Training in progress, epoch 0
Browse files- all_results.json +5 -5
- config.json +4 -20
- model.safetensors +2 -2
- runs/Jul02_18-49-41_c6d9a0630dcb/events.out.tfevents.1719946836.c6d9a0630dcb.4133.1 +2 -2
- runs/Jul02_19-27-25_c6d9a0630dcb/events.out.tfevents.1719948503.c6d9a0630dcb.4133.2 +3 -0
- test_results.json +5 -5
- trainer_state.json +119 -75
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.5,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second": 3.
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.5,
|
| 3 |
+
"eval_accuracy": 0.7870967741935484,
|
| 4 |
+
"eval_loss": 0.6657504439353943,
|
| 5 |
+
"eval_runtime": 42.1495,
|
| 6 |
+
"eval_samples_per_second": 3.677,
|
| 7 |
+
"eval_steps_per_second": 1.851
|
| 8 |
}
|
config.json
CHANGED
|
@@ -12,31 +12,15 @@
|
|
| 12 |
"hidden_dropout_prob": 0.0,
|
| 13 |
"hidden_size": 768,
|
| 14 |
"id2label": {
|
| 15 |
-
"0": "
|
| 16 |
-
"1": "
|
| 17 |
-
"2": "Archery",
|
| 18 |
-
"3": "BabyCrawling",
|
| 19 |
-
"4": "BalanceBeam",
|
| 20 |
-
"5": "BandMarching",
|
| 21 |
-
"6": "BaseballPitch",
|
| 22 |
-
"7": "Basketball",
|
| 23 |
-
"8": "BasketballDunk",
|
| 24 |
-
"9": "BenchPress"
|
| 25 |
},
|
| 26 |
"image_size": 224,
|
| 27 |
"initializer_range": 0.02,
|
| 28 |
"intermediate_size": 3072,
|
| 29 |
"label2id": {
|
| 30 |
-
"
|
| 31 |
-
"
|
| 32 |
-
"Archery": 2,
|
| 33 |
-
"BabyCrawling": 3,
|
| 34 |
-
"BalanceBeam": 4,
|
| 35 |
-
"BandMarching": 5,
|
| 36 |
-
"BaseballPitch": 6,
|
| 37 |
-
"Basketball": 7,
|
| 38 |
-
"BasketballDunk": 8,
|
| 39 |
-
"BenchPress": 9
|
| 40 |
},
|
| 41 |
"layer_norm_eps": 1e-12,
|
| 42 |
"model_type": "videomae",
|
|
|
|
| 12 |
"hidden_dropout_prob": 0.0,
|
| 13 |
"hidden_size": 768,
|
| 14 |
"id2label": {
|
| 15 |
+
"0": "Not Risky",
|
| 16 |
+
"1": "Risky"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
},
|
| 18 |
"image_size": 224,
|
| 19 |
"initializer_range": 0.02,
|
| 20 |
"intermediate_size": 3072,
|
| 21 |
"label2id": {
|
| 22 |
+
"Not Risky": 0,
|
| 23 |
+
"Risky": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
},
|
| 25 |
"layer_norm_eps": 1e-12,
|
| 26 |
"model_type": "videomae",
|
model.safetensors
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:aeee4826e549aec20a78f2a13875b8392b38e5eaf3d7715ea079ab583283122d
|
| 3 |
+
size 344937368
|
runs/Jul02_18-49-41_c6d9a0630dcb/events.out.tfevents.1719946836.c6d9a0630dcb.4133.1
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 sha256:6fee780fc4d286169c1067496efa80e90ea0c8ae16d7a6bb146a138fca73a1a1
|
| 3 |
+
size 734
|
runs/Jul02_19-27-25_c6d9a0630dcb/events.out.tfevents.1719948503.c6d9a0630dcb.4133.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8145403af70de9dd892277faa752f7973749eb9a0b1c8d4495fd6a53fb8d72e4
|
| 3 |
+
size 5843
|
test_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.5,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second": 3.
