Commit
•
19d8036
1
Parent(s):
eaab99b
Training in progress, epoch 5
Browse files- model.safetensors +1 -1
- run-0/checkpoint-120/config.json +80 -0
- run-0/checkpoint-120/model.safetensors +3 -0
- run-0/checkpoint-120/optimizer.pt +3 -0
- run-0/checkpoint-120/preprocessor_config.json +9 -0
- run-0/checkpoint-120/rng_state.pth +3 -0
- run-0/checkpoint-120/scheduler.pt +3 -0
- run-0/checkpoint-120/trainer_state.json +237 -0
- run-0/checkpoint-120/training_args.bin +3 -0
- run-0/checkpoint-24/config.json +80 -0
- run-0/checkpoint-24/model.safetensors +3 -0
- run-0/checkpoint-24/optimizer.pt +3 -0
- run-0/checkpoint-24/preprocessor_config.json +9 -0
- run-0/checkpoint-24/rng_state.pth +3 -0
- run-0/checkpoint-24/scheduler.pt +3 -0
- run-0/checkpoint-24/trainer_state.json +61 -0
- run-0/checkpoint-24/training_args.bin +3 -0
- run-0/checkpoint-48/model.safetensors +1 -1
- run-0/checkpoint-48/optimizer.pt +1 -1
- run-0/checkpoint-48/rng_state.pth +1 -1
- run-0/checkpoint-48/scheduler.pt +1 -1
- run-0/checkpoint-48/trainer_state.json +56 -65
- run-0/checkpoint-48/training_args.bin +1 -1
- run-0/checkpoint-72/config.json +80 -0
- run-0/checkpoint-72/model.safetensors +3 -0
- run-0/checkpoint-72/optimizer.pt +3 -0
- run-0/checkpoint-72/preprocessor_config.json +9 -0
- run-0/checkpoint-72/rng_state.pth +3 -0
- run-0/checkpoint-72/scheduler.pt +3 -0
- run-0/checkpoint-72/trainer_state.json +149 -0
- run-0/checkpoint-72/training_args.bin +3 -0
- run-0/checkpoint-96/model.safetensors +1 -1
- run-0/checkpoint-96/optimizer.pt +1 -1
- run-0/checkpoint-96/rng_state.pth +1 -1
- run-0/checkpoint-96/scheduler.pt +1 -1
- run-0/checkpoint-96/trainer_state.json +111 -129
- run-0/checkpoint-96/training_args.bin +1 -1
- runs/Mar03_18-24-09_ca56ea9bc35e/events.out.tfevents.1709497668.ca56ea9bc35e.3883.24 +3 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94763496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4970a2abd2c86347378245a23a90bcb1c03225871c0732deda4b110c1402b05e
|
| 3 |
size 94763496
|
run-0/checkpoint-120/config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "NOT_WORD",
|
| 53 |
+
"1": "WORD"
|
| 54 |
+
},
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"intermediate_size": 3072,
|
| 57 |
+
"label2id": {
|
| 58 |
+
"NOT_WORD": "0",
|
| 59 |
+
"WORD": "1"
|
| 60 |
+
},
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.0,
|
| 63 |
+
"mask_feature_length": 10,
|
| 64 |
+
"mask_feature_min_masks": 0,
|
| 65 |
+
"mask_feature_prob": 0.0,
|
| 66 |
+
"mask_time_length": 10,
|
| 67 |
+
"mask_time_min_masks": 2,
|
| 68 |
+
"mask_time_prob": 0.05,
|
| 69 |
+
"model_type": "hubert",
|
| 70 |
+
"num_attention_heads": 12,
|
| 71 |
+
"num_conv_pos_embedding_groups": 16,
|
| 72 |
+
"num_conv_pos_embeddings": 128,
|
| 73 |
+
"num_feat_extract_layers": 7,
|
| 74 |
+
"num_hidden_layers": 2,
|
| 75 |
+
"pad_token_id": 0,
|
| 76 |
+
"torch_dtype": "float32",
|
| 77 |
+
"transformers_version": "4.38.1",
|
| 78 |
+
"use_weighted_layer_sum": false,
|
| 79 |
+
"vocab_size": 32
|
| 80 |
+
}
|
run-0/checkpoint-120/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4970a2abd2c86347378245a23a90bcb1c03225871c0732deda4b110c1402b05e
