paul
commited on
Commit
·
a8d845a
1
Parent(s):
e13ebbf
Training in progress, epoch 0
Browse files- all_results.json +8 -0
- pytorch_model.bin +1 -1
- runs/Jan22_04-00-47_teesta/events.out.tfevents.1674340255.teesta.849.2 +2 -2
- runs/Jan22_04-57-39_teesta/1674343666.9775045/events.out.tfevents.1674343666.teesta.849.5 +3 -0
- runs/Jan22_04-57-39_teesta/events.out.tfevents.1674343666.teesta.849.4 +3 -0
- train_results.json +8 -0
- trainer_state.json +337 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.89,
|
| 3 |
+
"total_flos": 7.312175696361554e+17,
|
| 4 |
+
"train_loss": 3.2800607363382976,
|
| 5 |
+
"train_runtime": 455.8097,
|
| 6 |
+
"train_samples_per_second": 75.821,
|
| 7 |
+
"train_steps_per_second": 0.263
|
| 8 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94555277
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4f1806e179beaad7cdb75e9106a6d82744a52105107664bcc66156693056b9f
|
| 3 |
size 94555277
|
runs/Jan22_04-00-47_teesta/events.out.tfevents.1674340255.teesta.849.2
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c00773d30d974424463f0c7e9445532ef68d78e80ed5d3651882896e49ecf347
|
| 3 |
+
size 15977
|
runs/Jan22_04-57-39_teesta/1674343666.9775045/events.out.tfevents.1674343666.teesta.849.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3db754efe4ef83347c633d65697aaa32fa0a66fc43515977ab09107c3d0526d8
|
| 3 |
+
size 4919
|
runs/Jan22_04-57-39_teesta/events.out.tfevents.1674343666.teesta.849.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dfe406c9b2bbe20def9c8d662376c5337c59224d6907775e69bcd81f6392df2
|
| 3 |
+
size 5034
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 19.89,
|
| 3 |
+
"total_flos": 7.312175696361554e+17,
|
| 4 |
+
"train_loss": 3.2800607363382976,
|
| 5 |
+
"train_runtime": 455.8097,
|
| 6 |
+
"train_samples_per_second": 75.821,
|
| 7 |
+
"train_steps_per_second": 0.263
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,337 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.19675925925925927,
|
| 3 |
+
"best_model_checkpoint": "microsoft-resnet-50-cartoon-face-recognition/checkpoint-24",
|
| 4 |
+
"epoch": 19.88888888888889,
|
| 5 |
+
"global_step": 120,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.89,
|
| 12 |
+
"eval_accuracy": 0.06712962962962964,
|
| 13 |
+
"eval_f1": 0.04268330700511537,
|
| 14 |
+
"eval_loss": 3.1718316078186035,
|
| 15 |
+
"eval_precision": 0.07750900471648707,
|
| 16 |
+
"eval_recall": 0.06712962962962964,
|
| 17 |
+
"eval_runtime": 6.9896,
|
| 18 |
+
"eval_samples_per_second": 61.806,
|
| 19 |
+
"eval_steps_per_second": 1.001,
|
| 20 |
+
"step": 6
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.59,
|
| 24 |
+
"learning_rate": 0.0001,
|
| 25 |
+
"loss": 3.409,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.89,
|
| 30 |
+
"eval_accuracy": 0.09722222222222222,
|
| 31 |
+
"eval_f1": 0.06941620132016908,
|
| 32 |
+
"eval_loss": 3.1434757709503174,
|
| 33 |
+
"eval_precision": 0.09483282105538404,
|
| 34 |
+
"eval_recall": 0.09722222222222222,
|
| 35 |
+
"eval_runtime": 6.3177,
|
| 36 |
+
"eval_samples_per_second": 68.379,
|
| 37 |
+
"eval_steps_per_second": 1.108,
|
| 38 |
+
"step": 12
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.89,
|
| 42 |
+
"eval_accuracy": 0.16666666666666666,
|
| 43 |
+
"eval_f1": 0.1157640285514969,
|
| 44 |
+
"eval_loss": 3.1100411415100098,
|
| 45 |
+
"eval_precision": 0.12231976324858271,
|
| 46 |
+
