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-dcft-v1.1-no-curation
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# oh-dcft-v1.1-no-curation
|
| 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: 0.4714
|
| 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-dcft-v1.1-no-curation
|
|
|
|
| 16 |
|
| 17 |
# oh-dcft-v1.1-no-curation
|
| 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-dcft-v1.1-no-curation dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.4714
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9980976537729864,
|
| 3 |
+
"eval_loss": 0.4713599979877472,
|
| 4 |
+
"eval_runtime": 132.103,
|
| 5 |
+
"eval_samples_per_second": 80.384,
|
| 6 |
+
"eval_steps_per_second": 0.628,
|
| 7 |
+
"total_flos": 1979475264798720.0,
|
| 8 |
+
"train_loss": 0.4632013658985067,
|
| 9 |
+
"train_runtime": 20039.4082,
|
| 10 |
+
"train_samples_per_second": 30.202,
|
| 11 |
+
"train_steps_per_second": 0.059
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9980976537729864,
|
| 3 |
+
"eval_loss": 0.4713599979877472,
|
| 4 |
+
"eval_runtime": 132.103,
|
| 5 |
+
"eval_samples_per_second": 80.384,
|
| 6 |
+
"eval_steps_per_second": 0.628
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9980976537729864,
|
| 3 |
+
"total_flos": 1979475264798720.0,
|
| 4 |
+
"train_loss": 0.4632013658985067,
|
| 5 |
+
"train_runtime": 20039.4082,
|
| 6 |
+
"train_samples_per_second": 30.202,
|
| 7 |
+
"train_steps_per_second": 0.059
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,892 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9980976537729864,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1182,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.025364616360177554,
|
| 13 |
+
"grad_norm": 2.4958535272810582,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7847,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05072923272035511,
|
| 20 |
+
"grad_norm": 1.332301089693953,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.6565,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07609384908053266,
|
| 27 |
+
"grad_norm": 0.8570758334622178,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6087,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.10145846544071022,
|
| 34 |
+
"grad_norm": 0.7961220667217911,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.5923,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.12682308180088775,
|
| 41 |
+
"grad_norm": 1.0397565268140934,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.5693,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1521876981610653,
|
| 48 |
+
"grad_norm": 0.8562621904197287,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.5503,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.17755231452124287,
|
| 55 |
+
"grad_norm": 0.8886037080258321,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.5498,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.20291693088142043,
|
| 62 |
+
"grad_norm": 0.6838633568199429,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.534,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.22828154724159797,
|
| 69 |
+
"grad_norm": 0.6556349806544307,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.535,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.2536461636017755,
|
| 76 |
+
"grad_norm": 0.7469146203238889,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.5333,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.27901077996195306,
|
| 83 |
+
"grad_norm": 0.5122739271343442,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.5172,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3043753963221306,
|
| 90 |
+
"grad_norm": 0.9622908612260581,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.5257,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3297400126823082,
|
| 97 |
+
"grad_norm": 0.6046903397133303,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.5151,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.35510462904248574,
|
| 104 |
+
"grad_norm": 0.47575500456135494,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.5143,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.3804692454026633,
|
| 111 |
+
"grad_norm": 0.7013205926571314,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.5144,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.40583386176284086,
|
| 118 |
+
"grad_norm": 0.6351422540630048,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.5058,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.43119847812301837,
|
| 125 |
+
"grad_norm": 0.6261693017885483,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.5102,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.45656309448319593,
|
| 132 |
+
"grad_norm": 0.7605740230985341,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.5078,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4819277108433735,
|
| 139 |
+
