
|
| 237 |
+
"grad_norm": 0.6135737091827808,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.6258,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.856962822936358,
|
| 244 |
+
"grad_norm": 0.5181177544801595,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.6238,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.8821676118462508,
|
| 251 |
+
"grad_norm": 0.627205460376999,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.6167,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9073724007561437,
|
| 258 |
+
"grad_norm": 0.5261678739160346,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.6117,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.9325771896660365,
|
| 265 |
+
"grad_norm": 0.6244352371075516,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.6153,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.9577819785759294,
|
| 272 |
+
"grad_norm": 0.48330689120915904,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.6157,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9829867674858223,
|
| 279 |
+
"grad_norm": 0.5423735222942331,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.6132,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.998109640831758,
|
| 286 |
+
"eval_loss": 0.6147013306617737,
|
| 287 |
+
"eval_runtime": 212.3997,
|
| 288 |
+
"eval_samples_per_second": 50.334,
|
| 289 |
+
"eval_steps_per_second": 0.395,
|
| 290 |
+
"step": 396
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.0081915563957151,
|
| 294 |
+
"grad_norm": 0.5070359483563761,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.6024,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.033396345305608,
|
| 301 |
+
"grad_norm": 0.5765247476192352,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.5805,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.0586011342155008,
|
| 308 |
+
"grad_norm": 0.6110502474250971,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.5715,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.0838059231253938,
|
| 315 |
+
"grad_norm": 0.7545087966794868,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.5797,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1090107120352868,
|
| 322 |
+
"grad_norm": 0.6365159456598485,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.5751,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.1342155009451795,
|
| 329 |
+
"grad_norm": 0.6056198671024684,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.5742,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.1594202898550725,
|
| 336 |
+
"grad_norm": 0.5291507949595291,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.5761,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.1846250787649653,
|
| 343 |
+
"grad_norm": 0.6153628132427752,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.5779,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2098298676748582,
|
| 350 |
+
"grad_norm": 0.5060871095129219,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.574,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.2350346565847512,
|
| 357 |
+
"grad_norm": 0.6456813781855114,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.5759,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.260239445494644,
|
| 364 |
+
"grad_norm": 0.5052335738280048,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5756,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.285444234404537,
|
| 371 |
+
"grad_norm": 0.5653893528313595,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.5754,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3106490233144297,
|
| 378 |
+
"grad_norm": 0.5278634789290781,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.5733,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.3358538122243226,
|
| 385 |
+
"grad_norm": 0.5245168937373562,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.5721,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.3610586011342156,
|
| 392 |
+
"grad_norm": 0.5215086066445794,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.5733,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.3862633900441084,
|
| 399 |
+
"grad_norm": 0.5370456877329636,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.571,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.4114681789540013,
|
| 406 |
+
"grad_norm": 0.5521665579415627,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.5698,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.436672967863894,
|
| 413 |
+
"grad_norm": 0.7002009297394419,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.5672,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.461877756773787,
|
| 420 |
+
"grad_norm": 0.5738916744555749,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.5646,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.48708254568368,
|
| 427 |
+
"grad_norm": 0.47370527901117226,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.5717,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.5122873345935728,
|
| 434 |
+
"grad_norm": 0.554049330965348,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.567,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.5374921235034655,
|
| 441 |
+
"grad_norm": 0.5960178872278222,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.5667,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.5626969124133585,
|
| 448 |
+
"grad_norm": 0.5085168346574576,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.5682,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.5879017013232515,
|
| 455 |
+
"grad_norm": 0.6537267193437978,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.5629,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.6131064902331445,