|
| 3 |
+
size 94763496
|
run-0/checkpoint-120/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be897b050782e3854dad80b8194d6dc55b64e92a9f6a8de27ffb6bc2f519f358
|
| 3 |
+
size 189552570
|
run-0/checkpoint-120/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 |
+
}
|
run-0/checkpoint-120/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea9b93979db9d187112d0877ca456edd569c23f080722f2fbbe337c28c1a6935
|
| 3 |
+
size 14244
|
run-0/checkpoint-120/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0473f5ebc64129e90069538909f48d93066ac572290ce5451bdd20c91af3d131
|
| 3 |
+
size 1064
|
run-0/checkpoint-120/trainer_state.json
ADDED
|
@@ -0,0 +1,237 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7326732673267327,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-0/checkpoint-24",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 120,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21,
|
| 13 |
+
"grad_norm": 1.6479910612106323,
|
| 14 |
+
"learning_rate": 3.3535706116592527e-06,
|
| 15 |
+
"loss": 0.699,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.42,
|
| 20 |
+
"grad_norm": 0.6159653663635254,
|
| 21 |
+
"learning_rate": 6.707141223318505e-06,
|
| 22 |
+
"loss": 0.6932,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.62,
|
| 27 |
+
"grad_norm": 0.5607424974441528,
|
| 28 |
+
"learning_rate": 1.0060711834977758e-05,
|
| 29 |
+
"loss": 0.6812,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.83,
|
| 34 |
+
"grad_norm": 1.401130199432373,
|
| 35 |
+
"learning_rate": 1.341428244663701e-05,
|
| 36 |
+
"loss": 0.6633,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_f1": 0.7326732673267327,
|
| 42 |
+
"eval_loss": 0.680633544921875,
|
| 43 |
+
"eval_runtime": 1.3853,
|
| 44 |
+
"eval_samples_per_second": 46.201,
|
| 45 |
+
"eval_steps_per_second": 5.775,
|
| 46 |
+
"step": 24
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.04,
|
| 50 |
+
"grad_norm": 0.9690802693367004,
|
| 51 |
+
"learning_rate": 1.602261514459421e-05,
|
| 52 |
+
"loss": 0.6644,
|
| 53 |
+
"step": 25
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.25,
|
| 57 |
+
"grad_norm": 1.8331551551818848,
|
| 58 |
+
"learning_rate": 1.564999618774318e-05,
|
| 59 |
+
"loss": 0.6073,
|
| 60 |
+
"step": 30
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.46,
|
| 64 |
+
"grad_norm": 1.799914002418518,
|
| 65 |
+
"learning_rate": 1.527737723089215e-05,
|
| 66 |
+
"loss": 0.5805,
|
| 67 |
+
"step": 35
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.67,
|
| 71 |
+
"grad_norm": 0.515367865562439,
|
| 72 |
+
"learning_rate": 1.4904758274041123e-05,
|
| 73 |
+
"loss": 0.6465,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.88,
|
| 78 |
+
"grad_norm": 0.6179113388061523,
|
| 79 |
+
"learning_rate": 1.4532139317190096e-05,
|
| 80 |
+
"loss": 0.6147,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.0,
|
| 85 |
+
"eval_f1": 0.7326732673267327,
|
| 86 |
+
"eval_loss": 0.701690673828125,
|
| 87 |
+
"eval_runtime": 1.4198,
|
| 88 |
+
"eval_samples_per_second": 45.078,
|
| 89 |
+
"eval_steps_per_second": 5.635,
|
| 90 |
+
"step": 48
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.08,