"grad_norm": 0.5845861272533613,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.5043,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.507292327203551,
|
| 146 |
+
"grad_norm": 0.7171099558889358,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.5053,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5326569435637286,
|
| 153 |
+
"grad_norm": 0.5158539718235372,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.5066,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5580215599239061,
|
| 160 |
+
"grad_norm": 0.7716179700630799,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.5037,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5833861762840837,
|
| 167 |
+
"grad_norm": 0.5356639716385265,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.5077,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6087507926442612,
|
| 174 |
+
"grad_norm": 0.5909560901543055,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.4978,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.6341154090044389,
|
| 181 |
+
"grad_norm": 0.5612449176342577,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.4955,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6594800253646164,
|
| 188 |
+
"grad_norm": 0.8220158158926282,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.4932,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.6848446417247939,
|
| 195 |
+
"grad_norm": 0.9803427711154427,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.4935,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7102092580849715,
|
| 202 |
+
"grad_norm": 0.7003489682973207,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.4921,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.735573874445149,
|
| 209 |
+
"grad_norm": 0.7155818668831541,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.4941,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7609384908053266,
|
| 216 |
+
"grad_norm": 0.5641884255018443,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.4905,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.7863031071655041,
|
| 223 |
+
"grad_norm": 0.5667685684791592,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.4972,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8116677235256817,
|
| 230 |
+
"grad_norm": 0.5424782856163526,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.4908,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.8370323398858592,
|
| 237 |
+
"grad_norm": 0.555119069867457,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.49,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8623969562460367,
|
| 244 |
+
"grad_norm": 0.5540403091132209,
|
| 245 |
+
"learning_rate": 5e-06,
|
| 246 |
+
"loss": 0.4892,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.8877615726062144,
|
| 251 |
+
"grad_norm": 0.6718528259146384,
|
| 252 |
+
"learning_rate": 5e-06,
|
| 253 |
+
"loss": 0.4879,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9131261889663919,
|
| 258 |
+
"grad_norm": 0.48504592421103015,
|
| 259 |
+
"learning_rate": 5e-06,
|
| 260 |
+
"loss": 0.4866,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.9384908053265695,
|
| 265 |
+
"grad_norm": 0.5794400662308987,
|
| 266 |
+
"learning_rate": 5e-06,
|
| 267 |
+
"loss": 0.489,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.963855421686747,
|
| 272 |
+
"grad_norm": 0.49175786205010735,
|
| 273 |
+
"learning_rate": 5e-06,
|
| 274 |
+
"loss": 0.4792,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.9892200380469245,
|
| 279 |
+
"grad_norm": 0.48088824717550854,
|
| 280 |
+
"learning_rate": 5e-06,
|
| 281 |
+
"loss": 0.4793,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.9993658845909955,
|
| 286 |
+
"eval_loss": 0.48458319902420044,
|
| 287 |
+
"eval_runtime": 140.5522,
|
| 288 |
+
"eval_samples_per_second": 75.552,
|
| 289 |
+
"eval_steps_per_second": 0.591,
|
| 290 |
+
"step": 394
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.014584654407102,
|
| 294 |
+
"grad_norm": 0.6241434976553506,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.4668,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.0399492707672797,
|
| 301 |
+
"grad_norm": 0.5387091155966651,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.4467,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.0653138871274572,
|
| 308 |
+
"grad_norm": 0.6088667420403366,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.4552,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.0906785034876347,
|
| 315 |
+
"grad_norm": 0.7635188991702534,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.4569,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1160431198478122,
|
| 322 |
+
"grad_norm": 0.5202613636726365,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.4532,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.1414077362079897,
|
| 329 |
+
"grad_norm": 0.5431289298627378,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.4552,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.1667723525681675,