"eval_recall": 0.16666666666666666,
|
| 47 |
+
"eval_runtime": 5.8995,
|
| 48 |
+
"eval_samples_per_second": 73.226,
|
| 49 |
+
"eval_steps_per_second": 1.187,
|
| 50 |
+
"step": 18
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 3.3,
|
| 54 |
+
"learning_rate": 0.00011111111111111112,
|
| 55 |
+
"loss": 3.597,
|
| 56 |
+
"step": 20
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.89,
|
| 60 |
+
"eval_accuracy": 0.19675925925925927,
|
| 61 |
+
"eval_f1": 0.11625378991501253,
|
| 62 |
+
"eval_loss": 3.0767667293548584,
|
| 63 |
+
"eval_precision": 0.13583887289090224,
|
| 64 |
+
"eval_recall": 0.19675925925925927,
|
| 65 |
+
"eval_runtime": 5.9054,
|
| 66 |
+
"eval_samples_per_second": 73.153,
|
| 67 |
+
"eval_steps_per_second": 1.185,
|
| 68 |
+
"step": 24
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.89,
|
| 72 |
+
"learning_rate": 0.0001,
|
| 73 |
+
"loss": 3.2968,
|
| 74 |
+
"step": 30
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 4.89,
|
| 78 |
+
"eval_accuracy": 0.17592592592592593,
|
| 79 |
+
"eval_f1": 0.08794959812293887,
|
| 80 |
+
"eval_loss": 3.051513195037842,
|
| 81 |
+
"eval_precision": 0.08687890109673733,
|
| 82 |
+
"eval_recall": 0.17592592592592593,
|
| 83 |
+
"eval_runtime": 5.8218,
|
| 84 |
+
"eval_samples_per_second": 74.204,
|
| 85 |
+
"eval_steps_per_second": 1.202,
|
| 86 |
+
"step": 30
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.89,
|
| 90 |
+
"eval_accuracy": 0.1712962962962963,
|
| 91 |
+
"eval_f1": 0.06999759781046332,
|
| 92 |
+
"eval_loss": 3.0226213932037354,
|
| 93 |
+
"eval_precision": 0.0456331710295125,
|
| 94 |
+
"eval_recall": 0.1712962962962963,
|
| 95 |
+
"eval_runtime": 5.7818,
|
| 96 |
+
"eval_samples_per_second": 74.718,
|
| 97 |
+
"eval_steps_per_second": 1.211,
|
| 98 |
+
"step": 36
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.59,
|
| 102 |
+
"learning_rate": 8.888888888888888e-05,
|
| 103 |
+
"loss": 3.4662,
|
| 104 |
+
"step": 40
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 6.89,
|
| 108 |
+
"eval_accuracy": 0.16666666666666666,
|
| 109 |
+
"eval_f1": 0.07065656451437614,
|
| 110 |
+
"eval_loss": 2.9997007846832275,
|
| 111 |
+
"eval_precision": 0.04987179172442097,
|
| 112 |
+
"eval_recall": 0.16666666666666666,
|
| 113 |
+
"eval_runtime": 5.8712,
|
| 114 |
+
"eval_samples_per_second": 73.579,
|
| 115 |
+
"eval_steps_per_second": 1.192,
|
| 116 |
+
"step": 42
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.89,
|
| 120 |
+
"eval_accuracy": 0.1550925925925926,
|
| 121 |
+
"eval_f1": 0.06279659825962769,
|
| 122 |
+
"eval_loss": 2.977167844772339,
|
| 123 |
+
"eval_precision": 0.046044346719881876,
|
| 124 |
+
"eval_recall": 0.1550925925925926,
|
| 125 |
+
"eval_runtime": 5.7878,
|
| 126 |
+
"eval_samples_per_second": 74.64,
|
| 127 |
+
"eval_steps_per_second": 1.209,
|
| 128 |
+
"step": 48
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.3,
|
| 132 |
+
"learning_rate": 7.777777777777778e-05,
|
| 133 |
+
"loss": 3.4141,
|
| 134 |
+
"step": 50
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.89,
|
| 138 |
+
"eval_accuracy": 0.18518518518518517,
|
| 139 |
+
"eval_f1": 0.08918606274115107,
|
| 140 |
+
"eval_loss": 2.9533445835113525,
|
| 141 |
+
"eval_precision": 0.16404070934618162,
|
| 142 |
+
"eval_recall": 0.18518518518518517,
|
| 143 |
+
"eval_runtime": 6.9368,
|
| 144 |
+
"eval_samples_per_second": 62.277,
|
| 145 |
+
