End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +630 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: tbench_traces_local_sharegptv1
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# tbench_traces_local_sharegptv1
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: tbench_traces_local_sharegptv1
|
|
|
|
| 16 |
|
| 17 |
# tbench_traces_local_sharegptv1
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/tbench_traces_local_sharegptv1 dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.88,
|
| 3 |
+
"total_flos": 2.05814528583467e+17,
|
| 4 |
+
"train_loss": 0.0877098992489101,
|
| 5 |
+
"train_runtime": 2823.2706,
|
| 6 |
+
"train_samples_per_second": 2.948,
|
| 7 |
+
"train_steps_per_second": 0.03
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.88,
|
| 3 |
+
"total_flos": 2.05814528583467e+17,
|
| 4 |
+
"train_loss": 0.0877098992489101,
|
| 5 |
+
"train_runtime": 2823.2706,
|
| 6 |
+
"train_samples_per_second": 2.948,
|
| 7 |
+
"train_steps_per_second": 0.03
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,630 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.88,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 84,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08,
|
| 13 |
+
"grad_norm": 10.036529266225477,
|
| 14 |
+
"learning_rate": 2.222222222222222e-06,
|
| 15 |
+
"loss": 0.7145,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16,
|
| 20 |
+
"grad_norm": 10.389414497171416,
|
| 21 |
+
"learning_rate": 4.444444444444444e-06,
|
| 22 |
+
"loss": 0.7369,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.24,
|
| 27 |
+
"grad_norm": 9.17790620062099,
|
| 28 |
+
"learning_rate": 6.666666666666667e-06,
|
| 29 |
+
"loss": 0.6944,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.32,
|
| 34 |
+
"grad_norm": 5.386931438168319,
|
| 35 |
+
"learning_rate": 8.888888888888888e-06,
|
| 36 |
+
"loss": 0.5333,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4,
|
| 41 |
+
"grad_norm": 2.9839616304428405,
|
| 42 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 43 |
+
"loss": 0.487,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.48,
|
| 48 |
+
"grad_norm": 3.126486872980733,
|
| 49 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 50 |
+
"loss": 0.4593,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.56,
|
| 55 |
+
"grad_norm": 2.612661793479886,
|
| 56 |
+
"learning_rate": 1.555555555555556e-05,
|
| 57 |
+
"loss": 0.4457,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.64,
|
| 62 |
+
"grad_norm": 2.3160585286198083,
|
| 63 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 64 |
+
"loss": 0.3924,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.72,
|
| 69 |
+
"grad_norm": 2.126071424027463,
|
| 70 |
+
"learning_rate": 2e-05,
|
| 71 |
+
"loss": 0.3736,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.8,
|
| 76 |
+
"grad_norm": 1.8185760212998934,
|
| 77 |
+
"learning_rate": 1.9991228300988586e-05,
|
| 78 |
+
"loss": 0.3098,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.88,
|
| 83 |
+
"grad_norm": 2.188934005237936,
|
| 84 |
+
"learning_rate": 1.9964928592495046e-05,
|
| 85 |
+
"loss": 0.2955,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.96,
|
| 90 |
+
"grad_norm": 1.2653132682151336,
|
| 91 |
+
"learning_rate": 1.9921147013144782e-05,
|
| 92 |
+
"loss": 0.2644,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.0666666666666667,
|
| 97 |
+
"grad_norm": 1.0529429385946099,
|
| 98 |
+
"learning_rate": 1.985996037070505e-05,
|
| 99 |
+
"loss": 0.1988,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.1466666666666667,
|
| 104 |
+
"grad_norm": 1.2808595466498691,
|
| 105 |
+