|
| 336 |
+
"grad_norm": 0.5447516747773636,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.4517,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.192136968928345,
|
| 343 |
+
"grad_norm": 0.5811733767557097,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.4596,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2175015852885225,
|
| 350 |
+
"grad_norm": 0.5291374404256166,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.4523,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.2428662016487,
|
| 357 |
+
"grad_norm": 0.920406850160634,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.4512,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.2682308180088775,
|
| 364 |
+
"grad_norm": 0.5379277068224477,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.4589,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.2935954343690552,
|
| 371 |
+
"grad_norm": 0.6084288782824112,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.4476,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3189600507292327,
|
| 378 |
+
"grad_norm": 0.6373203390142074,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.4508,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.3443246670894102,
|
| 385 |
+
"grad_norm": 0.5297816500484004,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.4519,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.369689283449588,
|
| 392 |
+
"grad_norm": 0.5214550304276996,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.4507,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.3950538998097652,
|
| 399 |
+
"grad_norm": 0.5932937282969459,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.4508,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.420418516169943,
|
| 406 |
+
"grad_norm": 0.5015573262400715,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.4529,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.4457831325301205,
|
| 413 |
+
"grad_norm": 0.6541003393290922,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.4487,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.471147748890298,
|
| 420 |
+
"grad_norm": 0.4738510019221813,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.4437,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.4965123652504757,
|
| 427 |
+
"grad_norm": 0.5284328908203406,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.449,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.521876981610653,
|
| 434 |
+
"grad_norm": 0.5814801147707117,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.4498,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.5472415979708307,
|
| 441 |
+
"grad_norm": 0.7380939259733779,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.4574,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.5726062143310082,
|
| 448 |
+
"grad_norm": 0.5158189079851289,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.4553,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.5979708306911857,
|
| 455 |
+
"grad_norm": 0.7517859976181999,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.4479,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.6233354470513635,
|
| 462 |
+
"grad_norm": 0.4624484508717309,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.4484,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.6487000634115407,
|
| 469 |
+
"grad_norm": 0.6517886187802472,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.4479,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.6740646797717185,
|
| 476 |
+
"grad_norm": 0.5168694302612785,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.4498,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.699429296131896,
|
| 483 |
+
"grad_norm": 0.5442235822761647,
|
| 484 |
+
"learning_rate": 5e-06,
|
| 485 |
+
"loss": 0.4546,
|
| 486 |
+
"step": 670
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.7247939124920735,
|
| 490 |
+
"grad_norm": 0.5866332538354704,
|
| 491 |
+
"learning_rate": 5e-06,
|
| 492 |
+
"loss": 0.4502,
|
| 493 |
+
"step": 680
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.7501585288522512,
|
| 497 |
+
"grad_norm": 0.5771993285709256,
|
| 498 |
+
"learning_rate": 5e-06,
|
| 499 |
+
"loss": 0.4489,
|
| 500 |
+
"step": 690
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.7755231452124287,
|
| 504 |
+
"grad_norm": 0.5856601574541924,
|
| 505 |
+
"learning_rate": 5e-06,
|
| 506 |
+
"loss": 0.4516,
|
| 507 |
+
"step": 700
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.8008877615726062,
|
| 511 |
+
"grad_norm": 0.5219735572020098,
|
| 512 |
+
"learning_rate": 5e-06,
|
| 513 |
+
"loss": 0.4504,
|
| 514 |
+
"step": 710
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.8262523779327837,
|
| 518 |
+
"grad_norm": 0.5294326989128105,
|
| 519 |
+
"learning_rate": 5e-06,
|
| 520 |
+
"loss": 0.4512,
|
| 521 |
+
"step": 720
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.8516169942929612,
|
| 525 |
+
"grad_norm": 0.5043747110843602,
|
