End of training
Browse files- README.md +2 -2
- all_results.json +15 -0
- eval_results.json +9 -0
- predict_results.txt +0 -0
- train_results.json +9 -0
- trainer_state.json +507 -0
README.md
CHANGED
|
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- F1: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2749
|
| 22 |
+
- F1: 0.9467
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_f1": 0.946677833612507,
|
| 4 |
+
"eval_loss": 0.2749080955982208,
|
| 5 |
+
"eval_runtime": 9.5585,
|
| 6 |
+
"eval_samples": 3582,
|
| 7 |
+
"eval_samples_per_second": 374.743,
|
| 8 |
+
"eval_steps_per_second": 2.929,
|
| 9 |
+
"total_flos": 6.517582470540288e+16,
|
| 10 |
+
"train_loss": 0.04250985115152044,
|
| 11 |
+
"train_runtime": 8305.2138,
|
| 12 |
+
"train_samples": 24771,
|
| 13 |
+
"train_samples_per_second": 119.303,
|
| 14 |
+
"train_steps_per_second": 0.934
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"eval_f1": 0.946677833612507,
|
| 4 |
+
"eval_loss": 0.2749080955982208,
|
| 5 |
+
"eval_runtime": 9.5585,
|
| 6 |
+
"eval_samples": 3582,
|
| 7 |
+
"eval_samples_per_second": 374.743,
|
| 8 |
+
"eval_steps_per_second": 2.929
|
| 9 |
+
}
|
predict_results.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 40.0,
|
| 3 |
+
"total_flos": 6.517582470540288e+16,
|
| 4 |
+
"train_loss": 0.04250985115152044,
|
| 5 |
+
"train_runtime": 8305.2138,
|
| 6 |
+
"train_samples": 24771,
|
| 7 |
+
"train_samples_per_second": 119.303,
|
| 8 |
+
"train_steps_per_second": 0.934
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,507 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.946677833612507,
|
| 3 |
+
"best_model_checkpoint": "/tmp/classification_phobert-v2/checkpoint-2522",
|
| 4 |
+
"epoch": 40.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 7760,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_f1": 0.9346733668341709,
|
| 14 |
+
"eval_loss": 0.2288697063922882,
|
| 15 |
+
"eval_runtime": 9.6999,
|
| 16 |
+
"eval_samples_per_second": 369.281,
|
| 17 |
+
"eval_steps_per_second": 2.887,
|
| 18 |
+
"step": 194
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 2.0,
|
| 22 |
+
"eval_f1": 0.9399776661083193,
|
| 23 |
+
"eval_loss": 0.1812455654144287,
|
| 24 |
+
"eval_runtime": 9.6897,
|
| 25 |
+
"eval_samples_per_second": 369.672,
|
| 26 |
+
"eval_steps_per_second": 2.89,
|
| 27 |
+
"step": 388
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 2.5773195876288657,
|
| 31 |
+
"grad_norm": 3.7161166667938232,
|
| 32 |
+
"learning_rate": 2.806701030927835e-05,
|
| 33 |
+
"loss": 0.2405,
|
| 34 |
+
"step": 500
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 3.0,
|
| 38 |
+
"eval_f1": 0.9447236180904522,
|
| 39 |
+
"eval_loss": 0.17744559049606323,
|
| 40 |
+
"eval_runtime": 9.6898,
|
| 41 |
+
"eval_samples_per_second": 369.666,
|
| 42 |
+
"eval_steps_per_second": 2.89,
|
| 43 |
+
"step": 582
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 4.0,
|
| 47 |
+
"eval_f1": 0.9433277498604131,
|
| 48 |
+
"eval_loss": 0.1997271031141281,
|
