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 +759 -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_original_wo_gpt4_llm
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# OH_original_wo_gpt4_llm
|
| 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: 0.6056
|
| 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_original_wo_gpt4_llm
|
|
|
|
| 16 |
|
| 17 |
# OH_original_wo_gpt4_llm
|
| 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_original_wo_gpt4_llm dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6056
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.995488721804511,
|
| 3 |
+
"eval_loss": 0.605595588684082,
|
| 4 |
+
"eval_runtime": 111.9171,
|
| 5 |
+
"eval_samples_per_second": 80.041,
|
| 6 |
+
"eval_steps_per_second": 0.625,
|
| 7 |
+
"total_flos": 1667918337146880.0,
|
| 8 |
+
"train_loss": 0.5664463261045126,
|
| 9 |
+
"train_runtime": 17372.9601,
|
| 10 |
+
"train_samples_per_second": 29.39,
|
| 11 |
+
"train_steps_per_second": 0.057
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.995488721804511,
|
| 3 |
+
"eval_loss": 0.605595588684082,
|
| 4 |
+
"eval_runtime": 111.9171,
|
| 5 |
+
"eval_samples_per_second": 80.041,
|
| 6 |
+
"eval_steps_per_second": 0.625
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.995488721804511,
|
| 3 |
+
"total_flos": 1667918337146880.0,
|
| 4 |
+
"train_loss": 0.5664463261045126,
|
| 5 |
+
"train_runtime": 17372.9601,
|
| 6 |
+
"train_samples_per_second": 29.39,
|
| 7 |
+
"train_steps_per_second": 0.057
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,759 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.995488721804511,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 996,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03007518796992481,
|
| 13 |
+
"grad_norm": 5.823914796640075,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.801,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06015037593984962,
|
| 20 |
+
"grad_norm": 2.3399969132192253,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.7172,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09022556390977443,
|
| 27 |
+
"grad_norm": 0.8783578572732146,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6923,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12030075187969924,
|
| 34 |
+
"grad_norm": 1.7232554735132826,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6834,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.15037593984962405,
|
| 41 |
+
"grad_norm": 1.6494035164725938,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6655,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.18045112781954886,
|
| 48 |
+
"grad_norm": 0.9942658093552336,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.6568,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21052631578947367,
|
| 55 |
+
"grad_norm": 0.8609069727317351,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.6548,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.24060150375939848,
|
| 62 |
+
"grad_norm": 0.8740060444495542,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.6454,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.2706766917293233,
|
| 69 |
+
"grad_norm": 1.0114201009544495,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.6331,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3007518796992481,
|
| 76 |
+
"grad_norm": 0.782353210012559,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6267,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3308270676691729,
|
| 83 |
+
"grad_norm": 0.6061308240718153,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6305,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3609022556390977,
|
| 90 |
+
"grad_norm": 0.663886451339362,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6246,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.39097744360902253,
|
| 97 |
+
"grad_norm": 0.8509285444900951,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6305,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.42105263157894735,
|
| 104 |
+
"grad_norm": 0.650634026198435,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6291,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.45112781954887216,
|
| 111 |
+
"grad_norm": 0.7050446482120244,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6279,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.48120300751879697,
|
| 118 |
+
"grad_norm": 0.5260864128397903,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6167,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5112781954887218,
|
| 125 |
+
"grad_norm": 0.5159636362174167,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6189,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5413533834586466,
|
| 132 |
+
"grad_norm": 0.576027072578746,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6096,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5714285714285714,
|
| 139 |
+
"grad_norm": 0.6020714354457843,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6207,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6015037593984962,
|
| 146 |
+
"grad_norm": 0.8904744763001984,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6143,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.631578947368421,
|
| 153 |
+
"grad_norm": 0.5645606661034147,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.619,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6616541353383458,
|
| 160 |
+
"grad_norm": 0.7456282489942,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6229,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.6917293233082706,
|
| 167 |
+
"grad_norm": 0.47671003637879944,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6141,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7218045112781954,
|
| 174 |
+
"grad_norm": 0.5712162016443497,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6148,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7518796992481203,
|
| 181 |
+
"grad_norm": 0.5787527818544967,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6112,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7819548872180451,
|
| 188 |
+
"grad_norm": 0.7727895820276254,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6124,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8120300751879699,
|
| 195 |
+
"grad_norm": 0.6627350412484229,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6101,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8421052631578947,
|
| 202 |
+
"grad_norm": 0.49307733921025576,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6101,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8721804511278195,
|
| 209 |
+
"grad_norm": 0.5299740752648865,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6074,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9022556390977443,
|
| 216 |
+
"grad_norm": 0.9821666854504033,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6035,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9323308270676691,