"learning_rate": 1.9781476007338058e-05,
|
| 106 |
+
"loss": 0.1705,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.2266666666666666,
|
| 111 |
+
"grad_norm": 0.8223507932291947,
|
| 112 |
+
"learning_rate": 1.9685831611286312e-05,
|
| 113 |
+
"loss": 0.1616,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.3066666666666666,
|
| 118 |
+
"grad_norm": 0.8487765234075525,
|
| 119 |
+
"learning_rate": 1.9573194975320672e-05,
|
| 120 |
+
"loss": 0.131,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.3866666666666667,
|
| 125 |
+
"grad_norm": 0.7732890236721263,
|
| 126 |
+
"learning_rate": 1.944376370237481e-05,
|
| 127 |
+
"loss": 0.1243,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.4666666666666668,
|
| 132 |
+
"grad_norm": 0.6492174454992042,
|
| 133 |
+
"learning_rate": 1.9297764858882516e-05,
|
| 134 |
+
"loss": 0.0922,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.5466666666666666,
|
| 139 |
+
"grad_norm": 0.6778244945425531,
|
| 140 |
+
"learning_rate": 1.913545457642601e-05,
|
| 141 |
+
"loss": 0.0817,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.6266666666666667,
|
| 146 |
+
"grad_norm": 0.5191186176081979,
|
| 147 |
+
"learning_rate": 1.895711760239413e-05,
|
| 148 |
+
"loss": 0.067,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.7066666666666666,
|
| 153 |
+
"grad_norm": 0.7183726841486737,
|
| 154 |
+
"learning_rate": 1.8763066800438638e-05,
|
| 155 |
+
"loss": 0.0648,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.7866666666666666,
|
| 160 |
+
"grad_norm": 0.4763579631057156,
|
| 161 |
+
"learning_rate": 1.855364260160507e-05,
|
| 162 |
+
"loss": 0.0483,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.8666666666666667,
|
| 167 |
+
"grad_norm": 0.6136982903243969,
|
| 168 |
+
"learning_rate": 1.8329212407100996e-05,
|
| 169 |
+
"loss": 0.0523,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.9466666666666668,
|
| 174 |
+
"grad_norm": 0.39593868001405813,
|
| 175 |
+
"learning_rate": 1.8090169943749477e-05,
|
| 176 |
+
"loss": 0.0397,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.0533333333333332,
|
| 181 |
+
"grad_norm": 0.48110884387677105,
|
| 182 |
+
"learning_rate": 1.78369345732584e-05,
|
| 183 |
+
"loss": 0.0316,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.1333333333333333,
|
| 188 |
+
"grad_norm": 0.36780275641080656,
|
| 189 |
+
"learning_rate": 1.7569950556517566e-05,
|
| 190 |
+
"loss": 0.0283,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.2133333333333334,
|
| 195 |
+
"grad_norm": 0.37090151490036466,
|
| 196 |
+
"learning_rate": 1.7289686274214116e-05,
|
| 197 |
+
"loss": 0.0252,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.2933333333333334,
|
| 202 |
+
"grad_norm": 0.41005471899554213,
|
| 203 |
+
"learning_rate": 1.6996633405133656e-05,
|
| 204 |
+
"loss": 0.0225,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.3733333333333335,
|
| 209 |
+
"grad_norm": 0.28113415709619594,
|
| 210 |
+
"learning_rate": 1.6691306063588583e-05,
|
| 211 |
+
"loss": 0.0168,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.453333333333333,
|
| 216 |
+
"grad_norm": 0.28690490127791546,
|
| 217 |
+
"learning_rate": 1.63742398974869e-05,
|
| 218 |
+
"loss": 0.0196,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.533333333333333,
|
| 223 |
+
"grad_norm": 0.359842251011263,
|
| 224 |
+
"learning_rate": 1.6045991148623752e-05,
|
| 225 |
+
"loss": 0.016,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.6133333333333333,
|
| 230 |
+
"grad_norm": 0.2867442565629624,
|
| 231 |
+
"learning_rate": 1.570713567684432e-05,
|
| 232 |
+
"loss": 0.0157,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.6933333333333334,