|
| 462 |
+
"grad_norm": 0.5874046443880916,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.5686,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.6383112791430372,
|
| 469 |
+
"grad_norm": 0.5727374180932888,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.5634,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.66351606805293,
|
| 476 |
+
"grad_norm": 0.4739882267214101,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.5643,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.688720856962823,
|
| 483 |
+
"grad_norm": 0.5225576157310349,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.5585,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.713925645872716,
|
| 490 |
+
"grad_norm": 0.5180601277471911,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.5656,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.7391304347826086,
|
| 497 |
+
"grad_norm": 0.4742139859545316,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.5601,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.7643352236925016,
|
| 504 |
+
"grad_norm": 0.569511350039058,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.5601,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.7895400126023944,
|
| 511 |
+
"grad_norm": 0.5632608053135445,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.5622,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.8147448015122873,
|
| 518 |
+
"grad_norm": 0.7901163025671061,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.5617,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.8399495904221803,
|
| 525 |
+
"grad_norm": 0.7242318592229516,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.5681,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.865154379332073,
|
| 532 |
+
"grad_norm": 0.5903083920098006,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.561,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.8903591682419658,
|
| 539 |
+
"grad_norm": 0.7074496398717507,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.5618,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.9155639571518588,
|
| 546 |
+
"grad_norm": 0.6211817411184037,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.5602,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.9407687460617518,
|
| 553 |
+
"grad_norm": 0.7491153337871396,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.5563,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.9659735349716447,
|
| 560 |
+
"grad_norm": 0.4814370775695788,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.5575,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.9911783238815375,
|
| 567 |
+
"grad_norm": 0.4983004502393923,
|
| 568 |
+
"learning_rate": 5e-06,
|
| 569 |
+
"loss": 0.5614,
|
| 570 |
+
"step": 790
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.9987397605545052,
|
| 574 |
+
"eval_loss": 0.5889107584953308,
|
| 575 |
+
"eval_runtime": 212.4952,
|
| 576 |
+
"eval_samples_per_second": 50.312,
|
| 577 |
+
"eval_steps_per_second": 0.395,
|
| 578 |
+
"step": 793
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.0163831127914302,
|
| 582 |
+
"grad_norm": 0.6245989305076182,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.5329,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.041587901701323,
|
| 589 |
+
"grad_norm": 0.5453952668705114,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.5187,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.066792690611216,
|
| 596 |
+
"grad_norm": 0.4731173438501679,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.5157,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.091997479521109,
|
| 603 |
+
"grad_norm": 0.5441667804629673,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.5227,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.1172022684310017,
|
| 610 |
+
"grad_norm": 0.5708819169258152,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5229,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.1424070573408946,
|
| 617 |
+
"grad_norm": 0.523183963336559,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5262,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.1676118462507876,
|
| 624 |
+
"grad_norm": 0.5229800543372238,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5235,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.1928166351606806,
|
| 631 |
+
"grad_norm": 0.5691473122380714,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.5177,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.2180214240705736,
|
| 638 |
+
"grad_norm": 0.5400039287033931,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5273,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.243226212980466,
|
| 645 |
+
"grad_norm": 0.5107824302626609,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.5323,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.268431001890359,
|
| 652 |
+
"grad_norm": 0.5059906821559053,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5202,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.293635790800252,
|
| 659 |
+
"grad_norm": 0.5379755140149425,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.5245,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.318840579710145,
|
| 666 |
+
"grad_norm": 0.5628132546435494,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.5227,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.344045368620038,
|
| 673 |
+
"grad_norm": 0.5940730599429787,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.5244,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.3692501575299305,
|
| 680 |
+
