Upload folder using huggingface_hub (#4)
Browse files- Upload folder using huggingface_hub (5b80219701c2f261bca70e37520884d074283fd1)
- config.json +34 -0
- optimizer.pt +3 -0
- preprocessor_config.json +22 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +610 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "Benign",
|
| 13 |
+
"1": "Malignant",
|
| 14 |
+
"2": "NoTumor"
|
| 15 |
+
},
|
| 16 |
+
"image_size": 224,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"Benign": "0",
|
| 21 |
+
"Malignant": "1",
|
| 22 |
+
"NoTumor": "2"
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"model_type": "vit",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_channels": 3,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"qkv_bias": true,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.31.0"
|
| 34 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5167b230451a751d190361a5f1abe4137481252f49d580e8af0df9e5b4e6771
|
| 3 |
+
size 686525061
|
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": "ViTFeatureExtractor",
|
| 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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bdb68787afb42af5a9e0105b9694fc8eea4e4778940b6791e5c2e0e043994b3
|
| 3 |
+
size 343271789
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab62043be50b93d4eb28964be2d945176db3d64fe73ddd052a7656ba9141c683
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7be74ea536e79eb53304c8ad7665b1808b95e8a71eefc3a101477593346ec95
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,610 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.057097259908914566,
|
| 3 |
+
"best_model_checkpoint": "./vit-base-beans/checkpoint-480",
|
| 4 |
+
"epoch": 1.9565217391304348,
|
| 5 |
+
"global_step": 720,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 0.0001972826086956522,
|
| 13 |
+
"loss": 0.6016,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 0.00019456521739130434,
|
| 19 |
+
"loss": 0.168,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 0.00019184782608695653,
|
| 25 |
+
"loss": 0.1568,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 0.0001891304347826087,
|
| 31 |
+
"loss": 0.1165,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.11,
|
| 36 |
+
"eval_accuracy": 0.9754768392370572,
|
| 37 |
+
"eval_loss": 0.10377205908298492,
|
| 38 |
+
"eval_runtime": 18.7416,
|
| 39 |
+
"eval_samples_per_second": 39.164,
|
| 40 |
+
"eval_steps_per_second": 4.909,
|
| 41 |
+
"step": 40
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.14,
|
| 45 |
+
"learning_rate": 0.0001864130434782609,
|
| 46 |
+
"loss": 0.0853,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.16,
|
| 51 |
+
"learning_rate": 0.00018369565217391304,
|
| 52 |
+
"loss": 0.179,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.19,
|
| 57 |
+
"learning_rate": 0.00018097826086956522,
|
| 58 |
+
"loss": 0.0871,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.22,
|
| 63 |
+
"learning_rate": 0.0001782608695652174,
|
| 64 |
+
"loss": 0.0596,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.22,
|
| 69 |
+
"eval_accuracy": 0.9673024523160763,
|
| 70 |
+
"eval_loss": 0.1255735605955124,
|
| 71 |
+
"eval_runtime": 19.1765,
|
| 72 |
+
"eval_samples_per_second": 38.276,
|
| 73 |
+
"eval_steps_per_second": 4.798,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.24,
|
| 78 |
+
"learning_rate": 0.00017554347826086956,
|
| 79 |
+
"loss": 0.1279,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.27,
|
| 84 |
+
"learning_rate": 0.00017282608695652174,
|
| 85 |
+
"loss": 0.0814,
|
| 86 |
+
"step": 100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3,
|
| 90 |
+
"learning_rate": 0.00017010869565217392,
|
| 91 |
+
"loss": 0.0967,
|
| 92 |
+
"step": 110
