End of training
Browse files- README.md +1 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +402 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# Model
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 0.3503
|
| 24 |
|
|
|
|
| 18 |
|
| 19 |
# Model
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the finance_qa_train dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
- Loss: 0.3503
|
| 24 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.3503350019454956,
|
| 4 |
+
"eval_runtime": 156.5604,
|
| 5 |
+
"eval_samples_per_second": 1.162,
|
| 6 |
+
"eval_steps_per_second": 1.162,
|
| 7 |
+
"total_flos": 6337444903649280.0,
|
| 8 |
+
"train_loss": 0.6454218102664482,
|
| 9 |
+
"train_runtime": 5611.1366,
|
| 10 |
+
"train_samples_per_second": 0.292,
|
| 11 |
+
"train_steps_per_second": 0.073
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.3503350019454956,
|
| 4 |
+
"eval_runtime": 156.5604,
|
| 5 |
+
"eval_samples_per_second": 1.162,
|
| 6 |
+
"eval_steps_per_second": 1.162
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 6337444903649280.0,
|
| 4 |
+
"train_loss": 0.6454218102664482,
|
| 5 |
+
"train_runtime": 5611.1366,
|
| 6 |
+
"train_samples_per_second": 0.292,
|
| 7 |
+
"train_steps_per_second": 0.073
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,402 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 410,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.02442002442002442,
|
| 14 |
+
"grad_norm": 1.8804959058761597,
|
| 15 |
+
"learning_rate": 2.1951219512195124e-05,
|
| 16 |
+
"loss": 1.0383675575256348,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.04884004884004884,
|
| 21 |
+
"grad_norm": 1.260099172592163,
|
| 22 |
+
"learning_rate": 4.634146341463415e-05,
|
| 23 |
+
"loss": 0.9142965316772461,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.07326007326007326,
|
| 28 |
+
"grad_norm": 2.452146291732788,
|
| 29 |
+
"learning_rate": 7.073170731707317e-05,
|
| 30 |
+
"loss": 0.5925925731658935,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.09768009768009768,
|
| 35 |
+
"grad_norm": 0.9088484644889832,
|
| 36 |
+
"learning_rate": 9.51219512195122e-05,
|
| 37 |
+
"loss": 0.625553035736084,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.1221001221001221,
|
| 42 |
+
"grad_norm": 1.1221411228179932,
|
| 43 |
+
"learning_rate": 9.98840691294159e-05,
|
| 44 |
+
"loss": 0.7184983253479004,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.1221001221001221,
|
| 49 |
+
"eval_loss": 0.4379732608795166,
|
| 50 |
+
"eval_runtime": 155.1212,
|
| 51 |
+
"eval_samples_per_second": 1.173,
|
| 52 |
+
"eval_steps_per_second": 1.173,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.14652014652014653,
|
| 57 |
+
"grad_norm": 1.48092520236969,
|
| 58 |
+
"learning_rate": 9.941402118901744e-05,
|
| 59 |
+
"loss": 0.6436511516571045,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.17094017094017094,
|
| 64 |
+
"grad_norm": 0.9403982162475586,
|
| 65 |
+
"learning_rate": 9.858601294888213e-05,
|
| 66 |
+
"loss": 0.6321167945861816,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.19536019536019536,
|
| 71 |
+
"grad_norm": 1.9959934949874878,
|
| 72 |
+
"learning_rate": 9.740604258666668e-05,
|
| 73 |
+
"loss": 0.4339743137359619,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.21978021978021978,
|
| 78 |
+
"grad_norm": 0.8679758310317993,
|
| 79 |
+
"learning_rate": 9.58826579301814e-05,
|
| 80 |
+
"loss": 0.7650653839111328,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.2442002442002442,