"grad_norm": 0.4876405401032709,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.5231,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.3944549464398235,
|
| 687 |
+
"grad_norm": 0.5287351322876084,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.5282,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.4196597353497165,
|
| 694 |
+
"grad_norm": 0.5497856784965347,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.5224,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.4448645242596094,
|
| 701 |
+
"grad_norm": 0.5169812352131126,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.5186,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.4700693131695024,
|
| 708 |
+
"grad_norm": 0.5065988236822105,
|
| 709 |
+
"learning_rate": 5e-06,
|
| 710 |
+
"loss": 0.5175,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.495274102079395,
|
| 715 |
+
"grad_norm": 0.5210233733825254,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.5167,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.520478890989288,
|
| 722 |
+
"grad_norm": 0.5188140313597245,
|
| 723 |
+
"learning_rate": 5e-06,
|
| 724 |
+
"loss": 0.518,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.545683679899181,
|
| 729 |
+
"grad_norm": 0.5405876217592858,
|
| 730 |
+
"learning_rate": 5e-06,
|
| 731 |
+
"loss": 0.5193,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.570888468809074,
|
| 736 |
+
"grad_norm": 0.46633858042210613,
|
| 737 |
+
"learning_rate": 5e-06,
|
| 738 |
+
"loss": 0.5248,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.596093257718967,
|
| 743 |
+
"grad_norm": 0.5030938635404251,
|
| 744 |
+
"learning_rate": 5e-06,
|
| 745 |
+
"loss": 0.5171,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.6212980466288593,
|
| 750 |
+
"grad_norm": 0.7552264831047579,
|
| 751 |
+
"learning_rate": 5e-06,
|
| 752 |
+
"loss": 0.5208,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.6465028355387523,
|
| 757 |
+
"grad_norm": 0.6446011609995526,
|
| 758 |
+
"learning_rate": 5e-06,
|
| 759 |
+
"loss": 0.5226,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.6717076244486453,
|
| 764 |
+
"grad_norm": 0.598720313170294,
|
| 765 |
+
"learning_rate": 5e-06,
|
| 766 |
+
"loss": 0.5201,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.6969124133585383,
|
| 771 |
+
"grad_norm": 0.5646013331239497,
|
| 772 |
+
"learning_rate": 5e-06,
|
| 773 |
+
"loss": 0.5247,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.7221172022684312,
|
| 778 |
+
"grad_norm": 0.5205190466062173,
|
| 779 |
+
"learning_rate": 5e-06,
|
| 780 |
+
"loss": 0.5228,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.7473219911783238,
|
| 785 |
+
"grad_norm": 0.6675587237327031,
|
| 786 |
+
"learning_rate": 5e-06,
|
| 787 |
+
"loss": 0.5238,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.7725267800882167,
|
| 792 |
+
"grad_norm": 0.5888446017638219,
|
| 793 |
+
"learning_rate": 5e-06,
|
| 794 |
+
"loss": 0.5246,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.7977315689981097,
|
| 799 |
+
"grad_norm": 0.5291240035154432,
|
| 800 |
+
"learning_rate": 5e-06,
|
| 801 |
+
"loss": 0.5207,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.8229363579080027,
|
| 806 |
+
"grad_norm": 0.5322435909276529,
|
| 807 |
+
"learning_rate": 5e-06,
|
| 808 |
+
"loss": 0.5167,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.8481411468178957,
|
| 813 |
+
"grad_norm": 0.4603004988767882,
|
| 814 |
+
"learning_rate": 5e-06,
|
| 815 |
+
"loss": 0.5236,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.873345935727788,
|
| 820 |
+
"grad_norm": 0.48682290640941545,
|
| 821 |
+
"learning_rate": 5e-06,
|
| 822 |
+
"loss": 0.5252,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.898550724637681,
|
| 827 |
+
"grad_norm": 0.5361316970255996,
|
| 828 |
+
"learning_rate": 5e-06,
|
| 829 |
+
"loss": 0.5264,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.923755513547574,
|
| 834 |
+
"grad_norm": 0.6157284870441493,
|
| 835 |
+
"learning_rate": 5e-06,
|
| 836 |
+
"loss": 0.5188,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.9489603024574667,
|
| 841 |
+
"grad_norm": 0.5584802223169939,
|
| 842 |
+
"learning_rate": 5e-06,
|
| 843 |
+
"loss": 0.5189,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.97416509136736,
|
| 848 |
+
"grad_norm": 0.5261737585816265,
|
| 849 |
+
"learning_rate": 5e-06,
|
| 850 |
+
"loss": 0.5205,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.9943289224952743,
|
| 855 |
+
"eval_loss": 0.58283931016922,
|
| 856 |
+
"eval_runtime": 213.9304,
|
| 857 |
+
"eval_samples_per_second": 49.974,
|
| 858 |
+
"eval_steps_per_second": 0.393,
|
| 859 |
+
"step": 1188
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.9943289224952743,
|
| 863 |
+
"step": 1188,
|
| 864 |
+
"total_flos": 1989525488271360.0,
|
| 865 |
+
"train_loss": 0.5829599999418162,
|
| 866 |
+
"train_runtime": 35401.3525,
|
| 867 |
+
"train_samples_per_second": 17.213,
|
| 868 |
+
"train_steps_per_second": 0.034
|
| 869 |
+
}
|
| 870 |
+
],
|
| 871 |
+
"logging_steps": 10,
|
| 872 |
+
"max_steps": 1188,
|
| 873 |
+
"num_input_tokens_seen": 0,
|
| 874 |
+
"num_train_epochs": 3,
|
| 875 |
+
"save_steps": 500,
|
| 876 |
+
"stateful_callbacks": {
|
| 877 |
+
"TrainerControl": {
|
| 878 |
+
"args": {
|
| 879 |
+
"should_epoch_stop": false,
|
| 880 |
+
"should_evaluate": false,
|
| 881 |
+
"should_log": false,
|
| 882 |
+
"should_save": true,
|
| 883 |
+
"should_training_stop": true
|
| 884 |
+
},
|
| 885 |
+
"attributes": {}
|
| 886 |
+
}
|
| 887 |
+
},
|
| 888 |
+
"total_flos": 1989525488271360.0,
|
| 889 |
+
"train_batch_size": 8,
|
| 890 |
+
"trial_name": null,
|
| 891 |
+
"trial_params": null
|
| 892 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|