|
| 223 |
+
"grad_norm": 0.5537120584191855,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6037,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9624060150375939,
|
| 230 |
+
"grad_norm": 0.5346047989400851,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6128,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9924812030075187,
|
| 237 |
+
"grad_norm": 0.5177704737274331,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.6043,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.9984962406015038,
|
| 244 |
+
"eval_loss": 0.6096732020378113,
|
| 245 |
+
"eval_runtime": 116.9563,
|
| 246 |
+
"eval_samples_per_second": 76.593,
|
| 247 |
+
"eval_steps_per_second": 0.599,
|
| 248 |
+
"step": 332
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0225563909774436,
|
| 252 |
+
"grad_norm": 0.4996873605367385,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.58,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0526315789473684,
|
| 259 |
+
"grad_norm": 0.59979801353788,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.5596,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.0827067669172932,
|
| 266 |
+
"grad_norm": 0.645810347625552,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.5591,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.112781954887218,
|
| 273 |
+
"grad_norm": 0.6113621459091085,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.5553,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1428571428571428,
|
| 280 |
+
"grad_norm": 0.6400931476209645,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.5564,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.1729323308270676,
|
| 287 |
+
"grad_norm": 0.6192317007821239,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.5605,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.2030075187969924,
|
| 294 |
+
"grad_norm": 0.5237078678145406,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.5519,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2330827067669172,
|
| 301 |
+
"grad_norm": 0.5140051147329998,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.5574,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.263157894736842,
|
| 308 |
+
"grad_norm": 0.6369697944320184,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.5541,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.2932330827067668,
|
| 315 |
+
"grad_norm": 0.5985062376730702,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.5582,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.3233082706766917,
|
| 322 |
+
"grad_norm": 0.48850272868134653,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.5532,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3533834586466165,
|
| 329 |
+
"grad_norm": 0.5920840023317582,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.5571,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.3834586466165413,
|
| 336 |
+
"grad_norm": 0.5287134171137652,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.5487,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.413533834586466,
|
| 343 |
+
"grad_norm": 0.48569117162380887,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.5586,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.443609022556391,
|
| 350 |
+
"grad_norm": 0.5524909003831754,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.5528,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.4736842105263157,
|
| 357 |
+
"grad_norm": 0.45528161895298735,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.5624,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.5037593984962405,
|
| 364 |
+
"grad_norm": 0.5654083015816137,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5565,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.5338345864661656,
|
| 371 |
+
"grad_norm": 0.5087876058685868,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.5587,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.5639097744360901,
|
| 378 |
+
"grad_norm": 0.4290062049121276,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.5493,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.5939849624060152,
|
| 385 |
+
"grad_norm": 0.6235091434876753,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.5603,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6240601503759398,
|
| 392 |
+
"grad_norm": 0.5314512113272476,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.5564,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.6541353383458648,
|
| 399 |
+
"grad_norm": 0.5049026603516721,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.5605,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.6842105263157894,
|
| 406 |
+
"grad_norm": 0.5650921119799542,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.5601,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.7142857142857144,
|
| 413 |
+
"grad_norm": 0.5193160484708012,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.5554,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.744360902255639,
|
| 420 |
+
"grad_norm": 0.5213313242863221,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.5645,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.774436090225564,
|
| 427 |
+
"grad_norm": 0.6327600595776153,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.5536,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.8045112781954886,
|
| 434 |
+
"grad_norm": 0.5461472827380875,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.5625,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.8345864661654137,
|
| 441 |
+
"grad_norm": 0.6541180795154581,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.554,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.8646616541353382,
|
| 448 |
+
"grad_norm": 0.5572692340571848,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.5529,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.8947368421052633,
|
| 455 |
+
"grad_norm": 0.5724927689201437,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.547,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.9248120300751879,
|
| 462 |
+
"grad_norm": 0.48899030621990486,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.5508,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.954887218045113,
|
| 469 |
+
"grad_norm": 0.4783796037203571,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.5626,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.9849624060150375,
|
| 476 |
+
"grad_norm": 0.4380429796439722,
|
| 477 |
+
"learning_rate": 5e-06,
|
| 478 |
+
"loss": 0.5579,
|
| 479 |
+
"step": 660
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.0,
|
| 483 |
+
"eval_loss": 0.6012639403343201,
|
| 484 |
+
"eval_runtime": 116.0368,
|
| 485 |
+
"eval_samples_per_second": 77.2,
|
| 486 |
+
"eval_steps_per_second": 0.603,
|
| 487 |
+
"step": 665
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.0150375939849625,
|
| 491 |
+
"grad_norm": 0.8195061236201225,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.5349,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.045112781954887,
