Training in progress, epoch 8, checkpoint
Browse files- checkpoint-452/config.json +96 -0
- checkpoint-452/model.safetensors +3 -0
- checkpoint-452/optimizer.pt +3 -0
- checkpoint-452/preprocessor_config.json +9 -0
- checkpoint-452/rng_state.pth +3 -0
- checkpoint-452/scheduler.pt +3 -0
- checkpoint-452/trainer_state.json +631 -0
- checkpoint-452/training_args.bin +3 -0
checkpoint-452/config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ntu-spml/distilhubert",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_norm": "group",
|
| 45 |
+
"feat_proj_dropout": 0.0,
|
| 46 |
+
"feat_proj_layer_norm": false,
|
| 47 |
+
"final_dropout": 0.0,
|
| 48 |
+
"hidden_act": "gelu",
|
| 49 |
+
"hidden_dropout": 0.1,
|
| 50 |
+
"hidden_size": 768,
|
| 51 |
+
"id2label": {
|
| 52 |
+
"0": "blues",
|
| 53 |
+
"1": "classical",
|
| 54 |
+
"2": "country",
|
| 55 |
+
"3": "disco",
|
| 56 |
+
"4": "hiphop",
|
| 57 |
+
"5": "jazz",
|
| 58 |
+
"6": "metal",
|
| 59 |
+
"7": "pop",
|
| 60 |
+
"8": "reggae",
|
| 61 |
+
"9": "rock"
|
| 62 |
+
},
|
| 63 |
+
"initializer_range": 0.02,
|
| 64 |
+
"intermediate_size": 3072,
|
| 65 |
+
"label2id": {
|
| 66 |
+
"blues": "0",
|
| 67 |
+
"classical": "1",
|
| 68 |
+
"country": "2",
|
| 69 |
+
"disco": "3",
|
| 70 |
+
"hiphop": "4",
|
| 71 |
+
"jazz": "5",
|
| 72 |
+
"metal": "6",
|
| 73 |
+
"pop": "7",
|
| 74 |
+
"reggae": "8",
|
| 75 |
+
"rock": "9"
|
| 76 |
+
},
|
| 77 |
+
"layer_norm_eps": 1e-05,
|
| 78 |
+
"layerdrop": 0.0,
|
| 79 |
+
"mask_feature_length": 10,
|
| 80 |
+
"mask_feature_min_masks": 0,
|
| 81 |
+
"mask_feature_prob": 0.0,
|
| 82 |
+
"mask_time_length": 10,
|
| 83 |
+
"mask_time_min_masks": 2,
|
| 84 |
+
"mask_time_prob": 0.05,
|
| 85 |
+
"model_type": "hubert",
|
| 86 |
+
"num_attention_heads": 12,
|
| 87 |
+
"num_conv_pos_embedding_groups": 16,
|
| 88 |
+
"num_conv_pos_embeddings": 128,
|
| 89 |
+
"num_feat_extract_layers": 7,
|
| 90 |
+
"num_hidden_layers": 2,
|
| 91 |
+
"pad_token_id": 0,
|
| 92 |
+
"torch_dtype": "float32",
|
| 93 |
+
"transformers_version": "4.35.2",
|
| 94 |
+
"use_weighted_layer_sum": false,
|
| 95 |
+
"vocab_size": 32
|
| 96 |
+
}
|
checkpoint-452/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1514e57a3f653367171eb05bd2f5654e3a45e8fed7450344b4b63cad80df99
|
| 3 |
+
size 94771728
|
checkpoint-452/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92518a67883bf5877461fceda01282bbde67b53dceae603859dfbc0ecd51bd5f
|
| 3 |
+
size 189575930
|
checkpoint-452/preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": true,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|
checkpoint-452/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b18cbc1584d59e5b5a244ac6734973516afc01e0044dabd8131bd9170dfbcfd8
|
| 3 |
+
size 14244
|
checkpoint-452/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1605b713fb22bd170d973a08e19c70f9207380be060cacde0d2489b37b44edf8
|
| 3 |
+
size 1064
|
checkpoint-452/trainer_state.json
ADDED
|
@@ -0,0 +1,631 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.79,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-gtzan/checkpoint-395",
|
| 4 |
+
"epoch": 8.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 452,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.09,
|
| 13 |
+
"learning_rate": 4.464285714285714e-05,
|
| 14 |
+
"loss": 2.2976,
|
| 15 |
+
"step": 5
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.18,
|
| 19 |
+
