Upload 8 files
Browse files- config.json +32 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +435 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224-in21k",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "Not Fresh",
|
| 13 |
+
"1": "Fresh"
|
| 14 |
+
},
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 3072,
|
| 18 |
+
"label2id": {
|
| 19 |
+
"Fresh": 1,
|
| 20 |
+
"Not Fresh": 0
|
| 21 |
+
},
|
| 22 |
+
"layer_norm_eps": 1e-12,
|
| 23 |
+
"model_type": "vit",
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"qkv_bias": true,
|
| 30 |
+
"torch_dtype": "float32",
|
| 31 |
+
"transformers_version": "4.46.2"
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1efb128d5eab14692b3240dd5a0f0809c93ae87388594bd29486c081633b5bd
|
| 3 |
+
size 343223968
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8608cb9262fab60d26edc70f35aa56e763af98297799020f739997c465c2002
|
| 3 |
+
size 686563258
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03540cf8c264dc4a7f513b6c540bb0c92d6d818989db1043306e06e4106e050f
|
| 3 |
+
size 13990
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81ee9cf73dc21e2ee45ea38df94088fc1efa51b1c7d53864650a7de1a1a97e2a
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,435 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 546,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.054945054945054944,
|
| 13 |
+
"grad_norm": 0.27392202615737915,
|
| 14 |
+
"learning_rate": 4.908424908424908e-05,
|
| 15 |
+
"loss": 0.6974,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10989010989010989,
|
| 20 |
+
"grad_norm": 1.1879206895828247,
|
| 21 |
+
"learning_rate": 4.816849816849817e-05,
|
| 22 |
+
"loss": 0.707,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16483516483516483,
|
| 27 |
+
"grad_norm": 0.04194138944149017,
|
| 28 |
+
"learning_rate": 4.7252747252747257e-05,
|
| 29 |
+
"loss": 0.6944,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.21978021978021978,
|
| 34 |
+
"grad_norm": 0.4733542203903198,
|
| 35 |
+
"learning_rate": 4.6336996336996343e-05,
|
| 36 |
+
"loss": 0.6962,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.27472527472527475,
|
| 41 |
+
"grad_norm": 0.5218614339828491,
|
| 42 |
+
"learning_rate": 4.5421245421245424e-05,
|
| 43 |
+
"loss": 0.6971,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.32967032967032966,
|
| 48 |
+
"grad_norm": 0.6687294244766235,
|
| 49 |
+
"learning_rate": 4.4505494505494504e-05,
|
| 50 |
+
"loss": 0.6912,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.38461538461538464,
|
| 55 |
+
"grad_norm": 0.8817914128303528,
|
| 56 |
+
"learning_rate": 4.358974358974359e-05,
|
| 57 |
+
"loss": 0.7019,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.43956043956043955,
|
| 62 |
+
"grad_norm": 0.0032853269949555397,
|
| 63 |
+
"learning_rate": 4.267399267399267e-05,
|
| 64 |
+
"loss": 0.6987,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.4945054945054945,
|
| 69 |
+
"grad_norm": 0.41789019107818604,
|
| 70 |
+
"learning_rate": 4.1758241758241765e-05,
|
| 71 |
+
"loss": 0.7004,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5494505494505495,
|
| 76 |
+
"grad_norm": 0.36019155383110046,
|
| 77 |
+
"learning_rate": 4.0842490842490845e-05,
|
| 78 |
+
"loss": 0.697,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.6043956043956044,
|
| 83 |
+
"grad_norm": 0.10219324380159378,
|
| 84 |
+
"learning_rate": 3.992673992673993e-05,
|
| 85 |
+
"loss": 0.6915,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.6593406593406593,
|