| 49 |
+
"eval_runtime": 9.6886,
|
| 50 |
+
"eval_samples_per_second": 369.711,
|
| 51 |
+
"eval_steps_per_second": 2.89,
|
| 52 |
+
"step": 776
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 5.0,
|
| 56 |
+
"eval_f1": 0.9427694025683976,
|
| 57 |
+
"eval_loss": 0.22364477813243866,
|
| 58 |
+
"eval_runtime": 9.704,
|
| 59 |
+
"eval_samples_per_second": 369.128,
|
| 60 |
+
"eval_steps_per_second": 2.885,
|
| 61 |
+
"step": 970
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 5.154639175257732,
|
| 65 |
+
"grad_norm": 8.774168968200684,
|
| 66 |
+
"learning_rate": 2.61340206185567e-05,
|
| 67 |
+
"loss": 0.1112,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 6.0,
|
| 72 |
+
"eval_f1": 0.9380234505862647,
|
| 73 |
+
"eval_loss": 0.24477960169315338,
|
| 74 |
+
"eval_runtime": 9.6887,
|
| 75 |
+
"eval_samples_per_second": 369.71,
|
| 76 |
+
"eval_steps_per_second": 2.89,
|
| 77 |
+
"step": 1164
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 7.0,
|
| 81 |
+
"eval_f1": 0.9441652707984366,
|
| 82 |
+
"eval_loss": 0.22501157224178314,
|
| 83 |
+
"eval_runtime": 9.6707,
|
| 84 |
+
"eval_samples_per_second": 370.399,
|
| 85 |
+
"eval_steps_per_second": 2.895,
|
| 86 |
+
"step": 1358
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 7.731958762886598,
|
| 90 |
+
"grad_norm": 1.4358633756637573,
|
| 91 |
+
"learning_rate": 2.4201030927835052e-05,
|
| 92 |
+
"loss": 0.0717,
|
| 93 |
+
"step": 1500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.0,
|
| 97 |
+
"eval_f1": 0.9413735343383585,
|
| 98 |
+
"eval_loss": 0.24096541106700897,
|
| 99 |
+
"eval_runtime": 9.6976,
|
| 100 |
+
"eval_samples_per_second": 369.369,
|
| 101 |
+
"eval_steps_per_second": 2.887,
|
| 102 |
+
"step": 1552
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 9.0,
|
| 106 |
+
"eval_f1": 0.9413735343383585,
|
| 107 |
+
"eval_loss": 0.24880127608776093,
|
| 108 |
+
"eval_runtime": 9.685,
|
| 109 |
+
"eval_samples_per_second": 369.852,
|
| 110 |
+
"eval_steps_per_second": 2.891,
|
| 111 |
+
"step": 1746
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 10.0,
|
| 115 |
+
"eval_f1": 0.9447236180904522,
|
| 116 |
+
"eval_loss": 0.26668497920036316,
|
| 117 |
+
"eval_runtime": 9.6717,
|
| 118 |
+
"eval_samples_per_second": 370.357,
|
| 119 |
+
"eval_steps_per_second": 2.895,
|
| 120 |
+
"step": 1940
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 10.309278350515465,
|
| 124 |
+
"grad_norm": 1.2549242973327637,
|
| 125 |
+
"learning_rate": 2.2268041237113402e-05,
|
| 126 |
+
"loss": 0.0525,
|
| 127 |
+
"step": 2000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 11.0,
|
| 131 |
+
"eval_f1": 0.9455611390284757,
|
| 132 |
+
"eval_loss": 0.26830339431762695,
|
| 133 |
+
"eval_runtime": 9.6812,
|
| 134 |
+
"eval_samples_per_second": 369.996,
|
| 135 |
+
"eval_steps_per_second": 2.892,
|
| 136 |
+
"step": 2134
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 12.0,
|
| 140 |
+
"eval_f1": 0.9413735343383585,
|
| 141 |
+
"eval_loss": 0.3144669532775879,
|
| 142 |
