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 +752 -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_camel_ai_chemistry
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# OH_original_wo_camel_ai_chemistry
|
| 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: 0.6135
|
| 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_camel_ai_chemistry
|
|
|
|
| 16 |
|
| 17 |
# OH_original_wo_camel_ai_chemistry
|
| 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_camel_ai_chemistry dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6135
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6134681701660156,
|
| 4 |
+
"eval_runtime": 176.2648,
|
| 5 |
+
"eval_samples_per_second": 49.993,
|
| 6 |
+
"eval_steps_per_second": 0.391,
|
| 7 |
+
"total_flos": 1642792778465280.0,
|
| 8 |
+
"train_loss": 0.5776342995062272,
|
| 9 |
+
"train_runtime": 29440.9564,
|
| 10 |
+
"train_samples_per_second": 17.06,
|
| 11 |
+
"train_steps_per_second": 0.033
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6134681701660156,
|
| 4 |
+
"eval_runtime": 176.2648,
|
| 5 |
+
"eval_samples_per_second": 49.993,
|
| 6 |
+
"eval_steps_per_second": 0.391
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1642792778465280.0,
|
| 4 |
+
"train_loss": 0.5776342995062272,
|
| 5 |
+
"train_runtime": 29440.9564,
|
| 6 |
+
"train_samples_per_second": 17.06,
|
| 7 |
+
"train_steps_per_second": 0.033
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,752 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 981,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03058103975535168,
|
| 13 |
+
"grad_norm": 4.613314070863576,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.8051,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06116207951070336,
|
| 20 |
+
"grad_norm": 1.8900295063815196,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.7288,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09174311926605505,
|
| 27 |
+
"grad_norm": 2.828490629262087,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.709,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12232415902140673,
|
| 34 |
+
"grad_norm": 1.3871149266999225,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.6966,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1529051987767584,
|
| 41 |
+
"grad_norm": 1.5967435207002258,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.6812,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1834862385321101,
|
| 48 |
+
"grad_norm": 1.882517891139545,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.6728,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.21406727828746178,
|
| 55 |
+
"grad_norm": 0.6460792834326635,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.661,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.24464831804281345,
|
| 62 |
+
"grad_norm": 0.8345961449379203,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.6527,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.27522935779816515,
|
| 69 |
+
"grad_norm": 0.6632736237849782,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.65,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3058103975535168,
|
| 76 |
+
"grad_norm": 0.6414397366786443,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.6416,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3363914373088685,
|
| 83 |
+
"grad_norm": 0.6410573252326648,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.6423,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3669724770642202,
|
| 90 |
+
"grad_norm": 0.6301173144669027,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.6431,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.39755351681957185,
|
| 97 |
+
"grad_norm": 0.6700047532457443,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.6328,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.42813455657492355,
|
| 104 |
+
"grad_norm": 0.7253886574556052,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.6379,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.45871559633027525,
|
| 111 |
+
"grad_norm": 0.6468641147049369,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.6226,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4892966360856269,
|
| 118 |
+
"grad_norm": 0.5346182726002575,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6297,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5198776758409785,
|
| 125 |
+
"grad_norm": 0.5313857610798393,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6315,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5504587155963303,
|
| 132 |
+
"grad_norm": 1.055453437070951,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6319,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.581039755351682,
|
| 139 |
+
"grad_norm": 1.0346764494649112,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6336,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6116207951070336,
|
| 146 |
+
"grad_norm": 0.5618281272496094,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6219,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6422018348623854,
|
| 153 |
+
"grad_norm": 1.3519206618987067,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6231,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.672782874617737,
|
| 160 |
+
"grad_norm": 0.7749478594608031,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6242,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.7033639143730887,
|
| 167 |
+
"grad_norm": 0.5893825196950665,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6241,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7339449541284404,
|
| 174 |
+
"grad_norm": 0.6773691040863971,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6222,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.764525993883792,
|
| 181 |
+
"grad_norm": 0.4827169638012845,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.619,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.7951070336391437,
|
| 188 |
+
"grad_norm": 0.6490833986094754,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6214,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8256880733944955,
|
| 195 |
+
"grad_norm": 0.4630327930179835,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6234,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.8562691131498471,
|
| 202 |
+
"grad_norm": 0.5519953643760132,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6238,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.8868501529051988,
|
| 209 |
+
"grad_norm": 0.6014046385653471,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6205,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9174311926605505,
|
| 216 |
+
"grad_norm": 0.9905714959978613,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.614,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9480122324159022,
|
| 223 |
+