|
| 237 |
+
"grad_norm": 0.32450600553408454,
|
| 238 |
+
"learning_rate": 1.5358267949789968e-05,
|
| 239 |
+
"loss": 0.013,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 2.7733333333333334,
|
| 244 |
+
"grad_norm": 0.23913095037188103,
|
| 245 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 246 |
+
"loss": 0.0116,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.8533333333333335,
|
| 251 |
+
"grad_norm": 0.2521275004069674,
|
| 252 |
+
"learning_rate": 1.463296035119862e-05,
|
| 253 |
+
"loss": 0.0111,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.9333333333333336,
|
| 258 |
+
"grad_norm": 0.30429449772821154,
|
| 259 |
+
"learning_rate": 1.4257792915650728e-05,
|
| 260 |
+
"loss": 0.0138,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.04,
|
| 265 |
+
"grad_norm": 0.23765457406792445,
|
| 266 |
+
"learning_rate": 1.3875155864521031e-05,
|
| 267 |
+
"loss": 0.0129,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.12,
|
| 272 |
+
"grad_norm": 0.24777987344005734,
|
| 273 |
+
"learning_rate": 1.3485720473218153e-05,
|
| 274 |
+
"loss": 0.0091,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.2,
|
| 279 |
+
"grad_norm": 0.2273206945273564,
|
| 280 |
+
"learning_rate": 1.3090169943749475e-05,
|
| 281 |
+
"loss": 0.009,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.2800000000000002,
|
| 286 |
+
"grad_norm": 0.16906368881507844,
|
| 287 |
+
"learning_rate": 1.2689198206152657e-05,
|
| 288 |
+
"loss": 0.0065,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.36,
|
| 293 |
+
"grad_norm": 0.1308790284029346,
|
| 294 |
+
"learning_rate": 1.2283508701106559e-05,
|
| 295 |
+
"loss": 0.0058,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.44,
|
| 300 |
+
"grad_norm": 0.26354395187456514,
|
| 301 |
+
"learning_rate": 1.187381314585725e-05,
|
| 302 |
+
"loss": 0.0082,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.52,
|
| 307 |
+
"grad_norm": 0.16212884441387132,
|
| 308 |
+
"learning_rate": 1.1460830285624119e-05,
|
| 309 |
+
"loss": 0.0068,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 3.6,
|
| 314 |
+
"grad_norm": 0.16191999234700347,
|
| 315 |
+
"learning_rate": 1.1045284632676535e-05,
|
| 316 |
+
"loss": 0.0062,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.68,
|
| 321 |
+
"grad_norm": 0.19030098427914469,
|
| 322 |
+
"learning_rate": 1.0627905195293135e-05,
|
| 323 |
+
"loss": 0.0076,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 3.76,
|
| 328 |
+
"grad_norm": 0.16439880706103482,
|
| 329 |
+
"learning_rate": 1.0209424198833571e-05,
|
| 330 |
+
"loss": 0.0054,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 3.84,
|
| 335 |
+
"grad_norm": 0.20040871225905432,
|
| 336 |
+
"learning_rate": 9.790575801166432e-06,
|
| 337 |
+
"loss": 0.0081,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.92,
|
| 342 |
+
"grad_norm": 0.1479638482803632,
|
| 343 |
+
"learning_rate": 9.372094804706867e-06,
|
| 344 |
+
"loss": 0.0047,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.026666666666666,
|
| 349 |
+
"grad_norm": 0.13994769734697188,
|
| 350 |
+
"learning_rate": 8.954715367323468e-06,
|
| 351 |
+
"loss": 0.0047,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.1066666666666665,
|
| 356 |
+
"grad_norm": 0.12131083240532735,
|
| 357 |
+
"learning_rate": 8.539169714375885e-06,
|
| 358 |
+
"loss": 0.0046,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.1866666666666665,
|
| 363 |
+
"grad_norm": 0.19601140528675995,
|
| 364 |
+
"learning_rate": 8.126186854142752e-06,
|
| 365 |
+
"loss": 0.005,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 4.266666666666667,
|
| 370 |
+
"grad_norm": 0.14775341696545702,
