Commit
•
5c0b824
1
Parent(s):
59ae145
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 +745 -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_metamath_40k
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# OH_original_wo_metamath_40k
|
| 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: 0.6206
|
| 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_metamath_40k
|
|
|
|
| 16 |
|
| 17 |
# OH_original_wo_metamath_40k
|
| 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_metamath_40k dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6206
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9977011494252874,
|
| 3 |
+
"eval_loss": 0.6206015944480896,
|
| 4 |
+
"eval_runtime": 174.9102,
|
| 5 |
+
"eval_samples_per_second": 50.237,
|
| 6 |
+
"eval_steps_per_second": 0.394,
|
| 7 |
+
"total_flos": 1637767666728960.0,
|
| 8 |
+
"train_loss": 0.5840159120735215,
|
| 9 |
+
"train_runtime": 29297.5545,
|
| 10 |
+
"train_samples_per_second": 17.094,
|
| 11 |
+
"train_steps_per_second": 0.033
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9977011494252874,
|
| 3 |
+
"eval_loss": 0.6206015944480896,
|
| 4 |
+
"eval_runtime": 174.9102,
|
| 5 |
+
"eval_samples_per_second": 50.237,
|
| 6 |
+
"eval_steps_per_second": 0.394
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9977011494252874,
|
| 3 |
+
"total_flos": 1637767666728960.0,
|
| 4 |
+
"train_loss": 0.5840159120735215,
|
| 5 |
+
"train_runtime": 29297.5545,
|
| 6 |
+
"train_samples_per_second": 17.094,
|
| 7 |
+
"train_steps_per_second": 0.033
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,745 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9977011494252874,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 978,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03065134099616858,
|
| 13 |
+
"grad_norm": 1.728469379207447,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.8116,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06130268199233716,
|
| 20 |
+
"grad_norm": 10.819369936863422,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.7399,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09195402298850575,
|
| 27 |
+
"grad_norm": 4.190454906116627,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.7334,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12260536398467432,
|
| 34 |
+
"grad_norm": 1.3438381662790366,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.7064,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1532567049808429,
|
| 41 |
+
"grad_norm": 0.8718769327333502,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6887,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1839080459770115,
|
| 48 |
+
"grad_norm": 1.005358100868816,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.6891,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21455938697318008,
|
| 55 |
+
"grad_norm": 1.4650120091926921,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.6725,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.24521072796934865,
|
| 62 |
+
"grad_norm": 0.7835954045094561,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.6616,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.27586206896551724,
|
| 69 |
+
"grad_norm": 0.8866257551751919,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.6505,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3065134099616858,
|
| 76 |
+
"grad_norm": 0.5918777617135533,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6513,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3371647509578544,
|
| 83 |
+
"grad_norm": 0.5197043260328372,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6424,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.367816091954023,
|
| 90 |
+
"grad_norm": 1.3052113076963672,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6453,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.39846743295019155,
|
| 97 |
+
"grad_norm": 1.1472080859635072,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6473,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.42911877394636017,
|
| 104 |
+
"grad_norm": 0.6535118613806697,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6464,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.45977011494252873,
|
| 111 |
+
"grad_norm": 0.5755555420983144,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6502,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4904214559386973,
|
| 118 |
+
"grad_norm": 0.5960503646265235,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6399,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5210727969348659,
|
| 125 |
+
"grad_norm": 0.6534430237511478,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6404,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5517241379310345,
|
| 132 |
+
"grad_norm": 0.479772716926196,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6379,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.5823754789272031,
|
| 139 |
+
"grad_norm": 0.6700701447636983,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6268,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6130268199233716,
|
| 146 |
+
"grad_norm": 0.46981415838615953,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6332,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6436781609195402,
|
| 153 |
+
"grad_norm": 0.6740217268091045,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6315,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.6743295019157088,
|
| 160 |
+
"grad_norm": 0.45781083259612837,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6251,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7049808429118773,
|
| 167 |
+
"grad_norm": 0.46419264516556447,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6331,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.735632183908046,
|
| 174 |
+
"grad_norm": 0.46609321446559443,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.636,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7662835249042146,
|
| 181 |
+
"grad_norm": 0.5350231771223092,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6177,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7969348659003831,
|
| 188 |
+
"grad_norm": 0.4743633834962204,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6261,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8275862068965517,
|
| 195 |
+
"grad_norm": 0.6677241895273329,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6334,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8582375478927203,
|
| 202 |
+
"grad_norm": 0.5408535187898951,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.628,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8888888888888888,
|
| 209 |
+
"grad_norm": 0.6364909996205239,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6304,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9195402298850575,
|