"learning_rate": 8.928571428571429e-05,
|
| 20 |
+
"loss": 2.2855,
|
| 21 |
+
"step": 10
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.27,
|
| 25 |
+
"learning_rate": 0.00013392857142857144,
|
| 26 |
+
"loss": 2.2307,
|
| 27 |
+
"step": 15
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.35,
|
| 31 |
+
"learning_rate": 0.00017857142857142857,
|
| 32 |
+
"loss": 2.1327,
|
| 33 |
+
"step": 20
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.44,
|
| 37 |
+
"learning_rate": 0.00022321428571428573,
|
| 38 |
+
"loss": 2.0339,
|
| 39 |
+
"step": 25
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.53,
|
| 43 |
+
"learning_rate": 0.00026785714285714287,
|
| 44 |
+
"loss": 1.9633,
|
| 45 |
+
"step": 30
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.62,
|
| 49 |
+
"learning_rate": 0.0003125,
|
| 50 |
+
"loss": 1.8021,
|
| 51 |
+
"step": 35
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.71,
|
| 55 |
+
"learning_rate": 0.00035714285714285714,
|
| 56 |
+
"loss": 1.6938,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.8,
|
| 61 |
+
"learning_rate": 0.00040178571428571433,
|
| 62 |
+
"loss": 1.5271,
|
| 63 |
+
"step": 45
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.88,
|
| 67 |
+
"learning_rate": 0.00044642857142857147,
|
| 68 |
+
"loss": 1.4038,
|
| 69 |
+
"step": 50
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.97,
|
| 73 |
+
"learning_rate": 0.0004910714285714286,
|
| 74 |
+
"loss": 1.496,
|
| 75 |
+
"step": 55
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.99,
|
| 79 |
+
"eval_accuracy": 0.27,
|
| 80 |
+
"eval_loss": 1.8467493057250977,
|
| 81 |
+
"eval_runtime": 72.5718,
|
| 82 |
+
"eval_samples_per_second": 1.378,
|
| 83 |
+
"eval_steps_per_second": 0.179,
|
| 84 |
+
"step": 56
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.06,
|
| 88 |
+
"learning_rate": 0.000496031746031746,
|
| 89 |
+
"loss": 1.3528,
|
| 90 |
+
"step": 60
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.15,
|
| 94 |
+
"learning_rate": 0.0004910714285714286,
|
| 95 |
+
"loss": 1.507,
|
| 96 |
+
"step": 65
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.24,
|
| 100 |
+
"learning_rate": 0.0004861111111111111,
|
| 101 |
+
"loss": 1.504,
|
| 102 |
+
"step": 70
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.33,
|
| 106 |
+
"learning_rate": 0.0004811507936507937,
|
| 107 |
+
"loss": 1.3719,
|
| 108 |
+
"step": 75
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.42,
|
| 112 |
+
"learning_rate": 0.0004761904761904762,
|
| 113 |
+
"loss": 1.2284,
|
| 114 |
+
"step": 80
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.5,
|
| 118 |
+
"learning_rate": 0.00047123015873015874,
|
| 119 |
+
"loss": 1.2997,
|
| 120 |
+
"step": 85
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.59,
|
| 124 |
+
"learning_rate": 0.0004662698412698413,
|
| 125 |
+
"loss": 1.2284,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.68,
|
| 130 |
+
"learning_rate": 0.00046130952380952383,
|
| 131 |
+
"loss": 1.3332,
|
| 132 |
+
"step": 95
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.77,
|
| 136 |
+
"learning_rate": 0.0004563492063492063,
|
| 137 |
+
"loss": 1.1091,
|
| 138 |
+
"step": 100
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.86,
|
| 142 |
+
"learning_rate": 0.0004513888888888889,
|
| 143 |
+
"loss": 1.1335,
|
| 144 |
+
"step": 105
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.95,
|
| 148 |
+