| 526 |
+
"learning_rate": 5e-06,
|
| 527 |
+
"loss": 0.4476,
|
| 528 |
+
"step": 730
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.876981610653139,
|
| 532 |
+
"grad_norm": 0.5243372113736201,
|
| 533 |
+
"learning_rate": 5e-06,
|
| 534 |
+
"loss": 0.4487,
|
| 535 |
+
"step": 740
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.9023462270133165,
|
| 539 |
+
"grad_norm": 0.46489075414726855,
|
| 540 |
+
"learning_rate": 5e-06,
|
| 541 |
+
"loss": 0.4477,
|
| 542 |
+
"step": 750
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.927710843373494,
|
| 546 |
+
"grad_norm": 0.47070137502563003,
|
| 547 |
+
"learning_rate": 5e-06,
|
| 548 |
+
"loss": 0.4491,
|
| 549 |
+
"step": 760
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.9530754597336717,
|
| 553 |
+
"grad_norm": 0.5114250833346574,
|
| 554 |
+
"learning_rate": 5e-06,
|
| 555 |
+
"loss": 0.4497,
|
| 556 |
+
"step": 770
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.978440076093849,
|
| 560 |
+
"grad_norm": 0.44673587993328173,
|
| 561 |
+
"learning_rate": 5e-06,
|
| 562 |
+
"loss": 0.4461,
|
| 563 |
+
"step": 780
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.9987317691819912,
|
| 567 |
+
"eval_loss": 0.4722590744495392,
|
| 568 |
+
"eval_runtime": 136.3111,
|
| 569 |
+
"eval_samples_per_second": 77.903,
|
| 570 |
+
"eval_steps_per_second": 0.609,
|
| 571 |
+
"step": 788
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.0038046924540267,
|
| 575 |
+
"grad_norm": 0.5253387493826779,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.4406,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.029169308814204,
|
| 582 |
+
"grad_norm": 0.5649979072148124,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.4174,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.0545339251743817,
|
| 589 |
+
"grad_norm": 0.554555886277626,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.416,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.0798985415345594,
|
| 596 |
+
"grad_norm": 0.5380213608538502,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.4075,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.1052631578947367,
|
| 603 |
+
"grad_norm": 0.6590004861365489,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.415,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.1306277742549145,
|
| 610 |
+
"grad_norm": 0.5145129946467305,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.4096,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.1559923906150917,
|
| 617 |
+
"grad_norm": 0.572199886696882,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.4189,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.1813570069752695,
|
| 624 |
+
"grad_norm": 0.5756593969633285,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.4201,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.206721623335447,
|
| 631 |
+
"grad_norm": 0.5265898189979799,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.4116,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.2320862396956245,
|
| 638 |
+
"grad_norm": 0.5424672160350248,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.4099,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.257450856055802,
|
| 645 |
+
"grad_norm": 0.5674446384978195,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.416,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.2828154724159795,
|
| 652 |
+
"grad_norm": 0.5128282183689237,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.4157,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.308180088776157,
|
| 659 |
+
"grad_norm": 0.5135015935006935,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.4172,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.333544705136335,
|
| 666 |
+
"grad_norm": 0.596189153928778,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.4152,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.3589093214965122,
|
| 673 |
+
"grad_norm": 0.5352826549369347,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.4149,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.38427393785669,
|
| 680 |
+
"grad_norm": 0.5014349895803593,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.4141,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.4096385542168672,
|
| 687 |
+
"grad_norm": 0.4805462505254729,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.4176,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.435003170577045,
|
| 694 |
+
"grad_norm": 0.6137290218711765,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.419,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.4603677869372227,
|
| 701 |
+
"grad_norm": 0.5732682054062723,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.4163,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.4857324032974,
|
| 708 |
+
"grad_norm": 0.4771910554061346,
|
| 709 |
+
"learning_rate": 5e-06,
|
| 710 |
+
"loss": 0.4134,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.5110970196575777,