|
| 7 |
-
"eval_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.5,
|
| 3 |
+
"eval_accuracy": 0.7870967741935484,
|
| 4 |
+
"eval_loss": 0.6657504439353943,
|
| 5 |
+
"eval_runtime": 42.1495,
|
| 6 |
+
"eval_samples_per_second": 3.677,
|
| 7 |
+
"eval_steps_per_second": 1.851
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-300",
|
| 4 |
"epoch": 1.5,
|
| 5 |
"eval_steps": 500,
|
|
@@ -9,236 +9,280 @@
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
|
|
|
| 13 |
"learning_rate": 1.6666666666666667e-05,
|
| 14 |
-
"loss": 2.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
|
|
|
| 19 |
"learning_rate": 3.3333333333333335e-05,
|
| 20 |
-
"loss": 2.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.1,
|
|
|
|
| 25 |
"learning_rate": 5e-05,
|
| 26 |
-
"loss": 2.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
|
|
|
| 31 |
"learning_rate": 4.814814814814815e-05,
|
| 32 |
-
"loss": 2.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
|
|
|
| 37 |
"learning_rate": 4.62962962962963e-05,
|
| 38 |
-
"loss": 2.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.2,
|
|
|
|
| 43 |
"learning_rate": 4.4444444444444447e-05,
|
| 44 |
-
"loss": 2.
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch": 0.
|
|
|
|
| 49 |
"learning_rate": 4.259259259259259e-05,
|
| 50 |
-
"loss": 2.
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
|
|
|
| 55 |
"learning_rate": 4.074074074074074e-05,
|
| 56 |
-
"loss": 1.
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.3,
|
|
|
|
| 61 |
"learning_rate": 3.888888888888889e-05,
|
| 62 |
-
"loss": 1.
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch": 0.
|
|
|
|
| 67 |
"learning_rate": 3.7037037037037037e-05,
|
| 68 |
-
"loss": 1.
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
-
"epoch": 0.
|
|
|
|
| 73 |
"learning_rate": 3.518518518518519e-05,
|
| 74 |
-
"loss": 1.
|
| 75 |
"step": 110
|
| 76 |
},
|
| 77 |
{
|
| 78 |
"epoch": 0.4,
|
|
|
|
| 79 |
"learning_rate": 3.3333333333333335e-05,
|
| 80 |
-
"loss": 1.
|
| 81 |
"step": 120
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch": 0.
|
|
|
|
| 85 |
"learning_rate": 3.148148148148148e-05,
|
| 86 |
-
"loss": 1.
|
| 87 |
"step": 130
|
| 88 |
},
|
| 89 |
{
|
| 90 |
-
"epoch": 0.
|
|
|
|
| 91 |
"learning_rate": 2.962962962962963e-05,
|
| 92 |
-
"loss": 1.
|
| 93 |
"step": 140
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.5,
|
|
|
|
| 97 |
"learning_rate": 2.777777777777778e-05,
|
| 98 |
-
"loss": 1.
|
| 99 |
"step": 150
|
| 100 |
},
|
| 101 |
{
|
| 102 |
"epoch": 0.5,
|
| 103 |
-
"eval_accuracy": 0.
|
| 104 |
-
"eval_loss":
|
| 105 |
-
"eval_runtime":
|
| 106 |
-
"eval_samples_per_second": 3.
|
| 107 |
-
"eval_steps_per_second": 1.
|
| 108 |
"step": 150
|
| 109 |
},
|
| 110 |
{
|
| 111 |
-
"epoch": 1.
|
|
|
|
| 112 |
"learning_rate": 2.5925925925925925e-05,
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 160
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 1.
|
|
|
|
| 118 |
"learning_rate": 2.4074074074074074e-05,
|
| 119 |
-
"loss": 1.
|
| 120 |
"step": 170
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 1.1,
|
|
|
|
| 124 |
"learning_rate": 2.2222222222222223e-05,
|
| 125 |
-
"loss": 0.
|
| 126 |
"step": 180
|
| 127 |
},
|
| 128 |
{
|
| 129 |
-
"epoch": 1.
|
|
|
|
| 130 |
"learning_rate": 2.037037037037037e-05,
|
| 131 |
-
"loss": 0.
|
| 132 |
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
-
"epoch": 1.
|
|
|
|
| 136 |
"learning_rate": 1.8518518518518518e-05,
|
| 137 |
-
"loss":
|
| 138 |
"step": 200
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 1.2,
|
|
|
|
| 142 |
"learning_rate": 1.6666666666666667e-05,
|
| 143 |
-
"loss": 0.
|
| 144 |
"step": 210
|
| 145 |
},
|
| 146 |
{
|
| 147 |
-
"epoch": 1.
|
|
|
|
| 148 |
"learning_rate": 1.4814814814814815e-05,
|
| 149 |
-
"loss": 0.
|
| 150 |
"step": 220
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch": 1.
|
|
|
|
| 154 |
"learning_rate": 1.2962962962962962e-05,
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 230
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 1.3,
|
|
|
|
| 160 |
"learning_rate": 1.1111111111111112e-05,
|
| 161 |
-
"loss": 0.