+
"eval_runtime": 9.668,
|
| 143 |
+
"eval_samples_per_second": 370.501,
|
| 144 |
+
"eval_steps_per_second": 2.896,
|
| 145 |
+
"step": 2328
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 12.88659793814433,
|
| 149 |
+
"grad_norm": 0.8762478232383728,
|
| 150 |
+
"learning_rate": 2.0335051546391752e-05,
|
| 151 |
+
"loss": 0.0402,
|
| 152 |
+
"step": 2500
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 13.0,
|
| 156 |
+
"eval_f1": 0.946677833612507,
|
| 157 |
+
"eval_loss": 0.2749080955982208,
|
| 158 |
+
"eval_runtime": 9.685,
|
| 159 |
+
"eval_samples_per_second": 369.852,
|
| 160 |
+
"eval_steps_per_second": 2.891,
|
| 161 |
+
"step": 2522
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 14.0,
|
| 165 |
+
"eval_f1": 0.9430485762144054,
|
| 166 |
+
"eval_loss": 0.3029841482639313,
|
| 167 |
+
"eval_runtime": 9.6934,
|
| 168 |
+
"eval_samples_per_second": 369.531,
|
| 169 |
+
"eval_steps_per_second": 2.889,
|
| 170 |
+
"step": 2716
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 15.0,
|
| 174 |
+
"eval_f1": 0.9458403126744835,
|
| 175 |
+
"eval_loss": 0.3058845102787018,
|
| 176 |
+
"eval_runtime": 9.6767,
|
| 177 |
+
"eval_samples_per_second": 370.168,
|
| 178 |
+
"eval_steps_per_second": 2.894,
|
| 179 |
+
"step": 2910
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 15.463917525773196,
|
| 183 |
+
"grad_norm": 0.3448758125305176,
|
| 184 |
+
"learning_rate": 1.8402061855670106e-05,
|
| 185 |
+
"loss": 0.0285,
|
| 186 |
+
"step": 3000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 16.0,
|
| 190 |
+
"eval_f1": 0.9424902289223898,
|
| 191 |
+
"eval_loss": 0.3259759247303009,
|
| 192 |
+
"eval_runtime": 9.6809,
|
| 193 |
+
"eval_samples_per_second": 370.008,
|
| 194 |
+
"eval_steps_per_second": 2.892,
|
| 195 |
+
"step": 3104
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 17.0,
|
| 199 |
+
"eval_f1": 0.9463986599664992,
|
| 200 |
+
"eval_loss": 0.32083001732826233,
|
| 201 |
+
"eval_runtime": 9.6806,
|
| 202 |
+
"eval_samples_per_second": 370.018,
|
| 203 |
+
"eval_steps_per_second": 2.892,
|
| 204 |
+
"step": 3298
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 18.0,
|
| 208 |
+
"eval_f1": 0.9394193188163037,
|
| 209 |
+
"eval_loss": 0.3752443492412567,
|
| 210 |
+
"eval_runtime": 9.6833,
|
| 211 |
+
"eval_samples_per_second": 369.914,
|
| 212 |
+
"eval_steps_per_second": 2.892,
|
| 213 |
+
"step": 3492
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 18.04123711340206,
|
| 217 |
+
"grad_norm": 0.16492746770381927,
|
| 218 |
+
"learning_rate": 1.6469072164948456e-05,
|
| 219 |
+
"loss": 0.0225,
|
| 220 |
+
"step": 3500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 19.0,
|
| 224 |
+
"eval_f1": 0.9450027917364601,
|
| 225 |
+
"eval_loss": 0.3408117890357971,
|
| 226 |
+
"eval_runtime": 9.6821,
|
| 227 |
+
"eval_samples_per_second": 369.963,
|
| 228 |
+
"eval_steps_per_second": 2.892,
|
| 229 |
+
"step": 3686
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 20.0,
|
| 233 |
+
"eval_f1": 0.9366275823562256,