|
| 371 |
+
"learning_rate": 7.716491298893443e-06,
|
| 372 |
+
"loss": 0.0037,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 4.346666666666667,
|
| 377 |
+
"grad_norm": 0.0684370948197902,
|
| 378 |
+
"learning_rate": 7.310801793847344e-06,
|
| 379 |
+
"loss": 0.0034,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 4.426666666666667,
|
| 384 |
+
"grad_norm": 0.10561347466529843,
|
| 385 |
+
"learning_rate": 6.909830056250527e-06,
|
| 386 |
+
"loss": 0.004,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.506666666666667,
|
| 391 |
+
"grad_norm": 0.08319160323721571,
|
| 392 |
+
"learning_rate": 6.5142795267818505e-06,
|
| 393 |
+
"loss": 0.0029,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 4.586666666666667,
|
| 398 |
+
"grad_norm": 0.10892669231861006,
|
| 399 |
+
"learning_rate": 6.124844135478971e-06,
|
| 400 |
+
"loss": 0.0037,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.666666666666667,
|
| 405 |
+
"grad_norm": 0.1844831079996731,
|
| 406 |
+
"learning_rate": 5.742207084349274e-06,
|
| 407 |
+
"loss": 0.0046,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 4.746666666666667,
|
| 412 |
+
"grad_norm": 0.06023531870392776,
|
| 413 |
+
"learning_rate": 5.367039648801386e-06,
|
| 414 |
+
"loss": 0.0032,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.826666666666666,
|
| 419 |
+
"grad_norm": 0.1081948873335093,
|
| 420 |
+
"learning_rate": 5.000000000000003e-06,
|
| 421 |
+
"loss": 0.0032,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.906666666666666,
|
| 426 |
+
"grad_norm": 0.08583026800527162,
|
| 427 |
+
"learning_rate": 4.641732050210032e-06,
|
| 428 |
+
"loss": 0.0031,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.013333333333334,
|
| 433 |
+
"grad_norm": 0.07554619569774117,
|
| 434 |
+
"learning_rate": 4.292864323155684e-06,
|
| 435 |
+
"loss": 0.0039,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 5.093333333333334,
|
| 440 |
+
"grad_norm": 0.06673160850858063,
|
| 441 |
+
"learning_rate": 3.954008851376252e-06,
|
| 442 |
+
"loss": 0.0034,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 5.173333333333334,
|
| 447 |
+
"grad_norm": 0.053971457375327915,
|
| 448 |
+
"learning_rate": 3.625760102513103e-06,
|
| 449 |
+
"loss": 0.0033,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 5.253333333333333,
|
| 454 |
+
"grad_norm": 0.07882357081909791,
|
| 455 |
+
"learning_rate": 3.308693936411421e-06,
|
| 456 |
+
"loss": 0.0031,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 5.333333333333333,
|
| 461 |
+
"grad_norm": 0.04070085115424002,
|
| 462 |
+
"learning_rate": 3.003366594866345e-06,
|
| 463 |
+
"loss": 0.0031,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 5.413333333333333,
|
| 468 |
+
"grad_norm": 0.03563287517057762,
|
| 469 |
+
"learning_rate": 2.7103137257858867e-06,
|
| 470 |
+
"loss": 0.0025,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 5.493333333333333,
|
| 475 |
+
"grad_norm": 0.06861151990784896,
|
| 476 |
+
"learning_rate": 2.4300494434824373e-06,
|
| 477 |
+
"loss": 0.0029,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 5.573333333333333,
|
| 482 |
+
"grad_norm": 0.04525506301252717,
|
| 483 |
+
"learning_rate": 2.163065426741603e-06,
|
| 484 |
+
"loss": 0.0025,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 5.653333333333333,
|
| 489 |
+
"grad_norm": 0.08040379629184667,
|
| 490 |
+
"learning_rate": 1.9098300562505266e-06,
|
| 491 |
+
"loss": 0.003,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 5.733333333333333,
|
| 496 |
+
"grad_norm": 0.04319505349171157,
|
| 497 |
+
"learning_rate": 1.6707875928990059e-06,
|
| 498 |
+