|
| 94 |
+
"grad_norm": 0.5513622760772705,
|
| 95 |
+
"learning_rate": 1.4159520360339068e-05,
|
| 96 |
+
"loss": 0.6301,
|
| 97 |
+
"step": 50
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.29,
|
| 101 |
+
"grad_norm": 0.5830497741699219,
|
| 102 |
+
"learning_rate": 1.3786901403488039e-05,
|
| 103 |
+
"loss": 0.5836,
|
| 104 |
+
"step": 55
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.5,
|
| 108 |
+
"grad_norm": 0.6891571879386902,
|
| 109 |
+
"learning_rate": 1.341428244663701e-05,
|
| 110 |
+
"loss": 0.6309,
|
| 111 |
+
"step": 60
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.71,
|
| 115 |
+
"grad_norm": 1.3063991069793701,
|
| 116 |
+
"learning_rate": 1.3041663489785983e-05,
|
| 117 |
+
"loss": 0.6199,
|
| 118 |
+
"step": 65
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.92,
|
| 122 |
+
"grad_norm": 1.164373517036438,
|
| 123 |
+
"learning_rate": 1.2669044532934955e-05,
|
| 124 |
+
"loss": 0.4871,
|
| 125 |
+
"step": 70
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.0,
|
| 129 |
+
"eval_f1": 0.7326732673267327,
|
| 130 |
+
"eval_loss": 0.7076148986816406,
|
| 131 |
+
"eval_runtime": 1.4157,
|
| 132 |
+
"eval_samples_per_second": 45.206,
|
| 133 |
+
"eval_steps_per_second": 5.651,
|
| 134 |
+
"step": 72
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 3.12,
|
| 138 |
+
"grad_norm": 0.5683964490890503,
|
| 139 |
+
"learning_rate": 1.2296425576083926e-05,
|
| 140 |
+
"loss": 0.5943,
|
| 141 |
+
"step": 75
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 3.33,
|
| 145 |
+
"grad_norm": 0.5915613770484924,
|
| 146 |
+
"learning_rate": 1.1923806619232898e-05,
|
| 147 |
+
"loss": 0.6051,
|
| 148 |
+
"step": 80
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 3.54,
|
| 152 |
+
"grad_norm": 1.4184000492095947,
|
| 153 |
+
"learning_rate": 1.155118766238187e-05,
|
| 154 |
+
"loss": 0.487,
|
| 155 |
+
"step": 85
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 3.75,
|
| 159 |
+
"grad_norm": 1.1929051876068115,
|
| 160 |
+
"learning_rate": 1.1178568705530843e-05,
|
| 161 |
+
"loss": 0.6096,
|
| 162 |
+
"step": 90
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.96,
|
| 166 |
+
"grad_norm": 1.1995503902435303,
|
| 167 |
+
"learning_rate": 1.0805949748679813e-05,
|
| 168 |
+
"loss": 0.5922,
|
| 169 |
+
"step": 95
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.0,
|
| 173 |
+
"eval_f1": 0.7326732673267327,
|
| 174 |
+
"eval_loss": 0.7007102966308594,
|
| 175 |
+
"eval_runtime": 1.4297,
|
| 176 |
+
"eval_samples_per_second": 44.764,
|
| 177 |
+
"eval_steps_per_second": 5.596,
|
| 178 |
+
"step": 96
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 4.17,
|
| 182 |
+
"grad_norm": 0.9711471796035767,
|
| 183 |
+
"learning_rate": 1.0433330791828785e-05,
|
| 184 |
+
"loss": 0.5077,
|
| 185 |
+
"step": 100
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 4.38,
|
| 189 |
+
"grad_norm": 2.008340358734131,
|
| 190 |
+
"learning_rate": 1.0060711834977758e-05,
|
| 191 |
+
"loss": 0.5911,
|
| 192 |
+
"step": 105
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 4.58,
|
| 196 |
+
"grad_norm": 0.9180999398231506,
|
