Training in progress, epoch 7
Browse files- all_results.json +21 -0
- confusion_matrix.png +0 -0
- logs/events.out.tfevents.1740978511.mac.lan.55690.79 +3 -0
- logs/events.out.tfevents.1741012110.mac.lan.55690.100 +3 -0
- model.safetensors +1 -1
- test_results.json +16 -0
- train_results.json +8 -0
- trainer_state.json +363 -0
all_results.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"test_accuracy": 0.4205607476635514,
|
| 4 |
+
"test_f1": 0.3758792694421824,
|
| 5 |
+
"test_f1_class_0": 0.5405405405405406,
|
| 6 |
+
"test_f1_class_1": 0.09090909090909091,
|
| 7 |
+
"test_f1_class_2": 0.1,
|
| 8 |
+
"test_f1_class_3": 0.21052631578947367,
|
| 9 |
+
"test_f1_class_4": 0.5979381443298969,
|
| 10 |
+
"test_loss": 1.3978204727172852,
|
| 11 |
+
"test_precision": 0.37640186915887847,
|
| 12 |
+
"test_recall": 0.4205607476635514,
|
| 13 |
+
"test_runtime": 5.415,
|
| 14 |
+
"test_samples_per_second": 19.76,
|
| 15 |
+
"test_steps_per_second": 4.986,
|
| 16 |
+
"total_flos": 873039758653440.0,
|
| 17 |
+
"train_loss": 1.1469601062228003,
|
| 18 |
+
"train_runtime": 498.0507,
|
| 19 |
+
"train_samples_per_second": 8.573,
|
| 20 |
+
"train_steps_per_second": 2.148
|
| 21 |
+
}
|
confusion_matrix.png
ADDED
|
logs/events.out.tfevents.1740978511.mac.lan.55690.79
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f5aa64134ce6e1805f763e5513d5887aab92a4764784f5d3e882e293c8af8b7
|
| 3 |
+
size 830
|
logs/events.out.tfevents.1741012110.mac.lan.55690.100
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d44f357d7b7a5d8b33f525d2c718ceef7018660d37b2a56bc32a2b8178801b0
|
| 3 |
+
size 7807
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 598449012
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1afa1babf84f54ac357610bb13f7de51551aee7d830ea84dd7f41924ced93373
|
| 3 |
size 598449012
|
test_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"test_accuracy": 0.4205607476635514,
|
| 4 |
+
"test_f1": 0.3758792694421824,
|
| 5 |
+
"test_f1_class_0": 0.5405405405405406,
|
| 6 |
+
"test_f1_class_1": 0.09090909090909091,
|
| 7 |
+
"test_f1_class_2": 0.1,
|
| 8 |
+
"test_f1_class_3": 0.21052631578947367,
|
| 9 |
+
"test_f1_class_4": 0.5979381443298969,
|
| 10 |
+
"test_loss": 1.3978204727172852,
|
| 11 |
+
"test_precision": 0.37640186915887847,
|
| 12 |
+
"test_recall": 0.4205607476635514,
|
| 13 |
+
"test_runtime": 5.415,
|
| 14 |
+
"test_samples_per_second": 19.76,
|
| 15 |
+
"test_steps_per_second": 4.986
|
| 16 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"total_flos": 873039758653440.0,
|
| 4 |
+
"train_loss": 1.1469601062228003,
|
| 5 |
+
"train_runtime": 498.0507,
|
| 6 |
+
"train_samples_per_second": 8.573,
|
| 7 |
+
"train_steps_per_second": 2.148
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,363 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3978204727172852,
|
| 3 |
+
"best_model_checkpoint": "user_models/user_50149/checkpoint-321",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 642,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.19626168224299065,