"grad_norm": 0.5722101718286907,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6174,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.9785932721712538,
|
| 230 |
+
"grad_norm": 0.49394030115956855,
|
| 231 |
+
"learning_rate": 5e-06,
|
| 232 |
+
"loss": 0.6318,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.0,
|
| 237 |
+
"eval_loss": 0.6179984211921692,
|
| 238 |
+
"eval_runtime": 175.4761,
|
| 239 |
+
"eval_samples_per_second": 50.218,
|
| 240 |
+
"eval_steps_per_second": 0.393,
|
| 241 |
+
"step": 327
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0091743119266054,
|
| 245 |
+
"grad_norm": 0.7689781158724909,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.6099,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.039755351681957,
|
| 252 |
+
"grad_norm": 0.6771992725638727,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.5636,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.070336391437309,
|
| 259 |
+
"grad_norm": 0.8428533582721723,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.5702,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.1009174311926606,
|
| 266 |
+
"grad_norm": 0.6417949273070751,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.5724,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.1314984709480123,
|
| 273 |
+
"grad_norm": 0.4739060770421859,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.5667,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.162079510703364,
|
| 280 |
+
"grad_norm": 0.8290714956133294,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.5723,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.1926605504587156,
|
| 287 |
+
"grad_norm": 0.4621451043452794,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.5712,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.2232415902140672,
|
| 294 |
+
"grad_norm": 0.5143870327303872,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.5665,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.2538226299694188,
|
| 301 |
+
"grad_norm": 0.5164679975473679,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.5738,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.2844036697247707,
|
| 308 |
+
"grad_norm": 0.8444328502616898,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.568,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.3149847094801224,
|
| 315 |
+
"grad_norm": 0.5068551444160476,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.5685,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.345565749235474,
|
| 322 |
+
"grad_norm": 0.5272187758950088,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.5719,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.3761467889908257,
|
| 329 |
+
"grad_norm": 0.6560982973750454,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.5631,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.4067278287461773,
|
| 336 |
+
"grad_norm": 0.4484289597201794,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.5662,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4373088685015292,
|
| 343 |
+
"grad_norm": 0.5845602559047488,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.5555,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.4678899082568808,
|
| 350 |
+
"grad_norm": 0.5019202622500104,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.572,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.4984709480122325,
|
| 357 |
+
"grad_norm": 0.5453352197296611,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.5678,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.529051987767584,
|
| 364 |
+
"grad_norm": 0.5096577153134583,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.5747,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.5596330275229358,
|
| 371 |
+
"grad_norm": 0.6175776252130769,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.5664,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.5902140672782874,
|
| 378 |
+
"grad_norm": 0.5104602945006693,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.5634,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.620795107033639,
|
| 385 |
+
"grad_norm": 0.596086026271991,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.5751,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.6513761467889907,
|
| 392 |
+
"grad_norm": 0.5308994737717756,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.5733,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.6819571865443423,
|
| 399 |
+
"grad_norm": 0.4845901344757882,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.5717,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.7125382262996942,
|
| 406 |
+
"grad_norm": 0.5671326796569592,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.5724,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.7431192660550459,
|
| 413 |
+
"grad_norm": 0.4598174188757565,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.5683,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.7737003058103975,
|
| 420 |
+
"grad_norm": 0.5112157139948377,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.5681,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.8042813455657494,
|
| 427 |
+
"grad_norm": 0.5586531166082738,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.5684,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.834862385321101,
|
| 434 |
+
"grad_norm": 0.4688565551712795,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.5644,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.8654434250764527,
|
| 441 |
+
"grad_norm": 0.5068561602224454,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.5634,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.8960244648318043,
|
| 448 |
+
"grad_norm": 0.5177020231748777,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.5693,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.926605504587156,
|
| 455 |
+
"grad_norm": 0.5480741145181502,
|
| 456 |
+
"learning_rate": 5e-06,
|
| 457 |
+
"loss": 0.5613,
|
| 458 |
+
"step": 630
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.9571865443425076,
|
| 462 |
+
"grad_norm": 0.4783567812818659,
|
| 463 |
+
"learning_rate": 5e-06,
|
| 464 |
+
"loss": 0.5585,
|
| 465 |
+
"step": 640
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.9877675840978593,
|
| 469 |
+
"grad_norm": 0.5551088225058829,
|
| 470 |
+
"learning_rate": 5e-06,
|
| 471 |
+
"loss": 0.5674,
|
| 472 |
+
"step": 650
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.0,
|
| 476 |
+
"eval_loss": 0.6093349456787109,
|
| 477 |
+
"eval_runtime": 174.9969,
|
| 478 |
+
"eval_samples_per_second": 50.355,
|
| 479 |
+
"eval_steps_per_second": 0.394,
|
| 480 |
+
"step": 654
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.018348623853211,
|
| 484 |
+
"grad_norm": 0.6215337411502556,
|
| 485 |
+
"learning_rate": 5e-06,
|
| 486 |
+
"loss": 0.5384,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.0489296636085625,
|
| 491 |
+
