End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +462 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-32B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: SWE-BENCH-500-set-4o-file-localization_qwen_code_32B_test_swe
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# SWE-BENCH-500-set-4o-file-localization_qwen_code_32B_test_swe
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-Coder-32B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: SWE-BENCH-500-set-4o-file-localization_qwen_code_32B_test_swe
|
|
|
|
| 16 |
|
| 17 |
# SWE-BENCH-500-set-4o-file-localization_qwen_code_32B_test_swe
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) on the SWE-BENCH-500-set-4o-file-localization dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.96,
|
| 3 |
+
"total_flos": 2.770915149689651e+16,
|
| 4 |
+
"train_loss": 0.37391861056288084,
|
| 5 |
+
"train_runtime": 21254.7027,
|
| 6 |
+
"train_samples_per_second": 0.071,
|
| 7 |
+
"train_steps_per_second": 0.003
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.96,
|
| 3 |
+
"total_flos": 2.770915149689651e+16,
|
| 4 |
+
"train_loss": 0.37391861056288084,
|
| 5 |
+
"train_runtime": 21254.7027,
|
| 6 |
+
"train_samples_per_second": 0.071,
|
| 7 |
+
"train_steps_per_second": 0.003
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,462 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.96,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 60,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.048,
|
| 13 |
+
"grad_norm": 0.5960447192192078,
|
| 14 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 15 |
+
"loss": 0.6433,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.096,
|
| 20 |
+
"grad_norm": 0.5785825252532959,
|
| 21 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 22 |
+
"loss": 0.637,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.144,
|
| 27 |
+
"grad_norm": 0.6395981311798096,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.6437,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.192,
|
| 34 |
+
"grad_norm": 0.32435280084609985,
|
| 35 |
+
"learning_rate": 6.666666666666667e-06,
|
| 36 |
+
"loss": 0.5838,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.24,
|
| 41 |
+
"grad_norm": 0.3350636661052704,
|
| 42 |
+
"learning_rate": 8.333333333333334e-06,
|
| 43 |
+
"loss": 0.5055,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.288,
|
| 48 |
+
"grad_norm": 0.26381659507751465,
|
| 49 |
+
"learning_rate": 1e-05,
|
| 50 |
+
"loss": 0.4363,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.336,
|
| 55 |
+
"grad_norm": 0.2484428882598877,
|
| 56 |
+
"learning_rate": 9.991540791356342e-06,
|
| 57 |
+
"loss": 0.4857,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.384,
|
| 62 |
+
"grad_norm": 0.2681486904621124,
|
| 63 |
+
"learning_rate": 9.966191788709716e-06,
|
| 64 |
+
"loss": 0.5556,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.432,
|
| 69 |
+
"grad_norm": 0.28722772002220154,
|
| 70 |
+
"learning_rate": 9.924038765061042e-06,
|
| 71 |
+
"loss": 0.5532,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.48,
|
| 76 |
+
"grad_norm": 0.26680728793144226,
|
| 77 |
+
"learning_rate": 9.86522435289912e-06,
|
| 78 |
+
"loss": 0.6138,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.528,
|
| 83 |
+
"grad_norm": 0.21414291858673096,
|
| 84 |
+
"learning_rate": 9.789947561577445e-06,
|
| 85 |
+
"loss": 0.5207,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.576,
|
| 90 |
+
"grad_norm": 0.22129523754119873,
|
| 91 |
+
"learning_rate": 9.698463103929542e-06,
|
| 92 |
+
"loss": 0.5395,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.624,
|
| 97 |
+
"grad_norm": 0.2071954756975174,
|
| 98 |
+
"learning_rate": 9.591080534401371e-06,
|
| 99 |
+
"loss": 0.5599,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.672,
|
| 104 |
+
"grad_norm": 0.18173572421073914,
|
| 105 |
+
"learning_rate": 9.468163201617063e-06,
|
| 106 |
+
"loss": 0.4935,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.72,
|
| 111 |
+
"grad_norm": 0.1673681139945984,
|
| 112 |
+
"learning_rate": 9.330127018922195e-06,
|
| 113 |
+
"loss": 0.5062,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.768,
|
| 118 |
+
"grad_norm": 0.1739712953567505,
|
| 119 |
+
"learning_rate": 9.177439057064684e-06,
|
| 120 |
+
"loss": 0.5003,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.816,
|
| 125 |
+
"grad_norm": 0.16390115022659302,
|
| 126 |
+
"learning_rate": 9.01061596377522e-06,
|
| 127 |
+