| 197 |
+
"learning_rate": 9.68809287812673e-06,
|
| 198 |
+
"loss": 0.5369,
|
| 199 |
+
"step": 110
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 4.79,
|
| 203 |
+
"grad_norm": 1.1544266939163208,
|
| 204 |
+
"learning_rate": 9.315473921275702e-06,
|
| 205 |
+
"loss": 0.5334,
|
| 206 |
+
"step": 115
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 5.0,
|
| 210 |
+
"grad_norm": 2.4023351669311523,
|
| 211 |
+
"learning_rate": 8.942854964424674e-06,
|
| 212 |
+
"loss": 0.5347,
|
| 213 |
+
"step": 120
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 5.0,
|
| 217 |
+
"eval_f1": 0.7326732673267327,
|
| 218 |
+
"eval_loss": 0.6761245727539062,
|
| 219 |
+
"eval_runtime": 1.3752,
|
| 220 |
+
"eval_samples_per_second": 46.538,
|
| 221 |
+
"eval_steps_per_second": 5.817,
|
| 222 |
+
"step": 120
|
| 223 |
+
}
|
| 224 |
+
],
|
| 225 |
+
"logging_steps": 5,
|
| 226 |
+
"max_steps": 240,
|
| 227 |
+
"num_input_tokens_seen": 0,
|
| 228 |
+
"num_train_epochs": 10,
|
| 229 |
+
"save_steps": 500,
|
| 230 |
+
"total_flos": 4193401989215328.0,
|
| 231 |
+
"train_batch_size": 8,
|
| 232 |
+
"trial_name": null,
|
| 233 |
+
"trial_params": {
|
| 234 |
+
"learning_rate": 1.6097138935964413e-05,
|
| 235 |
+
"per_device_train_batch_size": 8
|
| 236 |
+
}
|
| 237 |
+
}
|
run-0/checkpoint-120/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69b0aae1b6cc94401448b152c38be14ffcd8839b1499a5701f300de8efdf55e0
|
| 3 |
+
size 4920
|
run-0/checkpoint-24/config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "NOT_WORD",
|
| 53 |
+
"1": "WORD"
|
| 54 |
+
},
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"intermediate_size": 3072,
|
| 57 |
+
"label2id": {
|
| 58 |
+
"NOT_WORD": "0",
|
| 59 |
+
"WORD": "1"
|
| 60 |
+
},
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.0,
|
| 63 |
+
"mask_feature_length": 10,
|
| 64 |
+
"mask_feature_min_masks": 0,
|
| 65 |
+
"mask_feature_prob": 0.0,
|
| 66 |
+
"mask_time_length": 10,
|
| 67 |
+
"mask_time_min_masks": 2,
|
| 68 |
+
"mask_time_prob": 0.05,
|
| 69 |
+
"model_type": "hubert",
|
| 70 |
+
"num_attention_heads": 12,
|
| 71 |
+
"num_conv_pos_embedding_groups": 16,
|
| 72 |
+
"num_conv_pos_embeddings": 128,
|
| 73 |
+
"num_feat_extract_layers": 7,
|
| 74 |
+
"num_hidden_layers": 2,
|
| 75 |
+
"pad_token_id": 0,
|
| 76 |
+
"torch_dtype": "float32",
|
| 77 |
+
"transformers_version": "4.38.1",
|
| 78 |
+
"use_weighted_layer_sum": false,
|
| 79 |
+
"vocab_size": 32
|
| 80 |
+
}
|
run-0/checkpoint-24/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:203ce75c172df60c43147ad639437bfae06a12fde458f545bcfa9566f71c66e2
|
| 3 |
+
size 94763496
|
run-0/checkpoint-24/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44afb79906c8bbc5f625669f0a8610ac3248791cfe01df7397ef34f934faf328
|
| 3 |
+
size 189552570
|
run-0/checkpoint-24/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 |
+
}
|
run-0/checkpoint-24/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5fd464cfdc34ccc4a78e84a563ff84847a7f2ca68f8d1be703c5be378ce9c86
|
| 3 |
+
size 14244
|
run-0/checkpoint-24/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10b20289c4976533c8450c5bc9f8a90aa07e8c63cc39a142065bd92dfdbe4da6