|
| 13 |
+
"grad_norm": 18.907575607299805,
|
| 14 |
+
"learning_rate": 3.925233644859814e-06,
|
| 15 |
+
"loss": 1.6416,
|
| 16 |
+
"step": 21
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3925233644859813,
|
| 20 |
+
"grad_norm": 18.843624114990234,
|
| 21 |
+
"learning_rate": 7.850467289719627e-06,
|
| 22 |
+
"loss": 1.6233,
|
| 23 |
+
"step": 42
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5887850467289719,
|
| 27 |
+
"grad_norm": 10.201820373535156,
|
| 28 |
+
"learning_rate": 1.177570093457944e-05,
|
| 29 |
+
"loss": 1.6652,
|
| 30 |
+
"step": 63
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7850467289719626,
|
| 34 |
+
"grad_norm": 12.853364944458008,
|
| 35 |
+
"learning_rate": 1.5700934579439254e-05,
|
| 36 |
+
"loss": 1.582,
|
| 37 |
+
"step": 84
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9813084112149533,
|
| 41 |
+
"grad_norm": 14.50940227508545,
|
| 42 |
+
"learning_rate": 1.9626168224299065e-05,
|
| 43 |
+
"loss": 1.6005,
|
| 44 |
+
"step": 105
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_accuracy": 0.3177570093457944,
|
| 49 |
+
"eval_f1": 0.2863669085995949,
|
| 50 |
+
"eval_f1_class_0": 0.41935483870967744,
|
| 51 |
+
"eval_f1_class_1": 0.21052631578947367,
|
| 52 |
+
"eval_f1_class_2": 0.14285714285714285,
|
| 53 |
+
"eval_f1_class_3": 0.0,
|
| 54 |
+
"eval_f1_class_4": 0.4411764705882353,
|
| 55 |
+
"eval_loss": 1.538644790649414,
|
| 56 |
+
"eval_precision": 0.2783041645663615,
|
| 57 |
+
"eval_recall": 0.3177570093457944,
|
| 58 |
+
"eval_runtime": 5.1789,
|
| 59 |
+
"eval_samples_per_second": 20.661,
|
| 60 |
+
"eval_steps_per_second": 5.213,
|
| 61 |
+
"step": 107
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.1775700934579438,
|
| 65 |
+
"grad_norm": 8.494335174560547,
|
| 66 |
+
"learning_rate": 1.998079628167323e-05,
|
| 67 |
+
"loss": 1.4077,
|
| 68 |
+
"step": 126
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.3738317757009346,
|
| 72 |
+
"grad_norm": 11.252021789550781,
|
| 73 |
+
"learning_rate": 1.9914980058500016e-05,
|
| 74 |
+
"loss": 1.6239,
|
| 75 |
+
"step": 147
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.5700934579439252,
|
| 79 |
+
"grad_norm": 11.045428276062012,
|
| 80 |
+
"learning_rate": 1.9802647259292876e-05,
|
| 81 |
+
"loss": 1.5567,
|
| 82 |
+
"step": 168
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.7663551401869158,
|
| 86 |
+
"grad_norm": 7.688369274139404,
|
| 87 |
+
"learning_rate": 1.9644324898444645e-05,
|
| 88 |
+
"loss": 1.3852,
|
| 89 |
+
"step": 189
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 1.9626168224299065,
|
| 93 |
+
"grad_norm": 7.697967529296875,
|
| 94 |
+
"learning_rate": 1.9440755752450364e-05,
|
| 95 |
+
"loss": 1.5645,
|
| 96 |
+
"step": 210
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 2.0,
|
| 100 |
+
"eval_accuracy": 0.411214953271028,
|
| 101 |
+
"eval_f1": 0.29006813896052763,
|
| 102 |
+
"eval_f1_class_0": 0.4878048780487805,