|
| 162 |
"step": 240
|
| 163 |
},
|
| 164 |
{
|
| 165 |
-
"epoch": 1.
|
|
|
|
| 166 |
"learning_rate": 9.259259259259259e-06,
|
| 167 |
-
"loss": 0.
|
| 168 |
"step": 250
|
| 169 |
},
|
| 170 |
{
|
| 171 |
-
"epoch": 1.
|
|
|
|
| 172 |
"learning_rate": 7.4074074074074075e-06,
|
| 173 |
-
"loss": 0.
|
| 174 |
"step": 260
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 1.4,
|
|
|
|
| 178 |
"learning_rate": 5.555555555555556e-06,
|
| 179 |
-
"loss": 0.
|
| 180 |
"step": 270
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"epoch": 1.
|
|
|
|
| 184 |
"learning_rate": 3.7037037037037037e-06,
|
| 185 |
-
"loss": 0.
|
| 186 |
"step": 280
|
| 187 |
},
|
| 188 |
{
|
| 189 |
-
"epoch": 1.
|
|
|
|
| 190 |
"learning_rate": 1.8518518518518519e-06,
|
| 191 |
-
"loss": 0.
|
| 192 |
"step": 290
|
| 193 |
},
|
| 194 |
{
|
| 195 |
"epoch": 1.5,
|
|
|
|
| 196 |
"learning_rate": 0.0,
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 300
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 1.5,
|
| 202 |
-
"eval_accuracy": 0.
|
| 203 |
-
"eval_loss": 0.
|
| 204 |
-
"eval_runtime":
|
| 205 |
-
"eval_samples_per_second": 3.
|
| 206 |
-
"eval_steps_per_second": 1.
|
| 207 |
"step": 300
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 1.5,
|
| 211 |
"step": 300,
|
| 212 |
"total_flos": 7.47692094062592e+17,
|
| 213 |
-
"train_loss": 1.
|
| 214 |
-
"train_runtime":
|
| 215 |
-
"train_samples_per_second": 1.
|
| 216 |
-
"train_steps_per_second": 0.
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 1.5,
|
| 220 |
-
"eval_accuracy": 0.
|
| 221 |
-
"eval_loss": 0.
|
| 222 |
-
"eval_runtime":
|
| 223 |
-
"eval_samples_per_second": 3.
|
| 224 |
-
"eval_steps_per_second": 1.
|
| 225 |
"step": 300
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 1.5,
|
| 229 |
-
"eval_accuracy": 0.
|
| 230 |
-
"eval_loss": 0.
|
| 231 |
-
"eval_runtime":
|
| 232 |
-
"eval_samples_per_second": 3.
|
| 233 |
-
"eval_steps_per_second": 1.
|
| 234 |
"step": 300
|
| 235 |
}
|
| 236 |
],
|
| 237 |
"logging_steps": 10,
|
| 238 |
"max_steps": 300,
|
|
|
|
| 239 |
"num_train_epochs": 9223372036854775807,
|
| 240 |
"save_steps": 500,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 241 |
"total_flos": 7.47692094062592e+17,
|
|
|
|
| 242 |
"trial_name": null,
|
| 243 |
"trial_params": null
|
| 244 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7857142857142857,
|
| 3 |
"best_model_checkpoint": "videomae-base-finetuned-ucf101-subset/checkpoint-300",
|
| 4 |
"epoch": 1.5,
|
| 5 |
"eval_steps": 500,
|
|
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.03333333333333333,
|
| 13 |
+
"grad_norm": 12.915124893188477,
|
| 14 |
"learning_rate": 1.6666666666666667e-05,
|
| 15 |
+
"loss": 2.3784,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.06666666666666667,
|
| 20 |
+
"grad_norm": 12.616281509399414,
|
| 21 |
"learning_rate": 3.3333333333333335e-05,
|
| 22 |
+
"loss": 2.3684,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.1,
|
| 27 |
+
"grad_norm": 13.955244064331055,
|
| 28 |
"learning_rate": 5e-05,
|
| 29 |
+
"loss": 2.2632,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.13333333333333333,
|
| 34 |
+
"grad_norm": 15.318857192993164,
|
| 35 |
"learning_rate": 4.814814814814815e-05,
|
| 36 |
+
"loss": 2.2229,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.16666666666666666,
|
| 41 |
+
"grad_norm": 18.756649017333984,
|
| 42 |
"learning_rate": 4.62962962962963e-05,
|
| 43 |
+
"loss": 2.0136,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.2,
|
| 48 |
+
"grad_norm": 16.19718360900879,