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.33,
|
| 96 |
+
"learning_rate": 0.0001673913043478261,
|
| 97 |
+
"loss": 0.1317,
|
| 98 |
+
"step": 120
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.33,
|
| 102 |
+
"eval_accuracy": 0.9495912806539509,
|
| 103 |
+
"eval_loss": 0.18217410147190094,
|
| 104 |
+
"eval_runtime": 17.5926,
|
| 105 |
+
"eval_samples_per_second": 41.722,
|
| 106 |
+
"eval_steps_per_second": 5.229,
|
| 107 |
+
"step": 120
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.35,
|
| 111 |
+
"learning_rate": 0.00016467391304347828,
|
| 112 |
+
"loss": 0.0585,
|
| 113 |
+
"step": 130
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.38,
|
| 117 |
+
"learning_rate": 0.00016195652173913046,
|
| 118 |
+
"loss": 0.078,
|
| 119 |
+
"step": 140
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.41,
|
| 123 |
+
"learning_rate": 0.00015923913043478262,
|
| 124 |
+
"loss": 0.0794,
|
| 125 |
+
"step": 150
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.43,
|
| 129 |
+
"learning_rate": 0.0001565217391304348,
|
| 130 |
+
"loss": 0.0731,
|
| 131 |
+
"step": 160
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.43,
|
| 135 |
+
"eval_accuracy": 0.9741144414168937,
|
| 136 |
+
"eval_loss": 0.11143568158149719,
|
| 137 |
+
"eval_runtime": 18.204,
|
| 138 |
+
"eval_samples_per_second": 40.321,
|
| 139 |
+
"eval_steps_per_second": 5.054,
|
| 140 |
+
"step": 160
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.46,
|
| 144 |
+
"learning_rate": 0.00015380434782608698,
|
| 145 |
+
"loss": 0.0842,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.49,
|
| 150 |
+
"learning_rate": 0.00015108695652173913,
|
| 151 |
+
"loss": 0.0406,
|
| 152 |
+
"step": 180
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.52,
|
| 156 |
+
"learning_rate": 0.0001483695652173913,
|
| 157 |
+
"loss": 0.1171,
|
| 158 |
+
"step": 190
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.54,
|
| 162 |
+
"learning_rate": 0.0001456521739130435,
|
| 163 |
+
"loss": 0.1041,
|
| 164 |
+
"step": 200
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.54,
|
| 168 |
+
"eval_accuracy": 0.9754768392370572,
|
| 169 |
+
"eval_loss": 0.08514755964279175,
|
| 170 |
+
"eval_runtime": 17.638,
|
| 171 |
+
"eval_samples_per_second": 41.615,
|
| 172 |
+
"eval_steps_per_second": 5.216,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.57,
|
| 177 |
+
"learning_rate": 0.00014293478260869567,
|
| 178 |
+
"loss": 0.0823,
|
| 179 |
+
"step": 210
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.6,
|
| 183 |
+
"learning_rate": 0.00014021739130434783,
|
| 184 |
+
"loss": 0.0536,
|
| 185 |
+
"step": 220
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.62,
|
| 189 |
+
"learning_rate": 0.0001375,
|
| 190 |
+
"loss": 0.1171,
|
| 191 |
+
"step": 230
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.65,
|
| 195 |
+
"learning_rate": 0.0001347826086956522,
|
| 196 |
+
"loss": 0.1292,
|
| 197 |
+
"step": 240
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.65,
|
| 201 |
+
"eval_accuracy": 0.9645776566757494,
|
| 202 |
+
"eval_loss": 0.13422255218029022,
|
| 203 |
+
"eval_runtime": 17.8577,
|
| 204 |
+
"eval_samples_per_second": 41.103,
|
| 205 |
+
"eval_steps_per_second": 5.152,
|
| 206 |
+
"step": 240
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.68,
|
| 210 |
+
"learning_rate": 0.00013206521739130434,
|
| 211 |
+
"loss": 0.1483,
|
| 212 |
+
"step": 250
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.71,
|
| 216 |
+
"learning_rate": 0.00012934782608695652,
|
| 217 |
+
"loss": 0.1082,
|
| 218 |
+
"step": 260
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.73,
|
| 222 |
+
"learning_rate": 0.0001266304347826087,
|
| 223 |
+
"loss": 0.1206,
|
| 224 |
+
"step": 270
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.76,