|
| 85 |
+
"grad_norm": 0.8135587573051453,
|
| 86 |
+
"learning_rate": 9.402689453603815e-05,
|
| 87 |
+
"loss": 0.9344680786132813,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.2442002442002442,
|
| 92 |
+
"eval_loss": 0.410927414894104,
|
| 93 |
+
"eval_runtime": 155.7582,
|
| 94 |
+
"eval_samples_per_second": 1.168,
|
| 95 |
+
"eval_steps_per_second": 1.168,
|
| 96 |
+
"step": 100
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.2686202686202686,
|
| 100 |
+
"grad_norm": 0.9190899729728699,
|
| 101 |
+
"learning_rate": 9.185219574693242e-05,
|
| 102 |
+
"loss": 0.929171371459961,
|
| 103 |
+
"step": 110
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.29304029304029305,
|
| 107 |
+
"grad_norm": 1.7113302946090698,
|
| 108 |
+
"learning_rate": 8.937431530667328e-05,
|
| 109 |
+
"loss": 0.8475244522094727,
|
| 110 |
+
"step": 120
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.31746031746031744,
|
| 114 |
+
"grad_norm": 1.2021324634552002,
|
| 115 |
+
"learning_rate": 8.661120323842751e-05,
|
| 116 |
+
"loss": 0.7967288494110107,
|
| 117 |
+
"step": 130
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.3418803418803419,
|
| 121 |
+
"grad_norm": 1.2183983325958252,
|
| 122 |
+
"learning_rate": 8.358287581288822e-05,
|
| 123 |
+
"loss": 0.6628508567810059,
|
| 124 |
+
"step": 140
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.3663003663003663,
|
| 128 |
+
"grad_norm": 0.6963383555412292,
|
| 129 |
+
"learning_rate": 8.03112705483319e-05,
|
| 130 |
+
"loss": 0.35836048126220704,
|
| 131 |
+
"step": 150
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.3663003663003663,
|
| 135 |
+
"eval_loss": 0.3939921259880066,
|
| 136 |
+
"eval_runtime": 155.1823,
|
| 137 |
+
"eval_samples_per_second": 1.173,
|
| 138 |
+
"eval_steps_per_second": 1.173,
|
| 139 |
+
"step": 150
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.3907203907203907,
|
| 143 |
+
"grad_norm": 1.2565363645553589,
|
| 144 |
+
"learning_rate": 7.682008729295833e-05,
|
| 145 |
+
"loss": 0.6145974636077881,
|
| 146 |
+
"step": 160
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.41514041514041516,
|
| 150 |
+
"grad_norm": 0.4023746848106384,
|
| 151 |
+
"learning_rate": 7.313461654072973e-05,
|
| 152 |
+
"loss": 0.462252140045166,
|
| 153 |
+
"step": 170
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.43956043956043955,
|
| 157 |
+
"grad_norm": 0.8940127491950989,
|
| 158 |
+
"learning_rate": 6.92815562244068e-05,
|
| 159 |
+
"loss": 0.895142936706543,
|
| 160 |
+
"step": 180
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.463980463980464,
|
| 164 |
+
"grad_norm": 0.9050699472427368,
|
| 165 |
+
"learning_rate": 6.528881831295188e-05,
|
| 166 |
+
"loss": 0.5885900020599365,
|
| 167 |
+
"step": 190
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.4884004884004884,
|
| 171 |
+
"grad_norm": 1.7588568925857544,
|
| 172 |
+
"learning_rate": 6.118532661432812e-05,
|
| 173 |
+
"loss": 0.6375821590423584,
|
| 174 |
+
"step": 200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.4884004884004884,
|
| 178 |
+
"eval_loss": 0.3821566104888916,
|
| 179 |
+
"eval_runtime": 155.428,
|
| 180 |
+
"eval_samples_per_second": 1.171,
|
| 181 |
+
"eval_steps_per_second": 1.171,
|
| 182 |
+
"step": 200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.5128205128205128,
|
| 186 |
+
"grad_norm": 0.8788589239120483,
|
| 187 |
+
"learning_rate": 5.700080724843147e-05,
|
| 188 |
+
"loss": 0.5496622562408447,
|
| 189 |
+
"step": 210