"learning_rate": 0.00044642857142857147,
|
| 149 |
+
"loss": 1.1313,
|
| 150 |
+
"step": 110
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.0,
|
| 154 |
+
"eval_accuracy": 0.61,
|
| 155 |
+
"eval_loss": 1.175675868988037,
|
| 156 |
+
"eval_runtime": 71.9077,
|
| 157 |
+
"eval_samples_per_second": 1.391,
|
| 158 |
+
"eval_steps_per_second": 0.181,
|
| 159 |
+
"step": 113
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.04,
|
| 163 |
+
"learning_rate": 0.00044146825396825396,
|
| 164 |
+
"loss": 1.1765,
|
| 165 |
+
"step": 115
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.12,
|
| 169 |
+
"learning_rate": 0.0004365079365079365,
|
| 170 |
+
"loss": 1.0945,
|
| 171 |
+
"step": 120
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.21,
|
| 175 |
+
"learning_rate": 0.00043154761904761905,
|
| 176 |
+
"loss": 0.9198,
|
| 177 |
+
"step": 125
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.3,
|
| 181 |
+
"learning_rate": 0.0004265873015873016,
|
| 182 |
+
"loss": 1.1504,
|
| 183 |
+
"step": 130
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 2.39,
|
| 187 |
+
"learning_rate": 0.00042162698412698415,
|
| 188 |
+
"loss": 1.03,
|
| 189 |
+
"step": 135
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 2.48,
|
| 193 |
+
"learning_rate": 0.0004166666666666667,
|
| 194 |
+
"loss": 1.294,
|
| 195 |
+
"step": 140
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.57,
|
| 199 |
+
"learning_rate": 0.0004117063492063492,
|
| 200 |
+
"loss": 0.918,
|
| 201 |
+
"step": 145
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.65,
|
| 205 |
+
"learning_rate": 0.00040674603174603173,
|
| 206 |
+
"loss": 0.9529,
|
| 207 |
+
"step": 150
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.74,
|
| 211 |
+
"learning_rate": 0.00040178571428571433,
|
| 212 |
+
"loss": 0.9366,
|
| 213 |
+
"step": 155
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.83,
|
| 217 |
+
"learning_rate": 0.0003968253968253968,
|
| 218 |
+
"loss": 0.9388,
|
| 219 |
+
"step": 160
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.92,
|
| 223 |
+
"learning_rate": 0.00039186507936507937,
|
| 224 |
+
"loss": 1.2432,
|
| 225 |
+
"step": 165
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.99,
|
| 229 |
+
"eval_accuracy": 0.58,
|
| 230 |
+
"eval_loss": 1.3774330615997314,
|
| 231 |
+
"eval_runtime": 72.0805,
|
| 232 |
+
"eval_samples_per_second": 1.387,
|
| 233 |
+
"eval_steps_per_second": 0.18,
|
| 234 |
+
"step": 169
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.01,
|
| 238 |
+
"learning_rate": 0.0003869047619047619,
|
| 239 |
+
"loss": 0.8342,
|
| 240 |
+
"step": 170
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.1,
|
| 244 |
+
"learning_rate": 0.0003819444444444444,
|
| 245 |
+
"loss": 1.2782,
|
| 246 |
+
"step": 175
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.19,
|
| 250 |
+
"learning_rate": 0.000376984126984127,
|
| 251 |
+
"loss": 0.9997,
|
| 252 |
+
"step": 180
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.27,
|
| 256 |
+
"learning_rate": 0.00037202380952380956,
|
| 257 |
+
"loss": 0.6668,
|
| 258 |
+
"step": 185
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 3.36,
|
| 262 |
+
"learning_rate": 0.00036706349206349205,
|
| 263 |
+
"loss": 0.7267,
|
| 264 |
+
"step": 190
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.45,
|
| 268 |
+
"learning_rate": 0.0003621031746031746,
|
| 269 |
+
"loss": 0.892,
|
| 270 |
+
"step": 195