| 90 |
+
"grad_norm": 0.5682424902915955,
|
| 91 |
+
"learning_rate": 3.901098901098901e-05,
|
| 92 |
+
"loss": 0.6871,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.7142857142857143,
|
| 97 |
+
"grad_norm": 0.32208287715911865,
|
| 98 |
+
"learning_rate": 3.809523809523809e-05,
|
| 99 |
+
"loss": 0.6929,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.7692307692307693,
|
| 104 |
+
"grad_norm": 0.6399782299995422,
|
| 105 |
+
"learning_rate": 3.717948717948718e-05,
|
| 106 |
+
"loss": 0.6935,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.8241758241758241,
|
| 111 |
+
"grad_norm": 0.6218127012252808,
|
| 112 |
+
"learning_rate": 3.6263736263736266e-05,
|
| 113 |
+
"loss": 0.689,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8791208791208791,
|
| 118 |
+
"grad_norm": 0.15324005484580994,
|
| 119 |
+
"learning_rate": 3.534798534798535e-05,
|
| 120 |
+
"loss": 0.6934,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.9340659340659341,
|
| 125 |
+
"grad_norm": 0.6022002100944519,
|
| 126 |
+
"learning_rate": 3.443223443223443e-05,
|
| 127 |
+
"loss": 0.6959,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.989010989010989,
|
| 132 |
+
"grad_norm": 0.5421551465988159,
|
| 133 |
+
"learning_rate": 3.3516483516483513e-05,
|
| 134 |
+
"loss": 0.6943,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.0,
|
| 139 |
+
"eval_loss": 0.6939666867256165,
|
| 140 |
+
"eval_runtime": 189.5452,
|
| 141 |
+
"eval_samples_per_second": 3.83,
|
| 142 |
+
"eval_steps_per_second": 0.243,
|
| 143 |
+
"step": 182
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.043956043956044,
|
| 147 |
+
"grad_norm": 0.029725607484579086,
|
| 148 |
+
"learning_rate": 3.26007326007326e-05,
|
| 149 |
+
"loss": 0.6941,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.098901098901099,
|
| 154 |
+
"grad_norm": 0.2241191416978836,
|
| 155 |
+
"learning_rate": 3.168498168498169e-05,
|
| 156 |
+
"loss": 0.6947,
|
| 157 |
+
"step": 200
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.1538461538461537,
|
| 161 |
+
"grad_norm": 0.3774152100086212,
|
| 162 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 163 |
+
"loss": 0.6942,
|
| 164 |
+
"step": 210
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.2087912087912087,
|
| 168 |
+
"grad_norm": 0.20546726882457733,
|
| 169 |
+
"learning_rate": 2.9853479853479855e-05,
|
| 170 |
+
"loss": 0.6969,
|
| 171 |
+
"step": 220
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.2637362637362637,
|
| 175 |
+
"grad_norm": 0.13492144644260406,
|
| 176 |
+
"learning_rate": 2.893772893772894e-05,
|
| 177 |
+
"loss": 0.6902,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.3186813186813187,
|
| 182 |
+
"grad_norm": 0.8513393402099609,
|
| 183 |
+
"learning_rate": 2.8021978021978025e-05,
|
| 184 |
+
"loss": 0.6876,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.3736263736263736,
|
| 189 |
+
"grad_norm": 0.6317694783210754,
|
| 190 |
+
"learning_rate": 2.7106227106227105e-05,
|
| 191 |
+
"loss": 0.6997,
|
| 192 |
+
"step": 250
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.4285714285714286,
|
| 196 |
+
"grad_norm": 0.5553500056266785,
|
| 197 |
+
"learning_rate": 2.6190476190476192e-05,
|
| 198 |
+
"loss": 0.6957,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.4835164835164836,
|
| 203 |
+
"grad_norm": 0.6473520994186401,
|
| 204 |
+
"learning_rate": 2.5274725274725276e-05,
|
| 205 |
+
"loss": 0.6845,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.5384615384615383,
|
| 210 |
+