|
| 3 |
+
size 1064
|
run-0/checkpoint-24/trainer_state.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7326732673267327,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-0/checkpoint-24",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 24,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21,
|
| 13 |
+
"grad_norm": 1.6479910612106323,
|
| 14 |
+
"learning_rate": 3.3535706116592527e-06,
|
| 15 |
+
"loss": 0.699,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.42,
|
| 20 |
+
"grad_norm": 0.6159653663635254,
|
| 21 |
+
"learning_rate": 6.707141223318505e-06,
|
| 22 |
+
"loss": 0.6932,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.62,
|
| 27 |
+
"grad_norm": 0.5607424974441528,
|
| 28 |
+
"learning_rate": 1.0060711834977758e-05,
|
| 29 |
+
"loss": 0.6812,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.83,
|
| 34 |
+
"grad_norm": 1.401130199432373,
|
| 35 |
+
"learning_rate": 1.341428244663701e-05,
|
| 36 |
+
"loss": 0.6633,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_f1": 0.7326732673267327,
|
| 42 |
+
"eval_loss": 0.680633544921875,
|
| 43 |
+
"eval_runtime": 1.3853,
|
| 44 |
+
"eval_samples_per_second": 46.201,
|
| 45 |
+
"eval_steps_per_second": 5.775,
|
| 46 |
+
"step": 24
|
| 47 |
+
}
|
| 48 |
+
],
|
| 49 |
+
"logging_steps": 5,
|
| 50 |
+
"max_steps": 240,
|
| 51 |
+
"num_input_tokens_seen": 0,
|
| 52 |
+
"num_train_epochs": 10,
|
| 53 |
+
"save_steps": 500,
|
| 54 |
+
"total_flos": 670768569859200.0,
|
| 55 |
+
"train_batch_size": 8,
|
| 56 |
+
"trial_name": null,
|
| 57 |
+
"trial_params": {
|
| 58 |
+
"learning_rate": 1.6097138935964413e-05,
|
| 59 |
+
"per_device_train_batch_size": 8
|
| 60 |
+
}
|
| 61 |
+
}
|
run-0/checkpoint-24/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69b0aae1b6cc94401448b152c38be14ffcd8839b1499a5701f300de8efdf55e0
|
| 3 |
+
size 4920
|
run-0/checkpoint-48/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94763496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23842749f34d7cb29a9ff9626a7713537ce548c200d8713e828ad0cad4a9c15d
|
| 3 |
size 94763496
|
run-0/checkpoint-48/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 189552570
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11c2cb808887601222fb9cf33c2d409d468ab8f8b241ccc1a2909d3ce6a5d95a
|
| 3 |
size 189552570
|
run-0/checkpoint-48/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ea0f2253490889e9b5dbea96976236c3c1f025b5a24179f4bcaa44eec621be7
|
| 3 |
size 14244
|
run-0/checkpoint-48/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d11d359047a2e15674e19d2520244262d0d6bc2ec5ccc284a4928c5b79947d31
|
| 3 |
size 1064
|
run-0/checkpoint-48/trainer_state.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7326732673267327,
|
| 3 |
-
"best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-0/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 48,
|
| 7 |
"is_hyper_param_search": true,
|
|
@@ -9,106 +9,97 @@
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch":
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"eval_steps_per_second": 5.654,
|
| 39 |
-
"step": 16
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 1.