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 3.54,
|
| 274 |
+
"learning_rate": 0.00035714285714285714,
|
| 275 |
+
"loss": 1.0096,
|
| 276 |
+
"step": 200
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.63,
|
| 280 |
+
"learning_rate": 0.0003521825396825397,
|
| 281 |
+
"loss": 0.8909,
|
| 282 |
+
"step": 205
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.72,
|
| 286 |
+
"learning_rate": 0.00034722222222222224,
|
| 287 |
+
"loss": 1.0591,
|
| 288 |
+
"step": 210
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 3.81,
|
| 292 |
+
"learning_rate": 0.0003422619047619048,
|
| 293 |
+
"loss": 0.6526,
|
| 294 |
+
"step": 215
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 3.89,
|
| 298 |
+
"learning_rate": 0.00033730158730158733,
|
| 299 |
+
"loss": 0.847,
|
| 300 |
+
"step": 220
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.98,
|
| 304 |
+
"learning_rate": 0.0003323412698412698,
|
| 305 |
+
"loss": 0.7301,
|
| 306 |
+
"step": 225
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 4.0,
|
| 310 |
+
"eval_accuracy": 0.66,
|
| 311 |
+
"eval_loss": 0.9738250970840454,
|
| 312 |
+
"eval_runtime": 70.9865,
|
| 313 |
+
"eval_samples_per_second": 1.409,
|
| 314 |
+
"eval_steps_per_second": 0.183,
|
| 315 |
+
"step": 226
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 4.07,
|
| 319 |
+
"learning_rate": 0.00032738095238095237,
|
| 320 |
+
"loss": 0.8506,
|
| 321 |
+
"step": 230
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.16,
|
| 325 |
+
"learning_rate": 0.00032242063492063497,
|
| 326 |
+
"loss": 0.642,
|
| 327 |
+
"step": 235
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 4.25,
|
| 331 |
+
"learning_rate": 0.00031746031746031746,
|
| 332 |
+
"loss": 0.6132,
|
| 333 |
+
"step": 240
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.34,
|
| 337 |
+
"learning_rate": 0.0003125,
|
| 338 |
+
"loss": 0.6279,
|
| 339 |
+
"step": 245
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.42,
|
| 343 |
+
"learning_rate": 0.00030753968253968255,
|
| 344 |
+
"loss": 0.7194,
|
| 345 |
+
"step": 250
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.51,
|
| 349 |
+
"learning_rate": 0.00030257936507936505,
|
| 350 |
+
"loss": 0.7127,
|
| 351 |
+
"step": 255
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 4.6,
|
| 355 |
+
"learning_rate": 0.00029761904761904765,
|
| 356 |
+
"loss": 0.5318,
|
| 357 |
+
"step": 260
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 4.69,
|
| 361 |
+
"learning_rate": 0.0002926587301587302,
|
| 362 |
+
"loss": 0.7127,
|
| 363 |
+
"step": 265
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 4.78,
|
| 367 |
+
"learning_rate": 0.0002876984126984127,
|
| 368 |
+
"loss": 0.5685,
|
| 369 |
+
"step": 270
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 4.87,
|
| 373 |
+
"learning_rate": 0.00028273809523809523,
|
| 374 |
+
"loss": 0.6034,
|
| 375 |
+
"step": 275
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.96,
|
| 379 |
+
"learning_rate": 0.0002777777777777778,
|
| 380 |
+
"loss": 0.5192,
|
| 381 |
+
"step": 280
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.99,
|
| 385 |
+
"eval_accuracy": 0.73,
|
| 386 |
+
"eval_loss": 0.9078372120857239,
|
| 387 |
+
"eval_runtime": 71.0414,
|
| 388 |
+
"eval_samples_per_second": 1.408,
|
| 389 |
+
"eval_steps_per_second": 0.183,
|
| 390 |
+
"step": 282
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 5.04,
|
| 394 |