| 216 |
+
"grad_norm": 0.5219626763836217,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.624,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9501915708812261,
|
| 223 |
+
"grad_norm": 0.6504021944371435,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6229,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9808429118773946,
|
| 230 |
+
"grad_norm": 0.5113118633186393,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6389,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.9992337164750957,
|
| 237 |
+
"eval_loss": 0.6248807907104492,
|
| 238 |
+
"eval_runtime": 173.9145,
|
| 239 |
+
"eval_samples_per_second": 50.525,
|
| 240 |
+
"eval_steps_per_second": 0.397,
|
| 241 |
+
"step": 326
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0114942528735633,
|
| 245 |
+
"grad_norm": 0.6441733804420072,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.6049,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0421455938697317,
|
| 252 |
+
"grad_norm": 0.507096490465927,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.5799,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.0727969348659003,
|
| 259 |
+
"grad_norm": 0.46519093469137246,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.5673,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.103448275862069,
|
| 266 |
+
"grad_norm": 0.5442582638655543,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.5712,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.1340996168582376,
|
| 273 |
+
"grad_norm": 0.5538652390132913,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.5716,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.1647509578544062,
|
| 280 |
+
"grad_norm": 0.48392472216552723,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.571,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.1954022988505748,
|
| 287 |
+
"grad_norm": 0.45417280073723987,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.5747,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.2260536398467432,
|
| 294 |
+
"grad_norm": 0.5583573730240281,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.5671,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2567049808429118,
|
| 301 |
+
"grad_norm": 0.5207404064605624,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.573,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2873563218390804,
|
| 308 |
+
"grad_norm": 0.7437830024244683,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.5782,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.318007662835249,
|
| 315 |
+
"grad_norm": 0.47334072928355125,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.5719,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.3486590038314177,
|
| 322 |
+
"grad_norm": 0.4856499631859895,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.5734,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3793103448275863,
|
| 329 |
+
"grad_norm": 0.527600892251984,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.5721,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.4099616858237547,
|
| 336 |
+
"grad_norm": 0.7847888047362421,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.578,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4406130268199233,
|
| 343 |
+
"grad_norm": 0.5862516700997007,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.5819,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.471264367816092,
|
| 350 |
+
"grad_norm": 0.5210251428696359,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.5742,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.5019157088122606,
|
| 357 |
+
"grad_norm": 0.5051694283145385,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.5757,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.5325670498084292,
|
| 364 |
+
"grad_norm": 0.4944291165015092,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5676,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.5632183908045976,
|
| 371 |
+
"grad_norm": 0.5480611839354791,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.5711,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.5938697318007664,
|
| 378 |
+
"grad_norm": 0.6057348261647956,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.5761,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.6245210727969348,
|
| 385 |
+
"grad_norm": 0.4842987104881793,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.571,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6551724137931034,
|
| 392 |
+
"grad_norm": 0.47443514901158346,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.5738,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.685823754789272,
|
| 399 |
+
"grad_norm": 0.47018891679148556,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.571,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.7164750957854407,
|
| 406 |
+
"grad_norm": 0.49622691394409835,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.5741,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.7471264367816093,
|
| 413 |
+
"grad_norm": 0.5557199806859595,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.5825,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.7777777777777777,
|
| 420 |
+
"grad_norm": 0.5102099459496233,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.575,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.8084291187739465,
|
| 427 |
+
"grad_norm": 0.5072094199992658,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.5719,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.839080459770115,
|
| 434 |
+
"grad_norm": 0.4947973206788556,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.5756,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.8697318007662835,
|
| 441 |
+
"grad_norm": 0.5908448445205707,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.5731,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.9003831417624522,
|
| 448 |
+
"grad_norm": 0.5096415926362652,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.5714,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.9310344827586206,
|
| 455 |
+
"grad_norm": 0.4450734203993437,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.5746,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.9616858237547894,
|
| 462 |
+
"grad_norm": 0.4789070006031585,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.5734,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.9923371647509578,
|
| 469 |
+
"grad_norm": 0.45516367538378033,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.5656,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.9984674329501915,
|
| 476 |
+
"eval_loss": 0.6165235638618469,
|
| 477 |
+
"eval_runtime": 174.5393,
|
| 478 |
+
"eval_samples_per_second": 50.344,
|
| 479 |
+
"eval_steps_per_second": 0.395,
|
| 480 |
+
"step": 652
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.0229885057471266,
|
| 484 |
+