"grad_norm": 0.4740413427352905,
|
| 211 |
+
"learning_rate": 2.435897435897436e-05,
|
| 212 |
+
"loss": 0.6901,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.5934065934065935,
|
| 217 |
+
"grad_norm": 0.30147257447242737,
|
| 218 |
+
"learning_rate": 2.3443223443223443e-05,
|
| 219 |
+
"loss": 0.6938,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.6483516483516483,
|
| 224 |
+
"grad_norm": 0.8619340658187866,
|
| 225 |
+
"learning_rate": 2.252747252747253e-05,
|
| 226 |
+
"loss": 0.702,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.7032967032967035,
|
| 231 |
+
"grad_norm": 0.7783694863319397,
|
| 232 |
+
"learning_rate": 2.1611721611721613e-05,
|
| 233 |
+
"loss": 0.6931,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.7582417582417582,
|
| 238 |
+
"grad_norm": 1.2516826391220093,
|
| 239 |
+
"learning_rate": 2.0695970695970697e-05,
|
| 240 |
+
"loss": 0.6936,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.8131868131868132,
|
| 245 |
+
"grad_norm": 0.9541371464729309,
|
| 246 |
+
"learning_rate": 1.978021978021978e-05,
|
| 247 |
+
"loss": 0.6923,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.8681318681318682,
|
| 252 |
+
"grad_norm": 0.26722267270088196,
|
| 253 |
+
"learning_rate": 1.8864468864468864e-05,
|
| 254 |
+
"loss": 0.6944,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.9230769230769231,
|
| 259 |
+
"grad_norm": 0.26405128836631775,
|
| 260 |
+
"learning_rate": 1.794871794871795e-05,
|
| 261 |
+
"loss": 0.6936,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.978021978021978,
|
| 266 |
+
"grad_norm": 0.6899142861366272,
|
| 267 |
+
"learning_rate": 1.7032967032967035e-05,
|
| 268 |
+
"loss": 0.691,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.0,
|
| 273 |
+
"eval_loss": 0.6916947960853577,
|
| 274 |
+
"eval_runtime": 240.4419,
|
| 275 |
+
"eval_samples_per_second": 3.019,
|
| 276 |
+
"eval_steps_per_second": 0.191,
|
| 277 |
+
"step": 364
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 2.032967032967033,
|
| 281 |
+
"grad_norm": 0.15929658710956573,
|
| 282 |
+
"learning_rate": 1.6117216117216118e-05,
|
| 283 |
+
"loss": 0.6928,
|
| 284 |
+
"step": 370
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.087912087912088,
|
| 288 |
+
"grad_norm": 0.15032555162906647,
|
| 289 |
+
"learning_rate": 1.52014652014652e-05,
|
| 290 |
+
"loss": 0.6908,
|
| 291 |
+
"step": 380
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.142857142857143,
|
| 295 |
+
"grad_norm": 0.12846487760543823,
|
| 296 |
+
"learning_rate": 1.4285714285714285e-05,
|
| 297 |
+
"loss": 0.6912,
|
| 298 |
+
"step": 390
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 2.197802197802198,
|
| 302 |
+
"grad_norm": 0.1073530912399292,
|
| 303 |
+
"learning_rate": 1.336996336996337e-05,
|
| 304 |
+
"loss": 0.6958,
|
| 305 |
+
"step": 400
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.2527472527472527,
|
| 309 |
+
"grad_norm": 0.3209209144115448,
|
| 310 |
+
"learning_rate": 1.2454212454212454e-05,
|
| 311 |
+
"loss": 0.695,
|
| 312 |
+
"step": 410
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.3076923076923075,
|
| 316 |
+
"grad_norm": 0.19632519781589508,
|
| 317 |
+
"learning_rate": 1.153846153846154e-05,
|
| 318 |
+
"loss": 0.6951,
|
| 319 |
+
"step": 420
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.3626373626373627,
|
| 323 |
+
"grad_norm": 1.1780059337615967,
|
| 324 |
+
"learning_rate": 1.0622710622710623e-05,
|
| 325 |
+
"loss": 0.6906,
|
| 326 |
+
"step": 430