"eval_steps_per_second": 1.009,
|
| 146 |
+
"step": 54
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 9.89,
|
| 150 |
+
"learning_rate": 6.666666666666667e-05,
|
| 151 |
+
"loss": 3.1376,
|
| 152 |
+
"step": 60
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 9.89,
|
| 156 |
+
"eval_accuracy": 0.16666666666666666,
|
| 157 |
+
"eval_f1": 0.07419287680822054,
|
| 158 |
+
"eval_loss": 2.931124448776245,
|
| 159 |
+
"eval_precision": 0.08951358417023512,
|
| 160 |
+
"eval_recall": 0.16666666666666666,
|
| 161 |
+
"eval_runtime": 5.8186,
|
| 162 |
+
"eval_samples_per_second": 74.244,
|
| 163 |
+
"eval_steps_per_second": 1.203,
|
| 164 |
+
"step": 60
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 10.89,
|
| 168 |
+
"eval_accuracy": 0.16435185185185186,
|
| 169 |
+
"eval_f1": 0.0724480953675622,
|
| 170 |
+
"eval_loss": 2.920067310333252,
|
| 171 |
+
"eval_precision": 0.08232943904512993,
|
| 172 |
+
"eval_recall": 0.16435185185185186,
|
| 173 |
+
"eval_runtime": 5.8821,
|
| 174 |
+
"eval_samples_per_second": 73.444,
|
| 175 |
+
"eval_steps_per_second": 1.19,
|
| 176 |
+
"step": 66
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.59,
|
| 180 |
+
"learning_rate": 5.555555555555556e-05,
|
| 181 |
+
"loss": 3.3113,
|
| 182 |
+
"step": 70
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 11.89,
|
| 186 |
+
"eval_accuracy": 0.16435185185185186,
|
| 187 |
+
"eval_f1": 0.07315703439667075,
|
| 188 |
+
"eval_loss": 2.896663188934326,
|
| 189 |
+
"eval_precision": 0.0995273854967043,
|
| 190 |
+
"eval_recall": 0.16435185185185186,
|
| 191 |
+
"eval_runtime": 5.8475,
|
| 192 |
+
"eval_samples_per_second": 73.877,
|
| 193 |
+
"eval_steps_per_second": 1.197,
|
| 194 |
+
"step": 72
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 12.89,
|
| 198 |
+
"eval_accuracy": 0.1574074074074074,
|
| 199 |
+
"eval_f1": 0.06788189816821627,
|
| 200 |
+
"eval_loss": 2.8926467895507812,
|
| 201 |
+
"eval_precision": 0.07378815753932359,
|
| 202 |
+
"eval_recall": 0.1574074074074074,
|
| 203 |
+
"eval_runtime": 6.731,
|
| 204 |
+
"eval_samples_per_second": 64.181,
|
| 205 |
+
"eval_steps_per_second": 1.04,
|
| 206 |
+
"step": 78
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 13.3,
|
| 210 |
+
"learning_rate": 4.444444444444444e-05,
|
| 211 |
+
"loss": 3.2872,
|
| 212 |
+
"step": 80
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 13.89,
|
| 216 |
+
"eval_accuracy": 0.1712962962962963,
|
| 217 |
+
"eval_f1": 0.07606979068720418,
|
| 218 |
+
"eval_loss": 2.8844218254089355,
|
| 219 |
+
"eval_precision": 0.0804587704274602,
|
| 220 |
+
"eval_recall": 0.1712962962962963,
|
| 221 |
+
"eval_runtime": 5.7658,
|
| 222 |
+
"eval_samples_per_second": 74.924,
|
| 223 |
+
"eval_steps_per_second": 1.214,
|
| 224 |
+
"step": 84
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 14.89,
|
| 228 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 229 |
+
"loss": 3.0305,
|
| 230 |
+
"step": 90
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 14.89,
|
| 234 |
+
"eval_accuracy": 0.1712962962962963,
|
| 235 |
+
"eval_f1": 0.07456109408196694,
|
| 236 |
+
"eval_loss": 2.8605401515960693,
|
| 237 |
+
"eval_precision": 0.09364712421465295,
|
| 238 |
+
"eval_recall": 0.1712962962962963,
|
| 239 |
+
"eval_runtime": 5.8764,
|
| 240 |
+
"eval_samples_per_second": 73.515,
|
| 241 |
+
"eval_steps_per_second": 1.191,
|
| 242 |
+
"step": 90
