paul
commited on
Commit
•
5059a70
1
Parent(s):
ce01eb3
Training in progress, epoch 0
Browse files- all_results.json +8 -0
- config.json +16 -19
- preprocessor_config.json +8 -9
- pytorch_model.bin +2 -2
- runs/Jan21_17-13-54_teesta/events.out.tfevents.1674301465.teesta.3779.0 +2 -2
- runs/Jan21_17-25-09_teesta/1674302123.4912503/events.out.tfevents.1674302123.teesta.7894.1 +3 -0
- runs/Jan21_17-25-09_teesta/events.out.tfevents.1674302123.teesta.7894.0 +3 -0
- train_results.json +8 -0
- trainer_state.json +349 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 7.403951867151974e+17,
|
| 4 |
+
"train_loss": 1.1767685549599785,
|
| 5 |
+
"train_runtime": 421.2758,
|
| 6 |
+
"train_samples_per_second": 82.749,
|
| 7 |
+
"train_steps_per_second": 0.332
|
| 8 |
+
}
|
config.json
CHANGED
|
@@ -1,39 +1,36 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
-
],
|
| 6 |
-
"depths": [
|
| 7 |
-
3,
|
| 8 |
-
4,
|
| 9 |
-
6,
|
| 10 |
-
3
|
| 11 |
-
],
|
| 12 |
-
"downsample_in_first_stage": false,
|
| 13 |
-
"embedding_size": 64,
|
| 14 |
-
"hidden_act": "relu",
|
| 15 |
-
"hidden_sizes": [
|
| 16 |
-
256,
|
| 17 |
-
512,
|
| 18 |
-
1024,
|
| 19 |
-
2048
|
| 20 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"id2label": {
|
| 22 |
"0": "angry",
|
| 23 |
"1": "happy",
|
| 24 |
"2": "neutral",
|
| 25 |
"3": "sad"
|
| 26 |
},
|
|
|
|
|
|
|
|
|
|
| 27 |
"label2id": {
|
| 28 |
"angry": "0",
|
| 29 |
"happy": "1",
|
| 30 |
"neutral": "2",
|
| 31 |
"sad": "3"
|
| 32 |
},
|
| 33 |
-
"
|
| 34 |
-
"model_type": "
|
|
|
|
| 35 |
"num_channels": 3,
|
|
|
|
|
|
|
| 36 |
"problem_type": "single_label_classification",
|
|
|
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
"transformers_version": "4.24.0.dev0"
|
| 39 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 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": "angry",
|
| 13 |
"1": "happy",
|
| 14 |
"2": "neutral",
|
| 15 |
"3": "sad"
|
| 16 |
},
|
| 17 |
+
"image_size": 224,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
"label2id": {
|
| 21 |
"angry": "0",
|
| 22 |
"happy": "1",
|
| 23 |
"neutral": "2",
|
| 24 |
"sad": "3"
|
| 25 |
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"model_type": "vit",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
"num_channels": 3,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"patch_size": 16,
|
| 32 |
"problem_type": "single_label_classification",
|
| 33 |
+
"qkv_bias": true,
|
| 34 |
"torch_dtype": "float32",
|
| 35 |
"transformers_version": "4.24.0.dev0"
|
| 36 |
}
|
preprocessor_config.json
CHANGED
|
@@ -1,18 +1,17 @@
|
|
| 1 |
{
|
| 2 |
-
"crop_pct": 0.875,
|
| 3 |
"do_normalize": true,
|
| 4 |
"do_resize": true,
|
| 5 |
-
"feature_extractor_type": "
|
| 6 |
"image_mean": [
|
| 7 |
-
0.
|
| 8 |
-
0.
|
| 9 |
-
0.
|
| 10 |
],
|
| 11 |
"image_std": [
|
| 12 |
-
0.
|
| 13 |
-
0.
|
| 14 |
-
0.