"loss": 0.0027,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 5.8133333333333335,
|
| 503 |
+
"grad_norm": 0.028573716782012575,
|
| 504 |
+
"learning_rate": 1.446357398394934e-06,
|
| 505 |
+
"loss": 0.0027,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 5.8933333333333335,
|
| 510 |
+
"grad_norm": 0.060574015759331724,
|
| 511 |
+
"learning_rate": 1.2369331995613664e-06,
|
| 512 |
+
"loss": 0.0025,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 5.973333333333334,
|
| 517 |
+
"grad_norm": 0.03670461774764994,
|
| 518 |
+
"learning_rate": 1.042882397605871e-06,
|
| 519 |
+
"loss": 0.0025,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 6.08,
|
| 524 |
+
"grad_norm": 0.06022022050455768,
|
| 525 |
+
"learning_rate": 8.645454235739903e-07,
|
| 526 |
+
"loss": 0.0028,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 6.16,
|
| 531 |
+
"grad_norm": 0.037249309263902554,
|
| 532 |
+
"learning_rate": 7.022351411174866e-07,
|
| 533 |
+
"loss": 0.0028,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 6.24,
|
| 538 |
+
"grad_norm": 0.06532445454836046,
|
| 539 |
+
"learning_rate": 5.562362976251901e-07,
|
| 540 |
+
"loss": 0.0027,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 6.32,
|
| 545 |
+
"grad_norm": 0.053915117122606306,
|
| 546 |
+
"learning_rate": 4.268050246793276e-07,
|
| 547 |
+
"loss": 0.0024,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 6.4,
|
| 552 |
+
"grad_norm": 0.053551532022636204,
|
| 553 |
+
"learning_rate": 3.1416838871368925e-07,
|
| 554 |
+
"loss": 0.0029,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 6.48,
|
| 559 |
+
"grad_norm": 0.02789001987346699,
|
| 560 |
+
"learning_rate": 2.1852399266194312e-07,
|
| 561 |
+
"loss": 0.0026,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 6.5600000000000005,
|
| 566 |
+
"grad_norm": 0.02074533194355654,
|
| 567 |
+
"learning_rate": 1.400396292949513e-07,
|
| 568 |
+
"loss": 0.0026,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 6.64,
|
| 573 |
+
"grad_norm": 0.03282330611266334,
|
| 574 |
+
"learning_rate": 7.885298685522235e-08,
|
| 575 |
+
"loss": 0.0025,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 6.72,
|
| 580 |
+
"grad_norm": 0.02681692521500632,
|
| 581 |
+
"learning_rate": 3.50714075049563e-08,
|
| 582 |
+
"loss": 0.0025,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 6.8,
|
| 587 |
+
"grad_norm": 0.04409222037330554,
|
| 588 |
+
"learning_rate": 8.771699011416169e-09,
|
| 589 |
+
"loss": 0.0026,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 6.88,
|
| 594 |
+
"grad_norm": 0.030487364745168152,
|
| 595 |
+
"learning_rate": 0.0,
|
| 596 |
+
"loss": 0.0027,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 6.88,
|
| 601 |
+
"step": 84,
|
| 602 |
+
"total_flos": 2.05814528583467e+17,
|
| 603 |
+
"train_loss": 0.0877098992489101,
|
| 604 |
+
"train_runtime": 2823.2706,
|
| 605 |
+
"train_samples_per_second": 2.948,
|
| 606 |
+
"train_steps_per_second": 0.03
|
| 607 |
+
}
|
| 608 |
+
],
|
| 609 |
+
"logging_steps": 1,
|
| 610 |
+
"max_steps": 84,
|
| 611 |
+
"num_input_tokens_seen": 0,
|
| 612 |
+
"num_train_epochs": 7,
|
| 613 |
+
"save_steps": 500,
|
| 614 |
+
"stateful_callbacks": {
|
| 615 |
+
"TrainerControl": {
|
| 616 |
+
"args": {
|
| 617 |
+
"should_epoch_stop": false,
|
| 618 |
+
"should_evaluate": false,
|
| 619 |
+
"should_log": false,
|
| 620 |
+
"should_save": true,
|
| 621 |
+
"should_training_stop": true
|
| 622 |
+
},
|
| 623 |
+
"attributes": {}
|
| 624 |
+
}
|
| 625 |
+
},
|
| 626 |
+
"total_flos": 2.05814528583467e+17,
|
| 627 |
+
"train_batch_size": 1,
|
| 628 |
+
"trial_name": null,
|
| 629 |
+
"trial_params": null
|
| 630 |
+
}
|
training_loss.png
ADDED
|