|
| 49 |
"learning_rate": 4.4444444444444447e-05,
|
| 50 |
+
"loss": 2.1816,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.23333333333333334,
|
| 55 |
+
"grad_norm": 17.45854949951172,
|
| 56 |
"learning_rate": 4.259259259259259e-05,
|
| 57 |
+
"loss": 2.1317,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.26666666666666666,
|
| 62 |
+
"grad_norm": 24.390531539916992,
|
| 63 |
"learning_rate": 4.074074074074074e-05,
|
| 64 |
+
"loss": 1.6419,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.3,
|
| 69 |
+
"grad_norm": 18.53119468688965,
|
| 70 |
"learning_rate": 3.888888888888889e-05,
|
| 71 |
+
"loss": 1.8912,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.3333333333333333,
|
| 76 |
+
"grad_norm": 23.2191219329834,
|
| 77 |
"learning_rate": 3.7037037037037037e-05,
|
| 78 |
+
"loss": 1.6417,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.36666666666666664,
|
| 83 |
+
"grad_norm": 19.124753952026367,
|
| 84 |
"learning_rate": 3.518518518518519e-05,
|
| 85 |
+
"loss": 1.7508,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.4,
|
| 90 |
+
"grad_norm": 7.332584381103516,
|
| 91 |
"learning_rate": 3.3333333333333335e-05,
|
| 92 |
+
"loss": 1.6249,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.43333333333333335,
|
| 97 |
+
"grad_norm": 23.19915199279785,
|
| 98 |
"learning_rate": 3.148148148148148e-05,
|
| 99 |
+
"loss": 1.531,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.4666666666666667,
|
| 104 |
+
"grad_norm": 16.055986404418945,
|
| 105 |
"learning_rate": 2.962962962962963e-05,
|
| 106 |
+
"loss": 1.4367,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.5,
|
| 111 |
+
"grad_norm": 19.868087768554688,
|
| 112 |
"learning_rate": 2.777777777777778e-05,
|
| 113 |
+
"loss": 1.3617,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.5,
|
| 118 |
+
"eval_accuracy": 0.5,
|
| 119 |
+
"eval_loss": 1.3257172107696533,
|
| 120 |
+
"eval_runtime": 19.376,
|
| 121 |
+
"eval_samples_per_second": 3.613,
|
| 122 |
+
"eval_steps_per_second": 1.806,
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 1.0333333333333334,
|
| 127 |
+
"grad_norm": 17.58294105529785,
|
| 128 |
"learning_rate": 2.5925925925925925e-05,
|
| 129 |
+
"loss": 0.9594,
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"epoch": 1.0666666666666667,
|
| 134 |
+
"grad_norm": 23.686206817626953,
|
| 135 |
"learning_rate": 2.4074074074074074e-05,
|
| 136 |
+
"loss": 1.1516,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.1,
|
| 141 |
+
"grad_norm": 26.428407669067383,
|
| 142 |
"learning_rate": 2.2222222222222223e-05,
|
| 143 |
+
"loss": 0.906,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 1.1333333333333333,
|
| 148 |
+
"grad_norm": 19.449148178100586,
|
| 149 |
"learning_rate": 2.037037037037037e-05,
|
| 150 |
+
"loss": 0.7873,
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
+
"epoch": 1.1666666666666667,
|
| 155 |
+
"grad_norm": 40.24578857421875,
|
| 156 |
"learning_rate": 1.8518518518518518e-05,
|
| 157 |
+
"loss": 1.1222,
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.2,
|
| 162 |
+
"grad_norm": 15.197308540344238,
|
| 163 |
"learning_rate": 1.6666666666666667e-05,
|
| 164 |
+
"loss": 0.6263,
|
| 165 |
"step": 210
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 1.2333333333333334,
|
| 169 |
+
"grad_norm": 15.162151336669922,
|
| 170 |
"learning_rate": 1.4814814814814815e-05,
|
| 171 |
+
"loss": 0.6937,
|
| 172 |
"step": 220
|
| 173 |
},
|
| 174 |
{
|
| 175 |
+
"epoch": 1.2666666666666666,
|
| 176 |
+
"grad_norm": 5.493642330169678,
|
| 177 |