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.4175824175824174,
|
| 330 |
+
"grad_norm": 0.2050175666809082,
|
| 331 |
+
"learning_rate": 9.706959706959708e-06,
|
| 332 |
+
"loss": 0.6941,
|
| 333 |
+
"step": 440
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.4725274725274726,
|
| 337 |
+
"grad_norm": 0.6877321004867554,
|
| 338 |
+
"learning_rate": 8.791208791208792e-06,
|
| 339 |
+
"loss": 0.6908,
|
| 340 |
+
"step": 450
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 2.5274725274725274,
|
| 344 |
+
"grad_norm": 0.41336432099342346,
|
| 345 |
+
"learning_rate": 7.875457875457876e-06,
|
| 346 |
+
"loss": 0.6903,
|
| 347 |
+
"step": 460
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.5824175824175826,
|
| 351 |
+
"grad_norm": 0.339912474155426,
|
| 352 |
+
"learning_rate": 6.95970695970696e-06,
|
| 353 |
+
"loss": 0.6932,
|
| 354 |
+
"step": 470
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.6373626373626373,
|
| 358 |
+
"grad_norm": 0.3437363803386688,
|
| 359 |
+
"learning_rate": 6.043956043956044e-06,
|
| 360 |
+
"loss": 0.692,
|
| 361 |
+
"step": 480
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 2.6923076923076925,
|
| 365 |
+
"grad_norm": 0.10014953464269638,
|
| 366 |
+
"learning_rate": 5.128205128205128e-06,
|
| 367 |
+
"loss": 0.6907,
|
| 368 |
+
"step": 490
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.7472527472527473,
|
| 372 |
+
"grad_norm": 0.10608287155628204,
|
| 373 |
+
"learning_rate": 4.212454212454213e-06,
|
| 374 |
+
"loss": 0.6899,
|
| 375 |
+
"step": 500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.802197802197802,
|
| 379 |
+
"grad_norm": 0.13735678791999817,
|
| 380 |
+
"learning_rate": 3.2967032967032968e-06,
|
| 381 |
+
"loss": 0.694,
|
| 382 |
+
"step": 510
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.857142857142857,
|
| 386 |
+
"grad_norm": 0.5880533456802368,
|
| 387 |
+
"learning_rate": 2.3809523809523808e-06,
|
| 388 |
+
"loss": 0.7005,
|
| 389 |
+
"step": 520
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.912087912087912,
|
| 393 |
+
"grad_norm": 0.3347012996673584,
|
| 394 |
+
"learning_rate": 1.4652014652014652e-06,
|
| 395 |
+
"loss": 0.692,
|
| 396 |
+
"step": 530
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.967032967032967,
|
| 400 |
+
"grad_norm": 0.39770108461380005,
|
| 401 |
+
"learning_rate": 5.494505494505495e-07,
|
| 402 |
+
"loss": 0.6867,
|
| 403 |
+
"step": 540
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 3.0,
|
| 407 |
+
"eval_loss": 0.6915315389633179,
|
| 408 |
+
"eval_runtime": 192.9872,
|
| 409 |
+
"eval_samples_per_second": 3.762,
|
| 410 |
+
"eval_steps_per_second": 0.238,
|
| 411 |
+
"step": 546
|
| 412 |
+
}
|
| 413 |
+
],
|
| 414 |
+
"logging_steps": 10,
|
| 415 |
+
"max_steps": 546,
|
| 416 |
+
"num_input_tokens_seen": 0,
|
| 417 |
+
"num_train_epochs": 3,
|
| 418 |
+
"save_steps": 500,
|
| 419 |
+
"stateful_callbacks": {
|
| 420 |
+
"TrainerControl": {
|
| 421 |
+
"args": {
|
| 422 |
+
"should_epoch_stop": false,
|
| 423 |
+
"should_evaluate": false,
|
| 424 |
+
"should_log": false,
|
| 425 |
+
"should_save": true,
|
| 426 |
+
"should_training_stop": true
|
| 427 |
+
},
|
| 428 |
+
"attributes": {}
|
| 429 |
+
}
|
| 430 |
+
},
|
| 431 |
+
"total_flos": 6.751102135223255e+17,
|
| 432 |
+
"train_batch_size": 16,
|
| 433 |
+
"trial_name": null,
|
| 434 |
+
"trial_params": null
|
| 435 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59b115e2340cdab2780297a85eb4ea6e9664b27f157f57b4c73264a5ef5bd13c
|
| 3 |
+
size 5240
|