"grad_norm": 0.7229863984265442,
|
| 485 |
+
"learning_rate": 5e-06,
|
| 486 |
+
"loss": 0.5381,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.053639846743295,
|
| 491 |
+
"grad_norm": 0.6598298631907643,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.5185,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.0842911877394634,
|
| 498 |
+
"grad_norm": 0.68582902786082,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.5182,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.1149425287356323,
|
| 505 |
+
"grad_norm": 0.5582955965512938,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.5165,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.1455938697318007,
|
| 512 |
+
"grad_norm": 0.5574612110577156,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.5215,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.1762452107279695,
|
| 519 |
+
"grad_norm": 0.5869240427384007,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.5142,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.206896551724138,
|
| 526 |
+
"grad_norm": 0.5917922238270269,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.5169,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.2375478927203067,
|
| 533 |
+
"grad_norm": 0.5584099299795768,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.5226,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.268199233716475,
|
| 540 |
+
"grad_norm": 0.5168618242941307,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.526,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.2988505747126435,
|
| 547 |
+
"grad_norm": 0.548452551643676,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.5274,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.3295019157088124,
|
| 554 |
+
"grad_norm": 0.5102986091253042,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.5201,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.3601532567049808,
|
| 561 |
+
"grad_norm": 0.5270431299308651,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.5261,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.3908045977011496,
|
| 568 |
+
"grad_norm": 0.49928113754253045,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.5188,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.421455938697318,
|
| 575 |
+
"grad_norm": 0.5526978578532159,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.5169,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.4521072796934864,
|
| 582 |
+
"grad_norm": 0.5512472751145416,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.528,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.4827586206896552,
|
| 589 |
+
"grad_norm": 0.5213408423447775,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.5184,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.5134099616858236,
|
| 596 |
+
"grad_norm": 0.5057448072220034,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.5172,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.5440613026819925,
|
| 603 |
+
"grad_norm": 0.5108411960779173,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.5206,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.574712643678161,
|
| 610 |
+
"grad_norm": 0.6573602606621571,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5244,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.6053639846743293,
|
| 617 |
+
"grad_norm": 0.5606803819365237,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5287,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.636015325670498,
|
| 624 |
+
"grad_norm": 0.5198211565475227,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5246,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.6666666666666665,
|
| 631 |
+
"grad_norm": 0.6142828850111772,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.5253,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.6973180076628354,
|
| 638 |
+
"grad_norm": 0.4911449572882352,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5266,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.7279693486590038,
|
| 645 |
+
"grad_norm": 0.5541387277544253,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.5207,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.7586206896551726,
|
| 652 |
+
"grad_norm": 0.529597237583542,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5271,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.789272030651341,
|
| 659 |
+
"grad_norm": 0.527413846058275,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.5292,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.8199233716475094,
|
| 666 |
+
"grad_norm": 0.5127935237005165,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.5236,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.8505747126436782,
|
| 673 |
+
"grad_norm": 0.563060155094441,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.5256,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.8812260536398466,
|
| 680 |
+
"grad_norm": 0.5678860479436445,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.5293,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.9118773946360155,
|
| 687 |
+
"grad_norm": 0.5163021730870726,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.5299,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.942528735632184,
|
| 694 |
+
"grad_norm": 0.5461456019011041,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.521,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.9731800766283527,
|
| 701 |
+
"grad_norm": 0.530000023353534,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.5212,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.9977011494252874,
|
| 708 |
+
"eval_loss": 0.6206015944480896,
|
| 709 |
+
"eval_runtime": 175.2408,
|
| 710 |
+
"eval_samples_per_second": 50.142,
|
| 711 |
+
"eval_steps_per_second": 0.394,
|
| 712 |
+
"step": 978
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.9977011494252874,
|
| 716 |
+
"step": 978,
|
| 717 |
+
"total_flos": 1637767666728960.0,
|
| 718 |
+
"train_loss": 0.5840159120735215,
|
| 719 |
+
"train_runtime": 29297.5545,
|
| 720 |
+
"train_samples_per_second": 17.094,
|
| 721 |
+
"train_steps_per_second": 0.033
|
| 722 |
+
}
|
| 723 |
+
],
|
| 724 |
+
"logging_steps": 10,
|
| 725 |
+
"max_steps": 978,
|
| 726 |
+
"num_input_tokens_seen": 0,
|
| 727 |
+
"num_train_epochs": 3,
|
| 728 |
+
"save_steps": 500,
|
| 729 |
+
"stateful_callbacks": {
|
| 730 |
+
"TrainerControl": {
|
| 731 |
+
"args": {
|
| 732 |
+
"should_epoch_stop": false,
|
| 733 |
+
"should_evaluate": false,
|
| 734 |
+
"should_log": false,
|
| 735 |
+
"should_save": true,
|
| 736 |
+
"should_training_stop": true
|
| 737 |
+
},
|
| 738 |
+
"attributes": {}
|
| 739 |
+
}
|
| 740 |
+
},
|
| 741 |
+
"total_flos": 1637767666728960.0,
|
| 742 |
+
"train_batch_size": 8,
|
| 743 |
+
"trial_name": null,
|
| 744 |
+
"trial_params": null
|
| 745 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|