"learning_rate": 1.2962962962962962e-05,
|
| 178 |
+
"loss": 0.806,
|
| 179 |
"step": 230
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 1.3,
|
| 183 |
+
"grad_norm": 5.520137310028076,
|
| 184 |
"learning_rate": 1.1111111111111112e-05,
|
| 185 |
+
"loss": 0.5812,
|
| 186 |
"step": 240
|
| 187 |
},
|
| 188 |
{
|
| 189 |
+
"epoch": 1.3333333333333333,
|
| 190 |
+
"grad_norm": 28.708820343017578,
|
| 191 |
"learning_rate": 9.259259259259259e-06,
|
| 192 |
+
"loss": 0.7231,
|
| 193 |
"step": 250
|
| 194 |
},
|
| 195 |
{
|
| 196 |
+
"epoch": 1.3666666666666667,
|
| 197 |
+
"grad_norm": 1.0324937105178833,
|
| 198 |
"learning_rate": 7.4074074074074075e-06,
|
| 199 |
+
"loss": 0.3939,
|
| 200 |
"step": 260
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 1.4,
|
| 204 |
+
"grad_norm": 31.389986038208008,
|
| 205 |
"learning_rate": 5.555555555555556e-06,
|
| 206 |
+
"loss": 0.4833,
|
| 207 |
"step": 270
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 1.4333333333333333,
|
| 211 |
+
"grad_norm": 15.664688110351562,
|
| 212 |
"learning_rate": 3.7037037037037037e-06,
|
| 213 |
+
"loss": 0.2994,
|
| 214 |
"step": 280
|
| 215 |
},
|
| 216 |
{
|
| 217 |
+
"epoch": 1.4666666666666668,
|
| 218 |
+
"grad_norm": 12.544212341308594,
|
| 219 |
"learning_rate": 1.8518518518518519e-06,
|
| 220 |
+
"loss": 0.8584,
|
| 221 |
"step": 290
|
| 222 |
},
|
| 223 |
{
|
| 224 |
"epoch": 1.5,
|
| 225 |
+
"grad_norm": 7.230623722076416,
|
| 226 |
"learning_rate": 0.0,
|
| 227 |
+
"loss": 0.7925,
|
| 228 |
"step": 300
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 1.5,
|
| 232 |
+
"eval_accuracy": 0.7857142857142857,
|
| 233 |
+
"eval_loss": 0.6653470993041992,
|
| 234 |
+
"eval_runtime": 18.5919,
|
| 235 |
+
"eval_samples_per_second": 3.765,
|
| 236 |
+
"eval_steps_per_second": 1.883,
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 1.5,
|
| 241 |
"step": 300,
|
| 242 |
"total_flos": 7.47692094062592e+17,
|
| 243 |
+
"train_loss": 1.320799682935079,
|
| 244 |
+
"train_runtime": 404.8672,
|
| 245 |
+
"train_samples_per_second": 1.482,
|
| 246 |
+
"train_steps_per_second": 0.741
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 1.5,
|
| 250 |
+
"eval_accuracy": 0.7870967741935484,
|
| 251 |
+
"eval_loss": 0.6657505035400391,
|
| 252 |
+
"eval_runtime": 42.1038,
|
| 253 |
+
"eval_samples_per_second": 3.681,
|
| 254 |
+
"eval_steps_per_second": 1.853,
|
| 255 |
"step": 300
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 1.5,
|
| 259 |
+
"eval_accuracy": 0.7870967741935484,
|
| 260 |
+
"eval_loss": 0.6657504439353943,
|
| 261 |
+
"eval_runtime": 42.1495,
|
| 262 |
+
"eval_samples_per_second": 3.677,
|
| 263 |
+
"eval_steps_per_second": 1.851,
|
| 264 |
"step": 300
|
| 265 |
}
|
| 266 |
],
|
| 267 |
"logging_steps": 10,
|
| 268 |
"max_steps": 300,
|
| 269 |
+
"num_input_tokens_seen": 0,
|
| 270 |
"num_train_epochs": 9223372036854775807,
|
| 271 |
"save_steps": 500,
|
| 272 |
+
"stateful_callbacks": {
|
| 273 |
+
"TrainerControl": {
|
| 274 |
+
"args": {
|
| 275 |
+
"should_epoch_stop": false,
|
| 276 |
+
"should_evaluate": false,
|
| 277 |
+
"should_log": false,
|
| 278 |
+
"should_save": true,
|
| 279 |
+
"should_training_stop": true
|
| 280 |
+
},
|
| 281 |
+
"attributes": {}
|
| 282 |
+
}
|
| 283 |
+
},
|
| 284 |
"total_flos": 7.47692094062592e+17,
|
| 285 |
+
"train_batch_size": 2,
|
| 286 |
"trial_name": null,
|
| 287 |
"trial_params": null
|
| 288 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cba774569b4f69bf8b3e151f301f8a81a154c061b54bceb7919d0d01e97c129
|
| 3 |
size 5176
|