|
| 228 |
+
"learning_rate": 0.00012391304347826086,
|
| 229 |
+
"loss": 0.1232,
|
| 230 |
+
"step": 280
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.76,
|
| 234 |
+
"eval_accuracy": 0.9741144414168937,
|
| 235 |
+
"eval_loss": 0.08246026188135147,
|
| 236 |
+
"eval_runtime": 17.6614,
|
| 237 |
+
"eval_samples_per_second": 41.56,
|
| 238 |
+
"eval_steps_per_second": 5.209,
|
| 239 |
+
"step": 280
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.79,
|
| 243 |
+
"learning_rate": 0.00012119565217391304,
|
| 244 |
+
"loss": 0.0745,
|
| 245 |
+
"step": 290
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.82,
|
| 249 |
+
"learning_rate": 0.00011847826086956522,
|
| 250 |
+
"loss": 0.1076,
|
| 251 |
+
"step": 300
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.84,
|
| 255 |
+
"learning_rate": 0.00011576086956521739,
|
| 256 |
+
"loss": 0.0651,
|
| 257 |
+
"step": 310
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.87,
|
| 261 |
+
"learning_rate": 0.00011304347826086956,
|
| 262 |
+
"loss": 0.0782,
|
| 263 |
+
"step": 320
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.87,
|
| 267 |
+
"eval_accuracy": 0.9741144414168937,
|
| 268 |
+
"eval_loss": 0.09356382489204407,
|
| 269 |
+
"eval_runtime": 17.6794,
|
| 270 |
+
"eval_samples_per_second": 41.517,
|
| 271 |
+
"eval_steps_per_second": 5.204,
|
| 272 |
+
"step": 320
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.9,
|
| 276 |
+
"learning_rate": 0.00011032608695652174,
|
| 277 |
+
"loss": 0.115,
|
| 278 |
+
"step": 330
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.92,
|
| 282 |
+
"learning_rate": 0.0001076086956521739,
|
| 283 |
+
"loss": 0.0635,
|
| 284 |
+
"step": 340
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.95,
|
| 288 |
+
"learning_rate": 0.0001048913043478261,
|
| 289 |
+
"loss": 0.1061,
|
| 290 |
+
"step": 350
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.98,
|
| 294 |
+
"learning_rate": 0.00010217391304347828,
|
| 295 |
+
"loss": 0.1171,
|
| 296 |
+
"step": 360
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.98,
|
| 300 |
+
"eval_accuracy": 0.9768392370572208,
|
| 301 |
+
"eval_loss": 0.06765041500329971,
|
| 302 |
+
"eval_runtime": 18.1237,
|
| 303 |
+
"eval_samples_per_second": 40.499,
|
| 304 |
+
"eval_steps_per_second": 5.076,
|
| 305 |
+
"step": 360
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.01,
|
| 309 |
+
"learning_rate": 9.945652173913043e-05,
|
| 310 |
+
"loss": 0.086,
|
| 311 |
+
"step": 370
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.03,
|
| 315 |
+
"learning_rate": 9.673913043478261e-05,
|
| 316 |
+
"loss": 0.0685,
|
| 317 |
+
"step": 380
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.06,
|
| 321 |
+
"learning_rate": 9.402173913043478e-05,
|
| 322 |
+
"loss": 0.052,
|
| 323 |
+
"step": 390
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.09,
|
| 327 |
+
"learning_rate": 9.130434782608696e-05,
|
| 328 |
+
"loss": 0.0549,
|
| 329 |
+
"step": 400
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.09,
|
| 333 |
+
"eval_accuracy": 0.9727520435967303,
|
| 334 |
+
"eval_loss": 0.06371203064918518,
|
| 335 |
+
"eval_runtime": 17.6078,
|
| 336 |
+
"eval_samples_per_second": 41.686,
|
| 337 |
+
"eval_steps_per_second": 5.225,
|
| 338 |
+
"step": 400
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.11,
|
| 342 |
+
"learning_rate": 8.858695652173914e-05,
|
| 343 |
+
"loss": 0.058,
|
| 344 |
+
"step": 410
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.14,
|
| 348 |
+
"learning_rate": 8.586956521739131e-05,
|
| 349 |
+
"loss": 0.1215,
|
| 350 |
+
"step": 420
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.17,
|
| 354 |
+
"learning_rate": 8.315217391304349e-05,
|
| 355 |
+
"loss": 0.1048,