|
| 498 |
+
"grad_norm": 0.5727072462132908,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.5023,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.075187969924812,
|
| 505 |
+
"grad_norm": 0.5716937306059446,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.5025,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.1052631578947367,
|
| 512 |
+
"grad_norm": 0.5936120169922254,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.502,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.1353383458646618,
|
| 519 |
+
"grad_norm": 0.5323072505815232,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.5005,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.1654135338345863,
|
| 526 |
+
"grad_norm": 0.5082968360924967,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.5037,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.1954887218045114,
|
| 533 |
+
"grad_norm": 0.5227485772254855,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.4989,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.225563909774436,
|
| 540 |
+
"grad_norm": 0.6533374147188858,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.5051,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.255639097744361,
|
| 547 |
+
"grad_norm": 0.5912234992209703,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.5048,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.2857142857142856,
|
| 554 |
+
"grad_norm": 0.5434227115064355,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.508,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.3157894736842106,
|
| 561 |
+
"grad_norm": 0.5720087264790767,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.5099,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.345864661654135,
|
| 568 |
+
"grad_norm": 0.6089476678610672,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.5024,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.3759398496240602,
|
| 575 |
+
"grad_norm": 0.5508640915356684,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.5115,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.406015037593985,
|
| 582 |
+
"grad_norm": 0.5118656252283122,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.5051,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.43609022556391,
|
| 589 |
+
"grad_norm": 0.5065404177593222,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.5094,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.4661654135338344,
|
| 596 |
+
"grad_norm": 0.5181429354716248,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.5106,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.4962406015037595,
|
| 603 |
+
"grad_norm": 0.5322514457543749,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.5109,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.526315789473684,
|
| 610 |
+
"grad_norm": 0.6196654734671412,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5061,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.556390977443609,
|
| 617 |
+
"grad_norm": 0.5256550356188423,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5096,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.5864661654135337,
|
| 624 |
+
"grad_norm": 0.4721653082846406,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5091,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.6165413533834587,
|
| 631 |
+
"grad_norm": 0.5461766886120224,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.5125,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.6466165413533833,
|
| 638 |
+
"grad_norm": 0.8881592761313983,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5133,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.6766917293233083,
|
| 645 |
+
"grad_norm": 0.5215263169318092,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.5137,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.706766917293233,
|
| 652 |
+
"grad_norm": 0.5970816519010325,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5085,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.736842105263158,
|
| 659 |
+
"grad_norm": 0.5663757119297533,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.5136,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.7669172932330826,
|
| 666 |
+
"grad_norm": 0.48531820284070437,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.5105,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.7969924812030076,
|
| 673 |
+
"grad_norm": 0.5235848494113168,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.5106,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.827067669172932,
|
| 680 |
+
"grad_norm": 0.6230274670862681,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.5109,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.857142857142857,
|
| 687 |
+
"grad_norm": 0.5464639670084257,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.502,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.887218045112782,
|
| 694 |
+
"grad_norm": 0.5388668922788399,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.5059,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.917293233082707,
|
| 701 |
+
"grad_norm": 0.5634658215547509,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.5147,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.9473684210526314,
|
| 708 |
+
"grad_norm": 0.5876554762818471,
|
| 709 |
+
"learning_rate": 5e-06,
|
| 710 |
+
"loss": 0.507,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.9774436090225564,
|
| 715 |
+
"grad_norm": 0.5816222818084577,
|
| 716 |
+
"learning_rate": 5e-06,
|
| 717 |
+
"loss": 0.5116,
|
| 718 |
+
"step": 990
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.995488721804511,
|
| 722 |
+
"eval_loss": 0.605595588684082,
|
| 723 |
+
"eval_runtime": 114.1196,
|
| 724 |
+
"eval_samples_per_second": 78.497,
|
| 725 |
+
"eval_steps_per_second": 0.613,
|
| 726 |
+
"step": 996
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.995488721804511,
|
| 730 |
+
"step": 996,
|
| 731 |
+
"total_flos": 1667918337146880.0,
|
| 732 |
+
"train_loss": 0.5664463261045126,
|
| 733 |
+
"train_runtime": 17372.9601,
|
| 734 |
+
"train_samples_per_second": 29.39,
|
| 735 |
+
"train_steps_per_second": 0.057
|
| 736 |
+
}
|
| 737 |
+
],
|
| 738 |
+
"logging_steps": 10,
|
| 739 |
+
"max_steps": 996,
|
| 740 |
+
"num_input_tokens_seen": 0,
|
| 741 |
+
"num_train_epochs": 3,
|
| 742 |
+
"save_steps": 500,
|
| 743 |
+
"stateful_callbacks": {
|
| 744 |
+
"TrainerControl": {
|
| 745 |
+
"args": {
|
| 746 |
+
"should_epoch_stop": false,
|
| 747 |
+
"should_evaluate": false,
|
| 748 |
+
"should_log": false,
|
| 749 |
+
"should_save": true,
|
| 750 |
+
"should_training_stop": true
|
| 751 |
+
},
|
| 752 |
+
"attributes": {}
|
| 753 |
+
}
|
| 754 |
+
},
|
| 755 |
+
"total_flos": 1667918337146880.0,
|
| 756 |
+
"train_batch_size": 8,
|
| 757 |
+
"trial_name": null,
|
| 758 |
+
"trial_params": null
|
| 759 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|