"loss": 0.4908,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.864,
|
| 132 |
+
"grad_norm": 0.1472504436969757,
|
| 133 |
+
"learning_rate": 8.83022221559489e-06,
|
| 134 |
+
"loss": 0.4909,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.912,
|
| 139 |
+
"grad_norm": 0.14271003007888794,
|
| 140 |
+
"learning_rate": 8.636868207865244e-06,
|
| 141 |
+
"loss": 0.4884,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.96,
|
| 146 |
+
"grad_norm": 0.15660056471824646,
|
| 147 |
+
"learning_rate": 8.43120818934367e-06,
|
| 148 |
+
"loss": 0.4936,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.048,
|
| 153 |
+
"grad_norm": 0.2163340151309967,
|
| 154 |
+
"learning_rate": 8.213938048432697e-06,
|
| 155 |
+
"loss": 0.7499,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.096,
|
| 160 |
+
"grad_norm": 0.14213234186172485,
|
| 161 |
+
"learning_rate": 7.985792958513932e-06,
|
| 162 |
+
"loss": 0.3572,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.144,
|
| 167 |
+
"grad_norm": 0.14226825535297394,
|
| 168 |
+
"learning_rate": 7.747544890354031e-06,
|
| 169 |
+
"loss": 0.3631,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.192,
|
| 174 |
+
"grad_norm": 0.12011696398258209,
|
| 175 |
+
"learning_rate": 7.500000000000001e-06,
|
| 176 |
+
"loss": 0.3414,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.24,
|
| 181 |
+
"grad_norm": 0.14066629111766815,
|
| 182 |
+
"learning_rate": 7.243995901002312e-06,
|
| 183 |
+
"loss": 0.3472,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.288,
|
| 188 |
+
"grad_norm": 0.11682265251874924,
|
| 189 |
+
"learning_rate": 6.980398830195785e-06,
|
| 190 |
+
"loss": 0.3415,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.336,
|
| 195 |
+
"grad_norm": 0.12975744903087616,
|
| 196 |
+
"learning_rate": 6.710100716628345e-06,
|
| 197 |
+
"loss": 0.3328,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.384,
|
| 202 |
+
"grad_norm": 0.11025315523147583,
|
| 203 |
+
"learning_rate": 6.434016163555452e-06,
|
| 204 |
+
"loss": 0.3587,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.432,
|
| 209 |
+
"grad_norm": 0.12963436543941498,
|
| 210 |
+
"learning_rate": 6.153079353712201e-06,
|
| 211 |
+
"loss": 0.3098,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.48,
|
| 216 |
+
"grad_norm": 0.11641515046358109,
|
| 217 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 218 |
+
"loss": 0.3159,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.528,
|
| 223 |
+
"grad_norm": 0.1281406134366989,
|
| 224 |
+
"learning_rate": 5.5804645706261515e-06,
|
| 225 |
+
"loss": 0.3283,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.576,
|
| 230 |
+
"grad_norm": 0.11018883436918259,
|
| 231 |
+
"learning_rate": 5.290724144552379e-06,
|
| 232 |
+
"loss": 0.3175,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.624,
|
| 237 |
+
"grad_norm": 0.13282187283039093,
|
| 238 |
+
"learning_rate": 5e-06,
|
| 239 |
+
"loss": 0.2702,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.6720000000000002,
|
| 244 |
+
"grad_norm": 0.14893370866775513,
|
| 245 |
+
"learning_rate": 4.7092758554476215e-06,
|
| 246 |
+
"loss": 0.2807,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.72,
|
| 251 |
+
"grad_norm": 0.1253272294998169,
|
| 252 |
+
"learning_rate": 4.4195354293738484e-06,
|
| 253 |
+
"loss": 0.2936,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.768,
|
| 258 |
+
"grad_norm": 0.11152789741754532,
|
| 259 |
+
"learning_rate": 4.131759111665349e-06,
|
| 260 |
+
"loss": 0.3005,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.8159999999999998,
|
| 265 |
+
"grad_norm": 0.11078399419784546,
|
| 266 |
+
"learning_rate": 3.8469206462878e-06,
|
| 267 |
+
"loss": 0.3255,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.8639999999999999,
|
| 272 |
+
"grad_norm": 0.11652141064405441,
|
| 273 |
+
"learning_rate": 3.5659838364445505e-06,
|
| 274 |
+
"loss": 0.3027,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.912,
|
| 279 |
+
"grad_norm": 0.10897649079561234,
|
| 280 |
+
"learning_rate": 3.289899283371657e-06,
|
| 281 |
+
"loss": 0.2728,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.96,
|
| 286 |
+
"grad_norm": 0.1067444458603859,
|
| 287 |
+
"learning_rate": 3.019601169804216e-06,
|
| 288 |
+
"loss": 0.3053,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.048,
|
| 293 |
+
"grad_norm": 0.12603534758090973,
|
| 294 |
+
"learning_rate": 2.7560040989976894e-06,
|
| 295 |
+
"loss": 0.5317,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.096,