|
| 103 |
+
"eval_f1_class_1": 0.0,
|
| 104 |
+
"eval_f1_class_2": 0.0,
|
| 105 |
+
"eval_f1_class_3": 0.0,
|
| 106 |
+
"eval_f1_class_4": 0.5619834710743802,
|
| 107 |
+
"eval_loss": 1.4633408784866333,
|
| 108 |
+
"eval_precision": 0.23809523809523808,
|
| 109 |
+
"eval_recall": 0.411214953271028,
|
| 110 |
+
"eval_runtime": 5.2459,
|
| 111 |
+
"eval_samples_per_second": 20.397,
|
| 112 |
+
"eval_steps_per_second": 5.147,
|
| 113 |
+
"step": 214
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 2.1588785046728973,
|
| 117 |
+
"grad_norm": 7.654632091522217,
|
| 118 |
+
"learning_rate": 1.9192894875137864e-05,
|
| 119 |
+
"loss": 1.3278,
|
| 120 |
+
"step": 231
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.3551401869158877,
|
| 124 |
+
"grad_norm": 12.362059593200684,
|
| 125 |
+
"learning_rate": 1.8901905116989687e-05,
|
| 126 |
+
"loss": 1.386,
|
| 127 |
+
"step": 252
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 2.5514018691588785,
|
| 131 |
+
"grad_norm": 14.643189430236816,
|
| 132 |
+
"learning_rate": 1.8569151669577584e-05,
|
| 133 |
+
"loss": 1.1659,
|
| 134 |
+
"step": 273
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.7476635514018692,
|
| 138 |
+
"grad_norm": 12.226801872253418,
|
| 139 |
+
"learning_rate": 1.8196195660704713e-05,
|
| 140 |
+
"loss": 1.3803,
|
| 141 |
+
"step": 294
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.94392523364486,
|
| 145 |
+
"grad_norm": 10.002374649047852,
|
| 146 |
+
"learning_rate": 1.7784786830304163e-05,
|
| 147 |
+
"loss": 1.4339,
|
| 148 |
+
"step": 315
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.0,
|
| 152 |
+
"eval_accuracy": 0.4205607476635514,
|
| 153 |
+
"eval_f1": 0.3758792694421824,
|
| 154 |
+
"eval_f1_class_0": 0.5405405405405406,
|
| 155 |
+
"eval_f1_class_1": 0.09090909090909091,
|
| 156 |
+
"eval_f1_class_2": 0.1,
|
| 157 |
+
"eval_f1_class_3": 0.21052631578947367,
|
| 158 |
+
"eval_f1_class_4": 0.5979381443298969,
|
| 159 |
+
"eval_loss": 1.3978204727172852,
|
| 160 |
+
"eval_precision": 0.37640186915887847,
|
| 161 |
+
"eval_recall": 0.4205607476635514,
|
| 162 |
+
"eval_runtime": 5.2114,
|
| 163 |
+
"eval_samples_per_second": 20.532,
|
| 164 |
+
"eval_steps_per_second": 5.181,
|
| 165 |
+
"step": 321
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 3.1401869158878504,
|
| 169 |
+
"grad_norm": 10.777024269104004,
|
| 170 |
+
"learning_rate": 1.7336855321455126e-05,
|
| 171 |
+
"loss": 1.0956,
|
| 172 |
+
"step": 336
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 3.336448598130841,
|
| 176 |
+
"grad_norm": 36.37456512451172,
|
| 177 |
+
"learning_rate": 1.6854502625029642e-05,
|
| 178 |
+
"loss": 1.0556,
|
| 179 |
+
"step": 357
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.5327102803738315,
|
| 183 |
+
"grad_norm": 12.113136291503906,
|
| 184 |
+
"learning_rate": 1.6339991720453395e-05,
|
| 185 |
+
"loss": 0.9665,
|
| 186 |
+
"step": 378
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 3.7289719626168223,