+
"learning_rate": 0.0002728174603174603,
|
| 395 |
+
"loss": 0.4625,
|
| 396 |
+
"step": 285
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.13,
|
| 400 |
+
"learning_rate": 0.00026785714285714287,
|
| 401 |
+
"loss": 0.5618,
|
| 402 |
+
"step": 290
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.22,
|
| 406 |
+
"learning_rate": 0.0002628968253968254,
|
| 407 |
+
"loss": 0.4268,
|
| 408 |
+
"step": 295
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.31,
|
| 412 |
+
"learning_rate": 0.00025793650793650796,
|
| 413 |
+
"loss": 0.545,
|
| 414 |
+
"step": 300
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 5.4,
|
| 418 |
+
"learning_rate": 0.00025297619047619046,
|
| 419 |
+
"loss": 0.4513,
|
| 420 |
+
"step": 305
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 5.49,
|
| 424 |
+
"learning_rate": 0.000248015873015873,
|
| 425 |
+
"loss": 0.4566,
|
| 426 |
+
"step": 310
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.58,
|
| 430 |
+
"learning_rate": 0.00024305555555555555,
|
| 431 |
+
"loss": 0.4533,
|
| 432 |
+
"step": 315
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.66,
|
| 436 |
+
"learning_rate": 0.0002380952380952381,
|
| 437 |
+
"loss": 0.4453,
|
| 438 |
+
"step": 320
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 5.75,
|
| 442 |
+
"learning_rate": 0.00023313492063492064,
|
| 443 |
+
"loss": 0.4401,
|
| 444 |
+
"step": 325
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 5.84,
|
| 448 |
+
"learning_rate": 0.00022817460317460316,
|
| 449 |
+
"loss": 0.3283,
|
| 450 |
+
"step": 330
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 5.93,
|
| 454 |
+
"learning_rate": 0.00022321428571428573,
|
| 455 |
+
"loss": 0.4163,
|
| 456 |
+
"step": 335
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 6.0,
|
| 460 |
+
"eval_accuracy": 0.71,
|
| 461 |
+
"eval_loss": 0.9995945692062378,
|
| 462 |
+
"eval_runtime": 71.0596,
|
| 463 |
+
"eval_samples_per_second": 1.407,
|
| 464 |
+
"eval_steps_per_second": 0.183,
|
| 465 |
+
"step": 339
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 6.02,
|
| 469 |
+
"learning_rate": 0.00021825396825396825,
|
| 470 |
+
"loss": 0.3108,
|
| 471 |
+
"step": 340
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.11,
|
| 475 |
+
"learning_rate": 0.0002132936507936508,
|
| 476 |
+
"loss": 0.2346,
|
| 477 |
+
"step": 345
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 6.19,
|
| 481 |
+
"learning_rate": 0.00020833333333333335,
|
| 482 |
+
"loss": 0.2996,
|
| 483 |
+
"step": 350
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 6.28,
|
| 487 |
+
"learning_rate": 0.00020337301587301587,
|
| 488 |
+
"loss": 0.2248,
|
| 489 |
+
"step": 355
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 6.37,
|
| 493 |
+
"learning_rate": 0.0001984126984126984,
|
| 494 |
+
"loss": 0.2535,
|
| 495 |
+
"step": 360
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 6.46,
|
| 499 |
+
"learning_rate": 0.00019345238095238096,
|
| 500 |
+
"loss": 0.1705,
|
| 501 |
+
"step": 365
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 6.55,
|
| 505 |
+
"learning_rate": 0.0001884920634920635,
|
| 506 |
+
"loss": 0.2647,
|
| 507 |
+
"step": 370
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 6.64,
|
| 511 |
+
"learning_rate": 0.00018353174603174602,
|
| 512 |
+
"loss": 0.3173,
|
| 513 |
+
"step": 375
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 6.73,
|
| 517 |
+