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.5372405372405372,
|
| 193 |
+
"grad_norm": 1.0257195234298706,
|
| 194 |
+
"learning_rate": 5.2765573307992036e-05,
|
| 195 |
+
"loss": 0.7461658000946045,
|
| 196 |
+
"step": 220
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.5616605616605617,
|
| 200 |
+
"grad_norm": 1.6746125221252441,
|
| 201 |
+
"learning_rate": 4.851030526738321e-05,
|
| 202 |
+
"loss": 0.5698539733886718,
|
| 203 |
+
"step": 230
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.5860805860805861,
|
| 207 |
+
"grad_norm": 0.8949107527732849,
|
| 208 |
+
"learning_rate": 4.4265828730079987e-05,
|
| 209 |
+
"loss": 0.5721668243408203,
|
| 210 |
+
"step": 240
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.6105006105006106,
|
| 214 |
+
"grad_norm": 2.384493350982666,
|
| 215 |
+
"learning_rate": 4.0062891124787e-05,
|
| 216 |
+
"loss": 0.7134846687316895,
|
| 217 |
+
"step": 250
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.6105006105006106,
|
| 221 |
+
"eval_loss": 0.36719319224357605,
|
| 222 |
+
"eval_runtime": 155.0828,
|
| 223 |
+
"eval_samples_per_second": 1.174,
|
| 224 |
+
"eval_steps_per_second": 1.174,
|
| 225 |
+
"step": 250
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.6349206349206349,
|
| 229 |
+
"grad_norm": 1.2632209062576294,
|
| 230 |
+
"learning_rate": 3.5931938967872766e-05,
|
| 231 |
+
"loss": 0.7118762969970703,
|
| 232 |
+
"step": 260
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.6593406593406593,
|
| 236 |
+
"grad_norm": 1.3680095672607422,
|
| 237 |
+
"learning_rate": 3.1902897305644095e-05,
|
| 238 |
+
"loss": 0.8658300399780273,
|
| 239 |
+
"step": 270
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.6837606837606838,
|
| 243 |
+
"grad_norm": 1.2788431644439697,
|
| 244 |
+
"learning_rate": 2.8004952934203838e-05,
|
| 245 |
+
"loss": 0.7101179122924804,
|
| 246 |
+
"step": 280
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.7081807081807082,
|
| 250 |
+
"grad_norm": 1.044674277305603,
|
| 251 |
+
"learning_rate": 2.4266342967269552e-05,
|
| 252 |
+
"loss": 0.5662980079650879,
|
| 253 |
+
"step": 290
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.7326007326007326,
|
| 257 |
+
"grad_norm": 1.589475154876709,
|
| 258 |
+
"learning_rate": 2.071415028359026e-05,
|
| 259 |
+
"loss": 0.5755983352661133,
|
| 260 |
+
"step": 300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.7326007326007326,
|
| 264 |
+
"eval_loss": 0.355652779340744,
|
| 265 |
+
"eval_runtime": 155.57,
|
| 266 |
+
"eval_samples_per_second": 1.17,
|
| 267 |
+
"eval_steps_per_second": 1.17,
|
| 268 |
+
"step": 300
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.757020757020757,
|
| 272 |
+
"grad_norm": 1.370431900024414,
|
| 273 |
+
"learning_rate": 1.7374107335760936e-05,
|
| 274 |
+
"loss": 0.539859390258789,
|
| 275 |
+
"step": 310
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7814407814407814,
|
| 279 |
+
"grad_norm": 0.995492160320282,
|
| 280 |
+
"learning_rate": 1.427040974166427e-05,
|
| 281 |
+
"loss": 0.2917079210281372,
|
| 282 |
+
"step": 320
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.8058608058608059,
|
| 286 |
+
"grad_norm": 1.1896394491195679,
|
| 287 |
+
"learning_rate": 1.1425541008902851e-05,
|
| 288 |
+
"loss": 0.7617981433868408,
|
| 289 |
+
"step": 330
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.8302808302808303,
|
| 293 |
+
"grad_norm": 2.3315072059631348,
|
| 294 |
+
"learning_rate": 8.860109661935674e-06,
|
| 295 |
+