"grad_norm": 0.6523651145276358,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.5183,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.079510703363914,
|
| 498 |
+
"grad_norm": 0.4938873169688457,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.5154,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.1100917431192663,
|
| 505 |
+
"grad_norm": 0.5700577847392374,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.513,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.140672782874618,
|
| 512 |
+
"grad_norm": 0.6865444356940279,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.5107,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.1712538226299696,
|
| 519 |
+
"grad_norm": 0.49230256627015,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.5109,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.2018348623853212,
|
| 526 |
+
"grad_norm": 0.8680096117870334,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.5201,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.232415902140673,
|
| 533 |
+
"grad_norm": 0.5282977989250981,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.5176,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.2629969418960245,
|
| 540 |
+
"grad_norm": 0.5641604277626704,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.5175,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.293577981651376,
|
| 547 |
+
"grad_norm": 0.5627994676639944,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.5233,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.324159021406728,
|
| 554 |
+
"grad_norm": 0.5351783170372003,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.5193,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.3547400611620795,
|
| 561 |
+
"grad_norm": 0.5159357728539045,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.5145,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.385321100917431,
|
| 568 |
+
"grad_norm": 0.6104068286820499,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.5164,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.4159021406727827,
|
| 575 |
+
"grad_norm": 0.677498087908613,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.5262,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.4464831804281344,
|
| 582 |
+
"grad_norm": 0.5283675690505885,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.5149,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.477064220183486,
|
| 589 |
+
"grad_norm": 0.5044083108738047,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.5176,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.5076452599388377,
|
| 596 |
+
"grad_norm": 0.49494102207897933,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.5204,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.5382262996941893,
|
| 603 |
+
"grad_norm": 0.4861352677652072,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.5337,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.5688073394495414,
|
| 610 |
+
"grad_norm": 0.48851988662021156,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5238,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.599388379204893,
|
| 617 |
+
"grad_norm": 0.5226833608668234,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5205,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.6299694189602447,
|
| 624 |
+
"grad_norm": 0.5465654006210326,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5221,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.6605504587155964,
|
| 631 |
+
"grad_norm": 0.5039029213538379,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.5196,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.691131498470948,
|
| 638 |
+
"grad_norm": 0.5371018828919037,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5237,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.7217125382262997,
|
| 645 |
+
"grad_norm": 0.5383889127160468,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.5169,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.7522935779816513,
|
| 652 |
+
"grad_norm": 0.5406840391563221,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5116,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.782874617737003,
|
| 659 |
+
"grad_norm": 0.5182378062317926,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.5147,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.8134556574923546,
|
| 666 |
+
"grad_norm": 0.483759876679847,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.514,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.8440366972477067,
|
| 673 |
+
"grad_norm": 0.5715170886676529,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.5189,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.8746177370030583,
|
| 680 |
+
"grad_norm": 0.4882822153954844,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.5131,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.90519877675841,
|
| 687 |
+
"grad_norm": 0.518462889966442,
|
| 688 |
+
"learning_rate": 5e-06,
|
| 689 |
+
"loss": 0.5228,
|
| 690 |
+
"step": 950
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.9357798165137616,
|
| 694 |
+
"grad_norm": 0.500511829330958,
|
| 695 |
+
"learning_rate": 5e-06,
|
| 696 |
+
"loss": 0.5177,
|
| 697 |
+
"step": 960
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.9663608562691133,
|
| 701 |
+
"grad_norm": 0.4799796524761594,
|
| 702 |
+
"learning_rate": 5e-06,
|
| 703 |
+
"loss": 0.5283,
|
| 704 |
+
"step": 970
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.996941896024465,
|
| 708 |
+
"grad_norm": 0.6756287967133653,
|
| 709 |
+
"learning_rate": 5e-06,
|
| 710 |
+
"loss": 0.5228,
|
| 711 |
+
"step": 980
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 3.0,
|
| 715 |
+
"eval_loss": 0.6134681701660156,
|
| 716 |
+
"eval_runtime": 174.9719,
|
| 717 |
+
"eval_samples_per_second": 50.362,
|
| 718 |
+
"eval_steps_per_second": 0.394,
|
| 719 |
+
"step": 981
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 3.0,
|
| 723 |
+
"step": 981,
|
| 724 |
+
"total_flos": 1642792778465280.0,
|
| 725 |
+
"train_loss": 0.5776342995062272,
|
| 726 |
+
"train_runtime": 29440.9564,
|
| 727 |
+
"train_samples_per_second": 17.06,
|
| 728 |
+
"train_steps_per_second": 0.033
|
| 729 |
+
}
|
| 730 |
+
],
|
| 731 |
+
"logging_steps": 10,
|
| 732 |
+
"max_steps": 981,
|
| 733 |
+
"num_input_tokens_seen": 0,
|
| 734 |
+
"num_train_epochs": 3,
|
| 735 |
+
"save_steps": 500,
|
| 736 |
+
"stateful_callbacks": {
|
| 737 |
+
"TrainerControl": {
|
| 738 |
+
"args": {
|
| 739 |
+
"should_epoch_stop": false,
|
| 740 |
+
"should_evaluate": false,
|
| 741 |
+
"should_log": false,
|
| 742 |
+
"should_save": true,
|
| 743 |
+
"should_training_stop": true
|
| 744 |
+
},
|
| 745 |
+
"attributes": {}
|
| 746 |
+
}
|
| 747 |
+
},
|
| 748 |
+
"total_flos": 1642792778465280.0,
|
| 749 |
+
"train_batch_size": 8,
|
| 750 |
+
"trial_name": null,
|
| 751 |
+
"trial_params": null
|
| 752 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|