|
| 356 |
+
"step": 430
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.2,
|
| 360 |
+
"learning_rate": 8.043478260869566e-05,
|
| 361 |
+
"loss": 0.0603,
|
| 362 |
+
"step": 440
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.2,
|
| 366 |
+
"eval_accuracy": 0.9768392370572208,
|
| 367 |
+
"eval_loss": 0.06182762607932091,
|
| 368 |
+
"eval_runtime": 18.5478,
|
| 369 |
+
"eval_samples_per_second": 39.574,
|
| 370 |
+
"eval_steps_per_second": 4.96,
|
| 371 |
+
"step": 440
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 1.22,
|
| 375 |
+
"learning_rate": 7.771739130434783e-05,
|
| 376 |
+
"loss": 0.0648,
|
| 377 |
+
"step": 450
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 1.25,
|
| 381 |
+
"learning_rate": 7.500000000000001e-05,
|
| 382 |
+
"loss": 0.0512,
|
| 383 |
+
"step": 460
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.28,
|
| 387 |
+
"learning_rate": 7.228260869565217e-05,
|
| 388 |
+
"loss": 0.0867,
|
| 389 |
+
"step": 470
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.3,
|
| 393 |
+
"learning_rate": 6.956521739130436e-05,
|
| 394 |
+
"loss": 0.049,
|
| 395 |
+
"step": 480
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.3,
|
| 399 |
+
"eval_accuracy": 0.9768392370572208,
|
| 400 |
+
"eval_loss": 0.057097259908914566,
|
| 401 |
+
"eval_runtime": 17.4967,
|
| 402 |
+
"eval_samples_per_second": 41.951,
|
| 403 |
+
"eval_steps_per_second": 5.258,
|
| 404 |
+
"step": 480
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.33,
|
| 408 |
+
"learning_rate": 6.684782608695652e-05,
|
| 409 |
+
"loss": 0.0389,
|
| 410 |
+
"step": 490
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.36,
|
| 414 |
+
"learning_rate": 6.413043478260869e-05,
|
| 415 |
+
"loss": 0.087,
|
| 416 |
+
"step": 500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.39,
|
| 420 |
+
"learning_rate": 6.141304347826087e-05,
|
| 421 |
+
"loss": 0.0733,
|
| 422 |
+
"step": 510
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.41,
|
| 426 |
+
"learning_rate": 5.869565217391305e-05,
|
| 427 |
+
"loss": 0.0199,
|
| 428 |
+
"step": 520
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.41,
|
| 432 |
+
"eval_accuracy": 0.9727520435967303,
|
| 433 |
+
"eval_loss": 0.07243036478757858,
|
| 434 |
+
"eval_runtime": 17.9356,
|
| 435 |
+
"eval_samples_per_second": 40.924,
|
| 436 |
+
"eval_steps_per_second": 5.129,
|
| 437 |
+
"step": 520
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.44,
|
| 441 |
+
"learning_rate": 5.5978260869565226e-05,
|
| 442 |
+
"loss": 0.0629,
|
| 443 |
+
"step": 530
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.47,
|
| 447 |
+
"learning_rate": 5.32608695652174e-05,
|
| 448 |
+
"loss": 0.0752,
|
| 449 |
+
"step": 540
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.49,
|
| 453 |
+
"learning_rate": 5.054347826086957e-05,
|
| 454 |
+
"loss": 0.0894,
|
| 455 |
+
"step": 550
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 1.52,
|
| 459 |
+
"learning_rate": 4.782608695652174e-05,
|
| 460 |
+
"loss": 0.0787,
|
| 461 |
+
"step": 560
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.52,
|
| 465 |
+
"eval_accuracy": 0.9754768392370572,
|
| 466 |
+
"eval_loss": 0.06181642785668373,
|
| 467 |
+
"eval_runtime": 17.5051,
|
| 468 |
+
"eval_samples_per_second": 41.931,
|
| 469 |
+
"eval_steps_per_second": 5.256,
|
| 470 |
+
"step": 560
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.55,
|
| 474 |
+
"learning_rate": 4.5108695652173916e-05,
|
| 475 |
+
"loss": 0.1088,
|
| 476 |
+
"step": 570
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.58,
|
| 480 |
+
"learning_rate": 4.239130434782609e-05,
|
| 481 |
+
"loss": 0.0586,
|
| 482 |
+
"step": 580
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.6,
|
| 486 |
+