|
| 190 |
+
"grad_norm": 24.207178115844727,
|
| 191 |
+
"learning_rate": 1.5795736458835698e-05,
|
| 192 |
+
"loss": 0.9452,
|
| 193 |
+
"step": 399
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 3.925233644859813,
|
| 197 |
+
"grad_norm": 11.722213745117188,
|
| 198 |
+
"learning_rate": 1.5224290238278161e-05,
|
| 199 |
+
"loss": 1.0045,
|
| 200 |
+
"step": 420
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 4.0,
|
| 204 |
+
"eval_accuracy": 0.3644859813084112,
|
| 205 |
+
"eval_f1": 0.3516195372033098,
|
| 206 |
+
"eval_f1_class_0": 0.42424242424242425,
|
| 207 |
+
"eval_f1_class_1": 0.3137254901960784,
|
| 208 |
+
"eval_f1_class_2": 0.2926829268292683,
|
| 209 |
+
"eval_f1_class_3": 0.0,
|
| 210 |
+
"eval_f1_class_4": 0.5217391304347826,
|
| 211 |
+
"eval_loss": 1.707943320274353,
|
| 212 |
+
"eval_precision": 0.3755250590530964,
|
| 213 |
+
"eval_recall": 0.3644859813084112,
|
| 214 |
+
"eval_runtime": 5.2821,
|
| 215 |
+
"eval_samples_per_second": 20.257,
|
| 216 |
+
"eval_steps_per_second": 5.112,
|
| 217 |
+
"step": 428
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 4.121495327102804,
|
| 221 |
+
"grad_norm": 12.007721900939941,
|
| 222 |
+
"learning_rate": 1.4628334024492366e-05,
|
| 223 |
+
"loss": 0.9364,
|
| 224 |
+
"step": 441
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.317757009345795,
|
| 228 |
+
"grad_norm": 15.63640022277832,
|
| 229 |
+
"learning_rate": 1.4010663772928339e-05,
|
| 230 |
+
"loss": 0.8197,
|
| 231 |
+
"step": 462
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 4.5140186915887845,
|
| 235 |
+
"grad_norm": 48.92936706542969,
|
| 236 |
+
"learning_rate": 1.3374177311423481e-05,
|
| 237 |
+
"loss": 0.6792,
|
| 238 |
+
"step": 483
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 4.710280373831775,
|
| 242 |
+
"grad_norm": 13.728958129882812,
|
| 243 |
+
"learning_rate": 1.2721860744912588e-05,
|
| 244 |
+
"loss": 1.0839,
|
| 245 |
+
"step": 504
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 4.906542056074766,
|
| 249 |
+
"grad_norm": 30.606203079223633,
|
| 250 |
+
"learning_rate": 1.2056774445981922e-05,
|
| 251 |
+
"loss": 0.6207,
|
| 252 |
+
"step": 525
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.0,
|
| 256 |
+
"eval_accuracy": 0.40186915887850466,
|
| 257 |
+
"eval_f1": 0.40351674467827703,
|
| 258 |
+
"eval_f1_class_0": 0.5454545454545454,
|
| 259 |
+
"eval_f1_class_1": 0.09523809523809523,
|
| 260 |
+
"eval_f1_class_2": 0.37209302325581395,
|
| 261 |
+
"eval_f1_class_3": 0.2857142857142857,
|
| 262 |
+
"eval_f1_class_4": 0.5263157894736842,
|
| 263 |
+
"eval_loss": 2.141951084136963,
|
| 264 |
+
"eval_precision": 0.46968927246613995,
|
| 265 |
+
"eval_recall": 0.40186915887850466,
|
| 266 |
+
"eval_runtime": 5.2359,
|
| 267 |
+
"eval_samples_per_second": 20.436,
|
| 268 |
+
"eval_steps_per_second": 5.157,
|
| 269 |
+
"step": 535
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 5.102803738317757,
|
| 273 |
+