"learning_rate": 0.00017857142857142857,
|
| 518 |
+
"loss": 0.2563,
|
| 519 |
+
"step": 380
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 6.81,
|
| 523 |
+
"learning_rate": 0.00017361111111111112,
|
| 524 |
+
"loss": 0.0983,
|
| 525 |
+
"step": 385
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 6.9,
|
| 529 |
+
"learning_rate": 0.00016865079365079366,
|
| 530 |
+
"loss": 0.5197,
|
| 531 |
+
"step": 390
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 6.99,
|
| 535 |
+
"learning_rate": 0.00016369047619047618,
|
| 536 |
+
"loss": 0.2178,
|
| 537 |
+
"step": 395
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 6.99,
|
| 541 |
+
"eval_accuracy": 0.79,
|
| 542 |
+
"eval_loss": 0.7682663202285767,
|
| 543 |
+
"eval_runtime": 71.9225,
|
| 544 |
+
"eval_samples_per_second": 1.39,
|
| 545 |
+
"eval_steps_per_second": 0.181,
|
| 546 |
+
"step": 395
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 7.08,
|
| 550 |
+
"learning_rate": 0.00015873015873015873,
|
| 551 |
+
"loss": 0.125,
|
| 552 |
+
"step": 400
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 7.17,
|
| 556 |
+
"learning_rate": 0.00015376984126984128,
|
| 557 |
+
"loss": 0.1267,
|
| 558 |
+
"step": 405
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 7.26,
|
| 562 |
+
"learning_rate": 0.00014880952380952382,
|
| 563 |
+
"loss": 0.216,
|
| 564 |
+
"step": 410
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 7.35,
|
| 568 |
+
"learning_rate": 0.00014384920634920634,
|
| 569 |
+
"loss": 0.1007,
|
| 570 |
+
"step": 415
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 7.43,
|
| 574 |
+
"learning_rate": 0.0001388888888888889,
|
| 575 |
+
"loss": 0.1302,
|
| 576 |
+
"step": 420
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 7.52,
|
| 580 |
+
"learning_rate": 0.00013392857142857144,
|
| 581 |
+
"loss": 0.1706,
|
| 582 |
+
"step": 425
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 7.61,
|
| 586 |
+
"learning_rate": 0.00012896825396825398,
|
| 587 |
+
"loss": 0.0971,
|
| 588 |
+
"step": 430
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 7.7,
|
| 592 |
+
"learning_rate": 0.0001240079365079365,
|
| 593 |
+
"loss": 0.1253,
|
| 594 |
+
"step": 435
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 7.79,
|
| 598 |
+
"learning_rate": 0.00011904761904761905,
|
| 599 |
+
"loss": 0.0798,
|
| 600 |
+
"step": 440
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 7.88,
|
| 604 |
+
"learning_rate": 0.00011408730158730158,
|
| 605 |
+
"loss": 0.5271,
|
| 606 |
+
"step": 445
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 7.96,
|
| 610 |
+
"learning_rate": 0.00010912698412698413,
|
| 611 |
+
"loss": 0.0814,
|
| 612 |
+
"step": 450
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 8.0,
|
| 616 |
+
"eval_accuracy": 0.78,
|
| 617 |
+
"eval_loss": 0.9985226392745972,
|
| 618 |
+
"eval_runtime": 70.9212,
|
| 619 |
+
"eval_samples_per_second": 1.41,
|
| 620 |
+
"eval_steps_per_second": 0.183,
|
| 621 |
+
"step": 452
|
| 622 |
+
}
|
| 623 |
+
],
|
| 624 |
+
"logging_steps": 5,
|
| 625 |
+
"max_steps": 560,
|
| 626 |
+
"num_train_epochs": 10,
|
| 627 |
+
"save_steps": 500,
|
| 628 |
+
"total_flos": 4.9071906196992e+17,
|
| 629 |
+
"trial_name": null,
|
| 630 |
+
"trial_params": null
|
| 631 |
+
}
|
checkpoint-452/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbef9bdfa53985d2dd1361cb595119941d5a4b9581e158c102613a779ed26711
|
| 3 |
+
size 4600
|