|
| 15 |
],
|
| 16 |
-
"resample":
|
| 17 |
"size": 224
|
| 18 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"do_normalize": true,
|
| 3 |
"do_resize": true,
|
| 4 |
+
"feature_extractor_type": "ViTFeatureExtractor",
|
| 5 |
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
],
|
| 10 |
"image_std": [
|
| 11 |
+
0.5,
|
| 12 |
+
0.5,
|
| 13 |
+
0.5
|
| 14 |
],
|
| 15 |
+
"resample": 2,
|
| 16 |
"size": 224
|
| 17 |
}
|
pytorch_model.bin
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:db408178bedaa6a5998bbb33212b113713f11eca99a0d912b0f908332844cca6
|
| 3 |
+
size 343273137
|
runs/Jan21_17-13-54_teesta/events.out.tfevents.1674301465.teesta.3779.0
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:ac1fbc022de3170b19d2227e0b53ffe7cce1dc5b96de754201894eb433c5e931
|
| 3 |
+
size 15567
|
runs/Jan21_17-25-09_teesta/1674302123.4912503/events.out.tfevents.1674302123.teesta.7894.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:965e196ff0c4b59fda1585981e171208c301e747b37824dd74dc199cc67bee5d
|
| 3 |
+
size 5550
|
runs/Jan21_17-25-09_teesta/events.out.tfevents.1674302123.teesta.7894.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d9175c9096796091c491259ff069f27b0176aad150041384a2d7603a97c818f
|
| 3 |
+
size 4327
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"total_flos": 7.403951867151974e+17,
|
| 4 |
+
"train_loss": 1.1767685549599785,
|
| 5 |
+
"train_runtime": 421.2758,
|
| 6 |
+
"train_samples_per_second": 82.749,
|
| 7 |
+
"train_steps_per_second": 0.332
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,349 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5711009174311926,
|
| 3 |
+
"best_model_checkpoint": "microsoft-resnet-50-cartoon-emotion-detection/checkpoint-133",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"global_step": 140,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 1.0,
|
| 12 |
+
"eval_accuracy": 0.25688073394495414,
|
| 13 |
+
"eval_f1": 0.22448538034486407,
|
| 14 |
+
"eval_loss": 1.380691409111023,
|
| 15 |
+
"eval_precision": 0.234238207374522,
|
| 16 |
+
"eval_recall": 0.25688073394495414,
|
| 17 |
+
"eval_runtime": 6.8682,
|
| 18 |
+
"eval_samples_per_second": 63.481,
|
| 19 |
+
"eval_steps_per_second": 1.019,
|
| 20 |
+
"step": 7
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.43,
|
| 24 |
+
"learning_rate": 8.571428571428571e-05,
|
| 25 |
+
"loss": 1.3806,
|
| 26 |
+
"step": 10
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.0,
|
| 30 |
+
"eval_accuracy": 0.36009174311926606,
|
| 31 |
+
"eval_f1": 0.27057592620444176,
|
| 32 |
+
"eval_loss": 1.3620387315750122,
|
| 33 |
+
"eval_precision": 0.3636846359984286,
|
| 34 |
+
"eval_recall": 0.36009174311926606,
|
| 35 |
+
"eval_runtime": 6.2511,
|
| 36 |
+
"eval_samples_per_second": 69.748,
|
| 37 |
+
"eval_steps_per_second": 1.12,
|
| 38 |
+
"step": 14
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.86,
|
| 42 |
+
"learning_rate": 0.00011428571428571428,
|
| 43 |
+
"loss": 1.3591,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_accuracy": 0.3669724770642202,
|
| 49 |
+
"eval_f1": 0.24291286665824255,
|
| 50 |
+
"eval_loss": 1.3456730842590332,
|
| 51 |
+
"eval_precision": 0.5651041088181502,
|
| 52 |
+
"eval_recall": 0.3669724770642202,
|
| 53 |
+
"eval_runtime": 5.6933,
|
| 54 |
+
"eval_samples_per_second": 76.582,
|
| 55 |
+
"eval_steps_per_second": 1.23,
|
| 56 |
+
"step": 21