"loss": 0.6248091697692871,
|
| 296 |
+
"step": 340
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.8547008547008547,
|
| 300 |
+
"grad_norm": 0.6425564885139465,
|
| 301 |
+
"learning_rate": 6.592699951787362e-06,
|
| 302 |
+
"loss": 0.4457353115081787,
|
| 303 |
+
"step": 350
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.8547008547008547,
|
| 307 |
+
"eval_loss": 0.35156095027923584,
|
| 308 |
+
"eval_runtime": 155.323,
|
| 309 |
+
"eval_samples_per_second": 1.172,
|
| 310 |
+
"eval_steps_per_second": 1.172,
|
| 311 |
+
"step": 350
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8791208791208791,
|
| 315 |
+
"grad_norm": 1.164421796798706,
|
| 316 |
+
"learning_rate": 4.639737229804403e-06,
|
| 317 |
+
"loss": 0.36368584632873535,
|
| 318 |
+
"step": 360
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.9035409035409036,
|
| 322 |
+
"grad_norm": 1.071614146232605,
|
| 323 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 324 |
+
"loss": 0.5256676197052002,
|
| 325 |
+
"step": 370
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.927960927960928,
|
| 329 |
+
"grad_norm": 0.6991368532180786,
|
| 330 |
+
"learning_rate": 1.7313622368738014e-06,
|
| 331 |
+
"loss": 0.5124877452850342,
|
| 332 |
+
"step": 380
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.9523809523809523,
|
| 336 |
+
"grad_norm": 1.053227186203003,
|
| 337 |
+
"learning_rate": 7.970185363271431e-07,
|
| 338 |
+
"loss": 0.444692325592041,
|
| 339 |
+
"step": 390
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.9768009768009768,
|
| 343 |
+
"grad_norm": 1.5848822593688965,
|
| 344 |
+
"learning_rate": 2.1910634183644474e-07,
|
| 345 |
+
"loss": 0.5859388828277587,
|
| 346 |
+
"step": 400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.9768009768009768,
|
| 350 |
+
"eval_loss": 0.3502028286457062,
|
| 351 |
+
"eval_runtime": 155.3968,
|
| 352 |
+
"eval_samples_per_second": 1.171,
|
| 353 |
+
"eval_steps_per_second": 1.171,
|
| 354 |
+
"step": 400
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.0,
|
| 358 |
+
"grad_norm": 0.7781813740730286,
|
| 359 |
+
"learning_rate": 1.8121093383671738e-09,
|
| 360 |
+
"loss": 0.6934732913970947,
|
| 361 |
+
"step": 410
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.0,
|
| 365 |
+
"eval_loss": 0.3503350019454956,
|
| 366 |
+
"eval_runtime": 155.368,
|
| 367 |
+
"eval_samples_per_second": 1.171,
|
| 368 |
+
"eval_steps_per_second": 1.171,
|
| 369 |
+
"step": 410
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.0,
|
| 373 |
+
"step": 410,
|
| 374 |
+
"total_flos": 6337444903649280.0,
|
| 375 |
+
"train_loss": 0.6454218102664482,
|
| 376 |
+
"train_runtime": 5611.1366,
|
| 377 |
+
"train_samples_per_second": 0.292,
|
| 378 |
+
"train_steps_per_second": 0.073
|
| 379 |
+
}
|
| 380 |
+
],
|
| 381 |
+
"logging_steps": 10,
|
| 382 |
+
"max_steps": 410,
|
| 383 |
+
"num_input_tokens_seen": 0,
|
| 384 |
+
"num_train_epochs": 1,
|
| 385 |
+
"save_steps": 200,
|
| 386 |
+
"stateful_callbacks": {
|
| 387 |
+
"TrainerControl": {
|
| 388 |
+
"args": {
|
| 389 |
+
"should_epoch_stop": false,
|
| 390 |
+
"should_evaluate": false,
|
| 391 |
+
"should_log": false,
|
| 392 |
+
"should_save": true,
|
| 393 |
+
"should_training_stop": true
|
| 394 |
+
},
|
| 395 |
+
"attributes": {}
|
| 396 |
+
}
|
| 397 |
+
},
|
| 398 |
+
"total_flos": 6337444903649280.0,
|
| 399 |
+
"train_batch_size": 1,
|
| 400 |
+
"trial_name": null,
|
| 401 |
+
"trial_params": null
|
| 402 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|