|
| 234 |
+
"eval_loss": 0.41283130645751953,
|
| 235 |
+
"eval_runtime": 9.6877,
|
| 236 |
+
"eval_samples_per_second": 369.748,
|
| 237 |
+
"eval_steps_per_second": 2.89,
|
| 238 |
+
"step": 3880
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 20.61855670103093,
|
| 242 |
+
"grad_norm": 0.5357736945152283,
|
| 243 |
+
"learning_rate": 1.4536082474226805e-05,
|
| 244 |
+
"loss": 0.0166,
|
| 245 |
+
"step": 4000
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 21.0,
|
| 249 |
+
"eval_f1": 0.9408151870463428,
|
| 250 |
+
"eval_loss": 0.37989336252212524,
|
| 251 |
+
"eval_runtime": 9.6608,
|
| 252 |
+
"eval_samples_per_second": 370.777,
|
| 253 |
+
"eval_steps_per_second": 2.898,
|
| 254 |
+
"step": 4074
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 22.0,
|
| 258 |
+
"eval_f1": 0.9388609715242882,
|
| 259 |
+
"eval_loss": 0.3940359354019165,
|
| 260 |
+
"eval_runtime": 9.6719,
|
| 261 |
+
"eval_samples_per_second": 370.351,
|
| 262 |
+
"eval_steps_per_second": 2.895,
|
| 263 |
+
"step": 4268
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 23.0,
|
| 267 |
+
"eval_f1": 0.9450027917364601,
|
| 268 |
+
"eval_loss": 0.37402409315109253,
|
| 269 |
+
"eval_runtime": 9.6886,
|
| 270 |
+
"eval_samples_per_second": 369.713,
|
| 271 |
+
"eval_steps_per_second": 2.89,
|
| 272 |
+
"step": 4462
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 23.195876288659793,
|
| 276 |
+
"grad_norm": 0.6457699537277222,
|
| 277 |
+
"learning_rate": 1.2603092783505155e-05,
|
| 278 |
+
"loss": 0.0153,
|
| 279 |
+
"step": 4500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 24.0,
|
| 283 |
+
"eval_f1": 0.9399776661083193,
|
| 284 |
+
"eval_loss": 0.3809983432292938,
|
| 285 |
+
"eval_runtime": 9.6663,
|
| 286 |
+
"eval_samples_per_second": 370.567,
|
| 287 |
+
"eval_steps_per_second": 2.897,
|
| 288 |
+
"step": 4656
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 25.0,
|
| 292 |
+
"eval_f1": 0.9402568397543272,
|
| 293 |
+
"eval_loss": 0.4277588427066803,
|
| 294 |
+
"eval_runtime": 9.6786,
|
| 295 |
+
"eval_samples_per_second": 370.097,
|
| 296 |
+
"eval_steps_per_second": 2.893,
|
| 297 |
+
"step": 4850
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 25.77319587628866,
|
| 301 |
+
"grad_norm": 0.11396524310112,
|
| 302 |
+
"learning_rate": 1.0670103092783506e-05,
|
| 303 |
+
"loss": 0.0122,
|
| 304 |
+
"step": 5000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 26.0,
|
| 308 |
+
"eval_f1": 0.943606923506421,
|
| 309 |
+
"eval_loss": 0.3878323435783386,
|
| 310 |
+
"eval_runtime": 9.6823,
|
| 311 |
+
"eval_samples_per_second": 369.953,
|
| 312 |
+
"eval_steps_per_second": 2.892,
|
| 313 |
+
"step": 5044
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 27.0,
|
| 317 |
+
"eval_f1": 0.9433277498604131,
|
| 318 |
+
"eval_loss": 0.3903436064720154,
|
| 319 |
+
"eval_runtime": 9.6664,
|
| 320 |
+
"eval_samples_per_second": 370.561,
|
| 321 |
+
"eval_steps_per_second": 2.897,
|
| 322 |
+
"step": 5238