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.0,
|
| 60 |
+
"eval_accuracy": 0.3738532110091743,
|
| 61 |
+
"eval_f1": 0.2447258618599714,
|
| 62 |
+
"eval_loss": 1.3271173238754272,
|
| 63 |
+
"eval_precision": 0.7011109363353202,
|
| 64 |
+
"eval_recall": 0.3738532110091743,
|
| 65 |
+
"eval_runtime": 5.6438,
|
| 66 |
+
"eval_samples_per_second": 77.253,
|
| 67 |
+
"eval_steps_per_second": 1.24,
|
| 68 |
+
"step": 28
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.29,
|
| 72 |
+
"learning_rate": 0.00010476190476190477,
|
| 73 |
+
"loss": 1.3344,
|
| 74 |
+
"step": 30
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 5.0,
|
| 78 |
+
"eval_accuracy": 0.3922018348623853,
|
| 79 |
+
"eval_f1": 0.27454202142043693,
|
| 80 |
+
"eval_loss": 1.3076415061950684,
|
| 81 |
+
"eval_precision": 0.49126041854050495,
|
| 82 |
+
"eval_recall": 0.3922018348623853,
|
| 83 |
+
"eval_runtime": 5.7497,
|
| 84 |
+
"eval_samples_per_second": 75.83,
|
| 85 |
+
"eval_steps_per_second": 1.217,
|
| 86 |
+
"step": 35
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.71,
|
| 90 |
+
"learning_rate": 9.523809523809524e-05,
|
| 91 |
+
"loss": 1.3035,
|
| 92 |
+
"step": 40
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.0,
|
| 96 |
+
"eval_accuracy": 0.4197247706422018,
|
| 97 |
+
"eval_f1": 0.31223198015887665,
|
| 98 |
+
"eval_loss": 1.2836155891418457,
|
| 99 |
+
"eval_precision": 0.4326493440983179,
|
| 100 |
+
"eval_recall": 0.4197247706422018,
|
| 101 |
+
"eval_runtime": 6.0675,
|
| 102 |
+
"eval_samples_per_second": 71.858,
|
| 103 |
+
"eval_steps_per_second": 1.154,
|
| 104 |
+
"step": 42
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"eval_accuracy": 0.4426605504587156,
|
| 109 |
+
"eval_f1": 0.341877970822925,
|
| 110 |
+
"eval_loss": 1.2649825811386108,
|
| 111 |
+
"eval_precision": 0.49930570990337153,
|
| 112 |
+
"eval_recall": 0.4426605504587156,
|
| 113 |
+
"eval_runtime": 5.7091,
|
| 114 |
+
"eval_samples_per_second": 76.37,
|
| 115 |
+
"eval_steps_per_second": 1.226,
|
| 116 |
+
"step": 49
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.14,
|
| 120 |
+
"learning_rate": 8.571428571428571e-05,
|
| 121 |
+
"loss": 1.2692,
|
| 122 |
+
"step": 50
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 8.0,
|
| 126 |
+
"eval_accuracy": 0.4701834862385321,
|
| 127 |
+
"eval_f1": 0.3759489302967564,
|
| 128 |
+
"eval_loss": 1.2467858791351318,
|
| 129 |
+
"eval_precision": 0.47456408321388993,
|
| 130 |
+
"eval_recall": 0.4701834862385321,
|
| 131 |
+
"eval_runtime": 5.6802,
|
| 132 |
+
"eval_samples_per_second": 76.758,
|
| 133 |
+
"eval_steps_per_second": 1.232,
|
| 134 |
+
"step": 56
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 8.57,
|
| 138 |
+
"learning_rate": 7.619047619047618e-05,
|
| 139 |
+
"loss": 1.2271,
|
| 140 |
+
"step": 60
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 9.0,
|
| 144 |
+
"eval_accuracy": 0.47706422018348627,
|
| 145 |
+
"eval_f1": 0.38295063344511215,
|
| 146 |
+
"eval_loss": 1.2168828248977661,
|
| 147 |
+
"eval_precision": 0.4426797391546095,
|
| 148 |
+
"eval_recall": 0.47706422018348627,
|
| 149 |
+
"eval_runtime": 5.7354,
|
| 150 |
+
"eval_samples_per_second": 76.019,
|
| 151 |
+
"eval_steps_per_second": 1.22,
|
| 152 |
+
"step": 63
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 10.0,
|
| 156 |
+
"learning_rate": 6.666666666666667e-05,
|
| 157 |
+
"loss": 1.1897,