|
| 300 |
+
"grad_norm": 0.10293126851320267,
|
| 301 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 302 |
+
"loss": 0.2568,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.144,
|
| 307 |
+
"grad_norm": 0.09188748151063919,
|
| 308 |
+
"learning_rate": 2.2524551096459703e-06,
|
| 309 |
+
"loss": 0.208,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.192,
|
| 314 |
+
"grad_norm": 0.08503475040197372,
|
| 315 |
+
"learning_rate": 2.0142070414860704e-06,
|
| 316 |
+
"loss": 0.2053,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 2.24,
|
| 321 |
+
"grad_norm": 0.10515239089727402,
|
| 322 |
+
"learning_rate": 1.7860619515673034e-06,
|
| 323 |
+
"loss": 0.2588,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.288,
|
| 328 |
+
"grad_norm": 0.08518028259277344,
|
| 329 |
+
"learning_rate": 1.5687918106563326e-06,
|
| 330 |
+
"loss": 0.2036,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.336,
|
| 335 |
+
"grad_norm": 0.08311820775270462,
|
| 336 |
+
"learning_rate": 1.3631317921347564e-06,
|
| 337 |
+
"loss": 0.2469,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.384,
|
| 342 |
+
"grad_norm": 0.08776900172233582,
|
| 343 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 344 |
+
"loss": 0.2237,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 2.432,
|
| 349 |
+
"grad_norm": 0.09390392154455185,
|
| 350 |
+
"learning_rate": 9.893840362247809e-07,
|
| 351 |
+
"loss": 0.2476,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 2.48,
|
| 356 |
+
"grad_norm": 0.09852010011672974,
|
| 357 |
+
"learning_rate": 8.225609429353187e-07,
|
| 358 |
+
"loss": 0.2475,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.528,
|
| 363 |
+
"grad_norm": 0.10095316171646118,
|
| 364 |
+
"learning_rate": 6.698729810778065e-07,
|
| 365 |
+
"loss": 0.2274,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.576,
|
| 370 |
+
"grad_norm": 0.08666174858808517,
|
| 371 |
+
"learning_rate": 5.318367983829393e-07,
|
| 372 |
+
"loss": 0.2497,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.624,
|
| 377 |
+
"grad_norm": 0.10396892577409744,
|
| 378 |
+
"learning_rate": 4.089194655986306e-07,
|
| 379 |
+
"loss": 0.2269,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.672,
|
| 384 |
+
"grad_norm": 0.09909585118293762,
|
| 385 |
+
"learning_rate": 3.015368960704584e-07,
|
| 386 |
+
"loss": 0.2198,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.7199999999999998,
|
| 391 |
+
"grad_norm": 0.08612281084060669,
|
| 392 |
+
"learning_rate": 2.1005243842255552e-07,
|
| 393 |
+
"loss": 0.2219,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.768,
|
| 398 |
+
"grad_norm": 0.09808117151260376,
|
| 399 |
+
"learning_rate": 1.3477564710088097e-07,
|
| 400 |
+
"loss": 0.209,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.816,
|
| 405 |
+
"grad_norm": 0.09213282912969589,
|
| 406 |
+
"learning_rate": 7.59612349389599e-08,
|
| 407 |
+
"loss": 0.2084,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.864,
|
| 412 |
+
"grad_norm": 0.10377876460552216,
|
| 413 |
+
"learning_rate": 3.3808211290284886e-08,
|
| 414 |
+
"loss": 0.2487,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.912,
|
| 419 |
+
"grad_norm": 0.10324692726135254,
|
| 420 |
+
"learning_rate": 8.459208643659122e-09,
|
| 421 |
+
"loss": 0.2267,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.96,
|
| 426 |
+
"grad_norm": 0.09482261538505554,
|
| 427 |
+
"learning_rate": 0.0,
|
| 428 |
+
"loss": 0.2104,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.96,
|
| 433 |
+
"step": 60,
|
| 434 |
+
"total_flos": 2.770915149689651e+16,
|
| 435 |
+
"train_loss": 0.37391861056288084,
|
| 436 |
+
"train_runtime": 21254.7027,
|
| 437 |
+
"train_samples_per_second": 0.071,
|
| 438 |
+
"train_steps_per_second": 0.003
|
| 439 |
+
}
|
| 440 |
+
],
|
| 441 |
+
"logging_steps": 1,
|
| 442 |
+
"max_steps": 60,
|
| 443 |
+
"num_input_tokens_seen": 0,
|
| 444 |
+
"num_train_epochs": 3,
|
| 445 |
+
"save_steps": 200,
|
| 446 |
+
"stateful_callbacks": {
|
| 447 |
+
"TrainerControl": {
|
| 448 |
+
"args": {
|
| 449 |
+
"should_epoch_stop": false,
|
| 450 |
+
"should_evaluate": false,
|
| 451 |
+
"should_log": false,
|
| 452 |
+
"should_save": true,
|
| 453 |
+
"should_training_stop": true
|
| 454 |
+
},
|
| 455 |
+
"attributes": {}
|
| 456 |
+
}
|
| 457 |
+
},
|
| 458 |
+
"total_flos": 2.770915149689651e+16,
|
| 459 |
+
"train_batch_size": 1,
|
| 460 |
+
"trial_name": null,
|
| 461 |
+
"trial_params": null
|
| 462 |
+
}
|
training_loss.png
ADDED
|