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 15.89,
|
| 246 |
+
"eval_accuracy": 0.17592592592592593,
|
| 247 |
+
"eval_f1": 0.077154753687655,
|
| 248 |
+
"eval_loss": 2.8563218116760254,
|
| 249 |
+
"eval_precision": 0.09599160283239885,
|
| 250 |
+
"eval_recall": 0.17592592592592593,
|
| 251 |
+
"eval_runtime": 5.8036,
|
| 252 |
+
"eval_samples_per_second": 74.436,
|
| 253 |
+
"eval_steps_per_second": 1.206,
|
| 254 |
+
"step": 96
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 16.59,
|
| 258 |
+
"learning_rate": 2.222222222222222e-05,
|
| 259 |
+
"loss": 3.2263,
|
| 260 |
+
"step": 100
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 16.89,
|
| 264 |
+
"eval_accuracy": 0.1712962962962963,
|
| 265 |
+
"eval_f1": 0.07532319701759846,
|
| 266 |
+
"eval_loss": 2.8487489223480225,
|
| 267 |
+
"eval_precision": 0.10121344883941782,
|
| 268 |
+
"eval_recall": 0.1712962962962963,
|
| 269 |
+
"eval_runtime": 5.766,
|
| 270 |
+
"eval_samples_per_second": 74.921,
|
| 271 |
+
"eval_steps_per_second": 1.214,
|
| 272 |
+
"step": 102
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 17.89,
|
| 276 |
+
"eval_accuracy": 0.1712962962962963,
|
| 277 |
+
"eval_f1": 0.07721457778893034,
|
| 278 |
+
"eval_loss": 2.8424181938171387,
|
| 279 |
+
"eval_precision": 0.12103390482470601,
|
| 280 |
+
"eval_recall": 0.1712962962962963,
|
| 281 |
+
"eval_runtime": 5.8577,
|
| 282 |
+
"eval_samples_per_second": 73.749,
|
| 283 |
+
"eval_steps_per_second": 1.195,
|
| 284 |
+
"step": 108
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 18.3,
|
| 288 |
+
"learning_rate": 1.111111111111111e-05,
|
| 289 |
+
"loss": 3.1927,
|
| 290 |
+
"step": 110
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 18.89,
|
| 294 |
+
"eval_accuracy": 0.1736111111111111,
|
| 295 |
+
"eval_f1": 0.07100199262795664,
|
| 296 |
+
"eval_loss": 2.837003707885742,
|
| 297 |
+
"eval_precision": 0.05610008615248136,
|
| 298 |
+
"eval_recall": 0.1736111111111111,
|
| 299 |
+
"eval_runtime": 5.7707,
|
| 300 |
+
"eval_samples_per_second": 74.861,
|
| 301 |
+
"eval_steps_per_second": 1.213,
|
| 302 |
+
"step": 114
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 19.89,
|
| 306 |
+
"learning_rate": 0.0,
|
| 307 |
+
"loss": 2.992,
|
| 308 |
+
"step": 120
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 19.89,
|
| 312 |
+
"eval_accuracy": 0.18055555555555555,
|
| 313 |
+
"eval_f1": 0.08808104613908821,
|
| 314 |
+
"eval_loss": 2.849083423614502,
|
| 315 |
+
"eval_precision": 0.15482731189307494,
|
| 316 |
+
"eval_recall": 0.18055555555555555,
|
| 317 |
+
"eval_runtime": 5.8109,
|
| 318 |
+
"eval_samples_per_second": 74.343,
|
| 319 |
+
"eval_steps_per_second": 1.205,
|
| 320 |
+
"step": 120
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 19.89,
|
| 324 |
+
"step": 120,
|
| 325 |
+
"total_flos": 7.312175696361554e+17,
|
| 326 |
+
"train_loss": 3.2800607363382976,
|
| 327 |
+
"train_runtime": 455.8097,
|
| 328 |
+
"train_samples_per_second": 75.821,
|
| 329 |
+
"train_steps_per_second": 0.263
|
| 330 |
+
}
|
| 331 |
+
],
|
| 332 |
+
"max_steps": 120,
|
| 333 |
+
"num_train_epochs": 20,
|
| 334 |
+
"total_flos": 7.312175696361554e+17,
|
| 335 |
+
"trial_name": null,
|
| 336 |
+
"trial_params": null
|
| 337 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3131
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b97ca6549aca4df2049e3610e0afe26dd44655a56d136daecbb58988b714c26f
|
| 3 |
size 3131
|