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 28.0,
|
| 326 |
+
"eval_f1": 0.9441652707984366,
|
| 327 |
+
"eval_loss": 0.3903617858886719,
|
| 328 |
+
"eval_runtime": 9.6852,
|
| 329 |
+
"eval_samples_per_second": 369.843,
|
| 330 |
+
"eval_steps_per_second": 2.891,
|
| 331 |
+
"step": 5432
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 28.350515463917525,
|
| 335 |
+
"grad_norm": 0.06657901406288147,
|
| 336 |
+
"learning_rate": 8.737113402061856e-06,
|
| 337 |
+
"loss": 0.0114,
|
| 338 |
+
"step": 5500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 29.0,
|
| 342 |
+
"eval_f1": 0.9427694025683976,
|
| 343 |
+
"eval_loss": 0.42051565647125244,
|
| 344 |
+
"eval_runtime": 9.6905,
|
| 345 |
+
"eval_samples_per_second": 369.642,
|
| 346 |
+
"eval_steps_per_second": 2.889,
|
| 347 |
+
"step": 5626
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 30.0,
|
| 351 |
+
"eval_f1": 0.9433277498604131,
|
| 352 |
+
"eval_loss": 0.3968648612499237,
|
| 353 |
+
"eval_runtime": 9.6628,
|
| 354 |
+
"eval_samples_per_second": 370.701,
|
| 355 |
+
"eval_steps_per_second": 2.898,
|
| 356 |
+
"step": 5820
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 30.927835051546392,
|
| 360 |
+
"grad_norm": 1.0208468437194824,
|
| 361 |
+
"learning_rate": 6.8041237113402065e-06,
|
| 362 |
+
"loss": 0.0096,
|
| 363 |
+
"step": 6000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 31.0,
|
| 367 |
+
"eval_f1": 0.9438860971524288,
|
| 368 |
+
"eval_loss": 0.39665865898132324,
|
| 369 |
+
"eval_runtime": 9.6861,
|
| 370 |
+
"eval_samples_per_second": 369.808,
|
| 371 |
+
"eval_steps_per_second": 2.891,
|
| 372 |
+
"step": 6014
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 32.0,
|
| 376 |
+
"eval_f1": 0.9441652707984366,
|
| 377 |
+
"eval_loss": 0.40085485577583313,
|
| 378 |
+
"eval_runtime": 9.6639,
|
| 379 |
+
"eval_samples_per_second": 370.659,
|
| 380 |
+
"eval_steps_per_second": 2.897,
|
| 381 |
+
"step": 6208
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 33.0,
|
| 385 |
+
"eval_f1": 0.9438860971524288,
|
| 386 |
+
"eval_loss": 0.405376136302948,
|
| 387 |
+
"eval_runtime": 9.6828,
|
| 388 |
+
"eval_samples_per_second": 369.935,
|
| 389 |
+
"eval_steps_per_second": 2.892,
|
| 390 |
+
"step": 6402
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 33.50515463917526,
|
| 394 |
+
"grad_norm": 0.0191043633967638,
|
| 395 |
+
"learning_rate": 4.871134020618557e-06,
|
| 396 |
+
"loss": 0.0082,
|
| 397 |
+
"step": 6500
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 34.0,
|
| 401 |
+
"eval_f1": 0.9422110552763819,
|
| 402 |
+
"eval_loss": 0.4114643335342407,
|
| 403 |
+
"eval_runtime": 9.6768,
|
| 404 |
+
"eval_samples_per_second": 370.163,
|
| 405 |
+
"eval_steps_per_second": 2.894,
|
| 406 |
+
"step": 6596
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 35.0,
|
| 410 |
+
"eval_f1": 0.9430485762144054,
|
| 411 |
+
"eval_loss": 0.42280834913253784,
|
| 412 |
+
"eval_runtime": 9.6847,
|
| 413 |
+
"eval_samples_per_second": 369.862,
|
| 414 |
+
"eval_steps_per_second": 2.891,