|
| 158 |
+
"step": 70
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.0,
|
| 162 |
+
"eval_accuracy": 0.4908256880733945,
|
| 163 |
+
"eval_f1": 0.40018913464018235,
|
| 164 |
+
"eval_loss": 1.1914395093917847,
|
| 165 |
+
"eval_precision": 0.4465401552610121,
|
| 166 |
+
"eval_recall": 0.4908256880733945,
|
| 167 |
+
"eval_runtime": 5.8725,
|
| 168 |
+
"eval_samples_per_second": 74.244,
|
| 169 |
+
"eval_steps_per_second": 1.192,
|
| 170 |
+
"step": 70
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 11.0,
|
| 174 |
+
"eval_accuracy": 0.5137614678899083,
|
| 175 |
+
"eval_f1": 0.4264259625764651,
|
| 176 |
+
"eval_loss": 1.1677685976028442,
|
| 177 |
+
"eval_precision": 0.6977269943419414,
|
| 178 |
+
"eval_recall": 0.5137614678899083,
|
| 179 |
+
"eval_runtime": 5.9101,
|
| 180 |
+
"eval_samples_per_second": 73.772,
|
| 181 |
+
"eval_steps_per_second": 1.184,
|
| 182 |
+
"step": 77
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 11.43,
|
| 186 |
+
"learning_rate": 5.714285714285714e-05,
|
| 187 |
+
"loss": 1.1449,
|
| 188 |
+
"step": 80
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 12.0,
|
| 192 |
+
"eval_accuracy": 0.5137614678899083,
|
| 193 |
+
"eval_f1": 0.42019701825907374,
|
| 194 |
+
"eval_loss": 1.1410157680511475,
|
| 195 |
+
"eval_precision": 0.4223060434667934,
|
| 196 |
+
"eval_recall": 0.5137614678899083,
|
| 197 |
+
"eval_runtime": 5.68,
|
| 198 |
+
"eval_samples_per_second": 76.761,
|
| 199 |
+
"eval_steps_per_second": 1.232,
|
| 200 |
+
"step": 84
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 12.86,
|
| 204 |
+
"learning_rate": 4.761904761904762e-05,
|
| 205 |
+
"loss": 1.1103,
|
| 206 |
+
"step": 90
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 13.0,
|
| 210 |
+
"eval_accuracy": 0.5435779816513762,
|
| 211 |
+
"eval_f1": 0.45463643608379634,
|
| 212 |
+
"eval_loss": 1.1230803728103638,
|
| 213 |
+
"eval_precision": 0.4453251266498374,
|
| 214 |
+
"eval_recall": 0.5435779816513762,
|
| 215 |
+
"eval_runtime": 5.6703,
|
| 216 |
+
"eval_samples_per_second": 76.892,
|
| 217 |
+
"eval_steps_per_second": 1.235,
|
| 218 |
+
"step": 91
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 14.0,
|
| 222 |
+
"eval_accuracy": 0.5527522935779816,
|
| 223 |
+
"eval_f1": 0.46754301809966226,
|
| 224 |
+
"eval_loss": 1.102858066558838,
|
| 225 |
+
"eval_precision": 0.4585875088630616,
|
| 226 |
+
"eval_recall": 0.5527522935779816,
|
| 227 |
+
"eval_runtime": 5.6798,
|
| 228 |
+
"eval_samples_per_second": 76.764,
|
| 229 |
+
"eval_steps_per_second": 1.232,
|
| 230 |
+
"step": 98
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 14.29,
|
| 234 |
+
"learning_rate": 3.809523809523809e-05,
|
| 235 |
+
"loss": 1.0763,
|
| 236 |
+
"step": 100
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 15.0,
|
| 240 |
+
"eval_accuracy": 0.5458715596330275,
|
| 241 |
+
"eval_f1": 0.4634974694985357,
|
| 242 |
+
"eval_loss": 1.0851385593414307,
|
| 243 |
+
"eval_precision": 0.6996862082871257,
|
| 244 |
+
"eval_recall": 0.5458715596330275,
|
| 245 |
+
"eval_runtime": 6.8058,
|
| 246 |
+
"eval_samples_per_second": 64.063,
|
| 247 |
+
"eval_steps_per_second": 1.029,
|
| 248 |
+
"step": 105
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 15.71,
|
| 252 |
+
"learning_rate": 2.857142857142857e-05,
|
| 253 |
+
"loss": 1.0496,
|
| 254 |
+
"step": 110
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 16.0,