"learning_rate": 3.9673913043478264e-05,
|
| 487 |
+
"loss": 0.0972,
|
| 488 |
+
"step": 590
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.63,
|
| 492 |
+
"learning_rate": 3.695652173913043e-05,
|
| 493 |
+
"loss": 0.049,
|
| 494 |
+
"step": 600
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.63,
|
| 498 |
+
"eval_accuracy": 0.9754768392370572,
|
| 499 |
+
"eval_loss": 0.058572325855493546,
|
| 500 |
+
"eval_runtime": 19.2109,
|
| 501 |
+
"eval_samples_per_second": 38.207,
|
| 502 |
+
"eval_steps_per_second": 4.789,
|
| 503 |
+
"step": 600
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.66,
|
| 507 |
+
"learning_rate": 3.423913043478261e-05,
|
| 508 |
+
"loss": 0.0505,
|
| 509 |
+
"step": 610
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.68,
|
| 513 |
+
"learning_rate": 3.152173913043479e-05,
|
| 514 |
+
"loss": 0.0226,
|
| 515 |
+
"step": 620
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.71,
|
| 519 |
+
"learning_rate": 2.8804347826086957e-05,
|
| 520 |
+
"loss": 0.0754,
|
| 521 |
+
"step": 630
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.74,
|
| 525 |
+
"learning_rate": 2.608695652173913e-05,
|
| 526 |
+
"loss": 0.0356,
|
| 527 |
+
"step": 640
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 1.74,
|
| 531 |
+
"eval_accuracy": 0.9754768392370572,
|
| 532 |
+
"eval_loss": 0.05890597403049469,
|
| 533 |
+
"eval_runtime": 17.4571,
|
| 534 |
+
"eval_samples_per_second": 42.046,
|
| 535 |
+
"eval_steps_per_second": 5.27,
|
| 536 |
+
"step": 640
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.77,
|
| 540 |
+
"learning_rate": 2.3369565217391306e-05,
|
| 541 |
+
"loss": 0.0261,
|
| 542 |
+
"step": 650
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.79,
|
| 546 |
+
"learning_rate": 2.065217391304348e-05,
|
| 547 |
+
"loss": 0.1149,
|
| 548 |
+
"step": 660
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.82,
|
| 552 |
+
"learning_rate": 1.793478260869565e-05,
|
| 553 |
+
"loss": 0.0605,
|
| 554 |
+
"step": 670
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.85,
|
| 558 |
+
"learning_rate": 1.5217391304347828e-05,
|
| 559 |
+
"loss": 0.0761,
|
| 560 |
+
"step": 680
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.85,
|
| 564 |
+
"eval_accuracy": 0.9754768392370572,
|
| 565 |
+
"eval_loss": 0.062350884079933167,
|
| 566 |
+
"eval_runtime": 17.6913,
|
| 567 |
+
"eval_samples_per_second": 41.489,
|
| 568 |
+
"eval_steps_per_second": 5.2,
|
| 569 |
+
"step": 680
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.88,
|
| 573 |
+
"learning_rate": 1.25e-05,
|
| 574 |
+
"loss": 0.1011,
|
| 575 |
+
"step": 690
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 1.9,
|
| 579 |
+
"learning_rate": 9.782608695652175e-06,
|
| 580 |
+
"loss": 0.0473,
|
| 581 |
+
"step": 700
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 1.93,
|
| 585 |
+
"learning_rate": 7.065217391304347e-06,
|
| 586 |
+
"loss": 0.0595,
|
| 587 |
+
"step": 710
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.96,
|
| 591 |
+
"learning_rate": 4.347826086956522e-06,
|
| 592 |
+
"loss": 0.0566,
|
| 593 |
+
"step": 720
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.96,
|
| 597 |
+
"eval_accuracy": 0.9754768392370572,
|
| 598 |
+
"eval_loss": 0.059235844761133194,
|
| 599 |
+
"eval_runtime": 17.9656,
|
| 600 |
+
"eval_samples_per_second": 40.856,
|
| 601 |
+
"eval_steps_per_second": 5.121,
|
| 602 |
+
"step": 720
|
| 603 |
+
}
|
| 604 |
+
],
|
| 605 |
+
"max_steps": 736,
|
| 606 |
+
"num_train_epochs": 2,
|
| 607 |
+
"total_flos": 8.915533311547699e+17,
|
| 608 |
+
"trial_name": null,
|
| 609 |
+
"trial_params": null
|
| 610 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94024797e7d1316e62c6bf965da1ed7e576bfdede5f093d36faf5554fa254f21
|
| 3 |
+
size 3963
|