|
| 415 |
+
"step": 6790
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 36.0,
|
| 419 |
+
"eval_f1": 0.9441652707984366,
|
| 420 |
+
"eval_loss": 0.4165395200252533,
|
| 421 |
+
"eval_runtime": 9.6675,
|
| 422 |
+
"eval_samples_per_second": 370.522,
|
| 423 |
+
"eval_steps_per_second": 2.896,
|
| 424 |
+
"step": 6984
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 36.08247422680412,
|
| 428 |
+
"grad_norm": 1.23173987865448,
|
| 429 |
+
"learning_rate": 2.938144329896907e-06,
|
| 430 |
+
"loss": 0.0083,
|
| 431 |
+
"step": 7000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 37.0,
|
| 435 |
+
"eval_f1": 0.943606923506421,
|
| 436 |
+
"eval_loss": 0.4226440489292145,
|
| 437 |
+
"eval_runtime": 9.6782,
|
| 438 |
+
"eval_samples_per_second": 370.111,
|
| 439 |
+
"eval_steps_per_second": 2.893,
|
| 440 |
+
"step": 7178
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 38.0,
|
| 444 |
+
"eval_f1": 0.9430485762144054,
|
| 445 |
+
"eval_loss": 0.4262131452560425,
|
| 446 |
+
"eval_runtime": 9.6774,
|
| 447 |
+
"eval_samples_per_second": 370.141,
|
| 448 |
+
"eval_steps_per_second": 2.893,
|
| 449 |
+
"step": 7372
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 38.65979381443299,
|
| 453 |
+
"grad_norm": 1.7488667964935303,
|
| 454 |
+
"learning_rate": 1.0051546391752577e-06,
|
| 455 |
+
"loss": 0.0071,
|
| 456 |
+
"step": 7500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 39.0,
|
| 460 |
+
"eval_f1": 0.943606923506421,
|
| 461 |
+
"eval_loss": 0.42308905720710754,
|
| 462 |
+
"eval_runtime": 9.6502,
|
| 463 |
+
"eval_samples_per_second": 371.183,
|
| 464 |
+
"eval_steps_per_second": 2.901,
|
| 465 |
+
"step": 7566
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 40.0,
|
| 469 |
+
"eval_f1": 0.9438860971524288,
|
| 470 |
+
"eval_loss": 0.4251147508621216,
|
| 471 |
+
"eval_runtime": 9.6262,
|
| 472 |
+
"eval_samples_per_second": 372.109,
|
| 473 |
+
"eval_steps_per_second": 2.909,
|
| 474 |
+
"step": 7760
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 40.0,
|
| 478 |
+
"step": 7760,
|
| 479 |
+
"total_flos": 6.517582470540288e+16,
|
| 480 |
+
"train_loss": 0.04250985115152044,
|
| 481 |
+
"train_runtime": 8305.2138,
|
| 482 |
+
"train_samples_per_second": 119.303,
|
| 483 |
+
"train_steps_per_second": 0.934
|
| 484 |
+
}
|
| 485 |
+
],
|
| 486 |
+
"logging_steps": 500,
|
| 487 |
+
"max_steps": 7760,
|
| 488 |
+
"num_input_tokens_seen": 0,
|
| 489 |
+
"num_train_epochs": 40,
|
| 490 |
+
"save_steps": 500,
|
| 491 |
+
"stateful_callbacks": {
|
| 492 |
+
"TrainerControl": {
|
| 493 |
+
"args": {
|
| 494 |
+
"should_epoch_stop": false,
|
| 495 |
+
"should_evaluate": false,
|
| 496 |
+
"should_log": false,
|
| 497 |
+
"should_save": true,
|
| 498 |
+
"should_training_stop": true
|
| 499 |
+
},
|
| 500 |
+
"attributes": {}
|
| 501 |
+
}
|
| 502 |
+
},
|
| 503 |
+
"total_flos": 6.517582470540288e+16,
|
| 504 |
+
"train_batch_size": 128,
|
| 505 |
+
"trial_name": null,
|
| 506 |
+
"trial_params": null
|
| 507 |
+
}
|