"grad_norm": 3.1776702404022217,
|
| 274 |
+
"learning_rate": 1.1382038696993195e-05,
|
| 275 |
+
"loss": 0.6466,
|
| 276 |
+
"step": 546
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 5.299065420560748,
|
| 280 |
+
"grad_norm": 5.055131912231445,
|
| 281 |
+
"learning_rate": 1.0700819051138189e-05,
|
| 282 |
+
"loss": 0.4934,
|
| 283 |
+
"step": 567
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 5.4953271028037385,
|
| 287 |
+
"grad_norm": 18.38237190246582,
|
| 288 |
+
"learning_rate": 1.0016311481103214e-05,
|
| 289 |
+
"loss": 0.705,
|
| 290 |
+
"step": 588
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 5.691588785046729,
|
| 294 |
+
"grad_norm": 54.925758361816406,
|
| 295 |
+
"learning_rate": 9.331727385019119e-06,
|
| 296 |
+
"loss": 0.5271,
|
| 297 |
+
"step": 609
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 5.88785046728972,
|
| 301 |
+
"grad_norm": 18.593154907226562,
|
| 302 |
+
"learning_rate": 8.650278520042169e-06,
|
| 303 |
+
"loss": 0.7996,
|
| 304 |
+
"step": 630
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 6.0,
|
| 308 |
+
"eval_accuracy": 0.411214953271028,
|
| 309 |
+
"eval_f1": 0.4151496271122439,
|
| 310 |
+
"eval_f1_class_0": 0.47619047619047616,
|
| 311 |
+
"eval_f1_class_1": 0.32,
|
| 312 |
+
"eval_f1_class_2": 0.37037037037037035,
|
| 313 |
+
"eval_f1_class_3": 0.2727272727272727,
|
| 314 |
+
"eval_f1_class_4": 0.509090909090909,
|
| 315 |
+
"eval_loss": 2.4410297870635986,
|
| 316 |
+
"eval_precision": 0.5027358415208882,
|
| 317 |
+
"eval_recall": 0.411214953271028,
|
| 318 |
+
"eval_runtime": 5.2882,
|
| 319 |
+
"eval_samples_per_second": 20.234,
|
| 320 |
+
"eval_steps_per_second": 5.106,
|
| 321 |
+
"step": 642
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 6.0,
|
| 325 |
+
"step": 642,
|
| 326 |
+
"total_flos": 873039758653440.0,
|
| 327 |
+
"train_loss": 1.1469601062228003,
|
| 328 |
+
"train_runtime": 498.0507,
|
| 329 |
+
"train_samples_per_second": 8.573,
|
| 330 |
+
"train_steps_per_second": 2.148
|
| 331 |
+
}
|
| 332 |
+
],
|
| 333 |
+
"logging_steps": 21,
|
| 334 |
+
"max_steps": 1070,
|
| 335 |
+
"num_input_tokens_seen": 0,
|
| 336 |
+
"num_train_epochs": 10,
|
| 337 |
+
"save_steps": 500,
|
| 338 |
+
"stateful_callbacks": {
|
| 339 |
+
"EarlyStoppingCallback": {
|
| 340 |
+
"args": {
|
| 341 |
+
"early_stopping_patience": 3,
|
| 342 |
+
"early_stopping_threshold": 0.02
|
| 343 |
+
},
|
| 344 |
+
"attributes": {
|
| 345 |
+
"early_stopping_patience_counter": 3
|
| 346 |
+
}
|
| 347 |
+
},
|
| 348 |
+
"TrainerControl": {
|
| 349 |
+
"args": {
|
| 350 |
+
"should_epoch_stop": false,
|
| 351 |
+
"should_evaluate": false,
|
| 352 |
+
"should_log": false,
|
| 353 |
+
"should_save": true,
|
| 354 |
+
"should_training_stop": true
|
| 355 |
+
},
|
| 356 |
+
"attributes": {}
|
| 357 |
+
}
|
| 358 |
+
},
|
| 359 |
+
"total_flos": 873039758653440.0,
|
| 360 |
+
"train_batch_size": 4,
|
| 361 |
+
"trial_name": null,
|
| 362 |
+
"trial_params": null
|
| 363 |
+
}
|