|
| 258 |
+
"eval_accuracy": 0.5688073394495413,
|
| 259 |
+
"eval_f1": 0.48620627733329547,
|
| 260 |
+
"eval_loss": 1.0685973167419434,
|
| 261 |
+
"eval_precision": 0.5379831413851768,
|
| 262 |
+
"eval_recall": 0.5688073394495413,
|
| 263 |
+
"eval_runtime": 5.6811,
|
| 264 |
+
"eval_samples_per_second": 76.746,
|
| 265 |
+
"eval_steps_per_second": 1.232,
|
| 266 |
+
"step": 112
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 17.0,
|
| 270 |
+
"eval_accuracy": 0.5527522935779816,
|
| 271 |
+
"eval_f1": 0.4768952189953553,
|
| 272 |
+
"eval_loss": 1.0685114860534668,
|
| 273 |
+
"eval_precision": 0.597456441198868,
|
| 274 |
+
"eval_recall": 0.5527522935779816,
|
| 275 |
+
"eval_runtime": 5.7578,
|
| 276 |
+
"eval_samples_per_second": 75.723,
|
| 277 |
+
"eval_steps_per_second": 1.216,
|
| 278 |
+
"step": 119
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 17.14,
|
| 282 |
+
"learning_rate": 1.9047619047619046e-05,
|
| 283 |
+
"loss": 1.0178,
|
| 284 |
+
"step": 120
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 18.0,
|
| 288 |
+
"eval_accuracy": 0.5435779816513762,
|
| 289 |
+
"eval_f1": 0.4674479767067327,
|
| 290 |
+
"eval_loss": 1.0596745014190674,
|
| 291 |
+
"eval_precision": 0.5879862703091682,
|
| 292 |
+
"eval_recall": 0.5435779816513762,
|
| 293 |
+
"eval_runtime": 5.6723,
|
| 294 |
+
"eval_samples_per_second": 76.865,
|
| 295 |
+
"eval_steps_per_second": 1.234,
|
| 296 |
+
"step": 126
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 18.57,
|
| 300 |
+
"learning_rate": 9.523809523809523e-06,
|
| 301 |
+
"loss": 1.0127,
|
| 302 |
+
"step": 130
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 19.0,
|
| 306 |
+
"eval_accuracy": 0.5711009174311926,
|
| 307 |
+
"eval_f1": 0.49584804868136073,
|
| 308 |
+
"eval_loss": 1.0444973707199097,
|
| 309 |
+
"eval_precision": 0.6083837079452298,
|
| 310 |
+
"eval_recall": 0.5711009174311926,
|
| 311 |
+
"eval_runtime": 5.7997,
|
| 312 |
+
"eval_samples_per_second": 75.176,
|
| 313 |
+
"eval_steps_per_second": 1.207,
|
| 314 |
+
"step": 133
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 20.0,
|
| 318 |
+
"learning_rate": 0.0,
|
| 319 |
+
"loss": 0.9996,
|
| 320 |
+
"step": 140
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 20.0,
|
| 324 |
+
"eval_accuracy": 0.5642201834862385,
|
| 325 |
+
"eval_f1": 0.4813301262382135,
|
| 326 |
+
"eval_loss": 1.0442301034927368,
|
| 327 |
+
"eval_precision": 0.5786388539620291,
|
| 328 |
+
"eval_recall": 0.5642201834862385,
|
| 329 |
+
"eval_runtime": 5.7325,
|
| 330 |
+
"eval_samples_per_second": 76.058,
|
| 331 |
+
"eval_steps_per_second": 1.221,
|
| 332 |
+
"step": 140
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 20.0,
|
| 336 |
+
"step": 140,
|
| 337 |
+
"total_flos": 7.403951867151974e+17,
|
| 338 |
+
"train_loss": 1.1767685549599785,
|
| 339 |
+
"train_runtime": 421.2758,
|
| 340 |
+
"train_samples_per_second": 82.749,
|
| 341 |
+
"train_steps_per_second": 0.332
|
| 342 |
+
}
|
| 343 |
+
],
|
| 344 |
+
"max_steps": 140,
|
| 345 |
+
"num_train_epochs": 20,
|
| 346 |
+
"total_flos": 7.403951867151974e+17,
|
| 347 |
+
"trial_name": null,
|
| 348 |
+
"trial_params": null
|
| 349 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3439
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:876d7e78c817fe779bc15169c094ee092e47bccd8d6e39205df03f212a0caa14
|
| 3 |
size 3439
|