|
| 715 |
+
"grad_norm": 0.476330897847943,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.4225,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.536461636017755,
|
| 722 |
+
"grad_norm": 0.47973764991876255,
|
| 723 |
+
"learning_rate": 5e-06,
|
| 724 |
+
"loss": 0.4145,
|
| 725 |
+
"step": 1000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.5618262523779327,
|
| 729 |
+
"grad_norm": 0.5939904213084772,
|
| 730 |
+
"learning_rate": 5e-06,
|
| 731 |
+
"loss": 0.4153,
|
| 732 |
+
"step": 1010
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.5871908687381104,
|
| 736 |
+
"grad_norm": 0.5936679428712734,
|
| 737 |
+
"learning_rate": 5e-06,
|
| 738 |
+
"loss": 0.4204,
|
| 739 |
+
"step": 1020
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.6125554850982877,
|
| 743 |
+
"grad_norm": 0.5188426106745951,
|
| 744 |
+
"learning_rate": 5e-06,
|
| 745 |
+
"loss": 0.4183,
|
| 746 |
+
"step": 1030
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.6379201014584654,
|
| 750 |
+
"grad_norm": 0.5644339619977095,
|
| 751 |
+
"learning_rate": 5e-06,
|
| 752 |
+
"loss": 0.4126,
|
| 753 |
+
"step": 1040
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.6632847178186427,
|
| 757 |
+
"grad_norm": 0.6020266606747191,
|
| 758 |
+
"learning_rate": 5e-06,
|
| 759 |
+
"loss": 0.4186,
|
| 760 |
+
"step": 1050
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.6886493341788205,
|
| 764 |
+
"grad_norm": 0.4752185053914476,
|
| 765 |
+
"learning_rate": 5e-06,
|
| 766 |
+
"loss": 0.4138,
|
| 767 |
+
"step": 1060
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.714013950538998,
|
| 771 |
+
"grad_norm": 0.7626568079783347,
|
| 772 |
+
"learning_rate": 5e-06,
|
| 773 |
+
"loss": 0.4135,
|
| 774 |
+
"step": 1070
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.739378566899176,
|
| 778 |
+
"grad_norm": 0.5108017704950135,
|
| 779 |
+
"learning_rate": 5e-06,
|
| 780 |
+
"loss": 0.4154,
|
| 781 |
+
"step": 1080
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.764743183259353,
|
| 785 |
+
"grad_norm": 0.5746749293115092,
|
| 786 |
+
"learning_rate": 5e-06,
|
| 787 |
+
"loss": 0.4173,
|
| 788 |
+
"step": 1090
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.7901077996195305,
|
| 792 |
+
"grad_norm": 0.5467822052037948,
|
| 793 |
+
"learning_rate": 5e-06,
|
| 794 |
+
"loss": 0.4166,
|
| 795 |
+
"step": 1100
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.815472415979708,
|
| 799 |
+
"grad_norm": 0.6357622704499519,
|
| 800 |
+
"learning_rate": 5e-06,
|
| 801 |
+
"loss": 0.4198,
|
| 802 |
+
"step": 1110
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.840837032339886,
|
| 806 |
+
"grad_norm": 0.7346508445377833,
|
| 807 |
+
"learning_rate": 5e-06,
|
| 808 |
+
"loss": 0.4161,
|
| 809 |
+
"step": 1120
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.8662016487000637,
|
| 813 |
+
"grad_norm": 0.4767595766550471,
|
| 814 |
+
"learning_rate": 5e-06,
|
| 815 |
+
"loss": 0.4136,
|
| 816 |
+
"step": 1130
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.891566265060241,
|
| 820 |
+
"grad_norm": 0.5450967603642648,
|
| 821 |
+
"learning_rate": 5e-06,
|
| 822 |
+
"loss": 0.416,
|
| 823 |
+
"step": 1140
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.9169308814204187,
|
| 827 |
+
"grad_norm": 0.6310631600995659,
|
| 828 |
+
"learning_rate": 5e-06,
|
| 829 |
+
"loss": 0.4156,
|
| 830 |
+
"step": 1150
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.942295497780596,
|
| 834 |
+
"grad_norm": 0.4875236135766479,
|
| 835 |
+
"learning_rate": 5e-06,
|
| 836 |
+
"loss": 0.4135,
|
| 837 |
+
"step": 1160
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.9676601141407737,
|
| 841 |
+
"grad_norm": 0.5024341899279373,
|
| 842 |
+
"learning_rate": 5e-06,
|
| 843 |
+
"loss": 0.4185,
|
| 844 |
+
"step": 1170
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.9930247305009514,
|
| 848 |
+
"grad_norm": 0.4812185425989623,
|
| 849 |
+
"learning_rate": 5e-06,
|
| 850 |
+
"loss": 0.422,
|
| 851 |
+
"step": 1180
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.9980976537729864,
|
| 855 |
+
"eval_loss": 0.4713599979877472,
|
| 856 |
+
"eval_runtime": 132.9609,
|
| 857 |
+
"eval_samples_per_second": 79.866,
|
| 858 |
+
"eval_steps_per_second": 0.624,
|
| 859 |
+
"step": 1182
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 2.9980976537729864,
|
| 863 |
+
"step": 1182,
|
| 864 |
+
"total_flos": 1979475264798720.0,
|
| 865 |
+
"train_loss": 0.4632013658985067,
|
| 866 |
+
"train_runtime": 20039.4082,
|
| 867 |
+
"train_samples_per_second": 30.202,
|
| 868 |
+
"train_steps_per_second": 0.059
|
| 869 |
+
}
|
| 870 |
+
],
|
| 871 |
+
"logging_steps": 10,
|
| 872 |
+
"max_steps": 1182,
|
| 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": 1979475264798720.0,
|
| 889 |
+
"train_batch_size": 8,
|
| 890 |
+
"trial_name": null,
|
| 891 |
+
"trial_params": null
|
| 892 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|