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
|
|
|
|
|
|
| 47 |
},
|
| 48 |
{
|
| 49 |
-
"epoch": 1.
|
| 50 |
-
"grad_norm": 0.
|
| 51 |
-
"learning_rate":
|
| 52 |
-
"loss": 0.
|
| 53 |
"step": 25
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch": 1.
|
| 57 |
-
"grad_norm":
|
| 58 |
-
"learning_rate":
|
| 59 |
-
"loss": 0.
|
| 60 |
"step": 30
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch":
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"eval_samples_per_second": 45.693,
|
| 68 |
-
"eval_steps_per_second": 5.712,
|
| 69 |
-
"step": 32
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 2.19,
|
| 73 |
-
"grad_norm": 0.758405327796936,
|
| 74 |
-
"learning_rate": 2.945709032521948e-05,
|
| 75 |
-
"loss": 0.5972,
|
| 76 |
"step": 35
|
| 77 |
},
|
| 78 |
{
|
| 79 |
-
"epoch":
|
| 80 |
-
"grad_norm": 0.
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss": 0.
|
| 83 |
"step": 40
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch":
|
| 87 |
-
"grad_norm":
|
| 88 |
-
"learning_rate":
|
| 89 |
-
"loss": 0.
|
| 90 |
"step": 45
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"epoch":
|
| 94 |
"eval_f1": 0.7326732673267327,
|
| 95 |
-
"eval_loss": 0.
|
| 96 |
-
"eval_runtime": 1.
|
| 97 |
-
"eval_samples_per_second":
|
| 98 |
-
"eval_steps_per_second": 5.
|
| 99 |
"step": 48
|
| 100 |
}
|
| 101 |
],
|
| 102 |
"logging_steps": 5,
|
| 103 |
-
"max_steps":
|
| 104 |
"num_input_tokens_seen": 0,
|
| 105 |
"num_train_epochs": 10,
|
| 106 |
"save_steps": 500,
|
| 107 |
-
"total_flos":
|
| 108 |
-
"train_batch_size":
|
| 109 |
"trial_name": null,
|
| 110 |
"trial_params": {
|
| 111 |
-
"learning_rate":
|
| 112 |
-
"per_device_train_batch_size":
|
| 113 |
}
|
| 114 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7326732673267327,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-0/checkpoint-24",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 48,
|
| 7 |
"is_hyper_param_search": true,
|
|
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.21,
|
| 13 |
+
"grad_norm": 1.6479910612106323,
|
| 14 |
+
"learning_rate": 3.3535706116592527e-06,
|
| 15 |
+
"loss": 0.699,
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.42,
|
| 20 |
+
"grad_norm": 0.6159653663635254,
|
| 21 |
+
"learning_rate": 6.707141223318505e-06,
|
| 22 |
+
"loss": 0.6932,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.62,
|
| 27 |
+
"grad_norm": 0.5607424974441528,
|
| 28 |
+
"learning_rate": 1.0060711834977758e-05,
|
| 29 |
+
"loss": 0.6812,
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.83,
|
| 34 |
+
"grad_norm": 1.401130199432373,
|
| 35 |
+
"learning_rate": 1.341428244663701e-05,
|
| 36 |
+
"loss": 0.6633,
|
| 37 |
+
"step": 20
|
|
|
|
|
|
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_f1": 0.7326732673267327,
|
| 42 |
+
"eval_loss": 0.680633544921875,
|
| 43 |
+
"eval_runtime": 1.3853,
|
| 44 |
+
"eval_samples_per_second": 46.201,
|
| 45 |
+
"eval_steps_per_second": 5.775,
|
| 46 |
+
"step": 24
|
| 47 |
},
|
| 48 |
{
|
| 49 |
+
"epoch": 1.04,
|
| 50 |
+
"grad_norm": 0.9690802693367004,
|
| 51 |
+
"learning_rate": 1.602261514459421e-05,
|
| 52 |
+
"loss": 0.6644,
|
| 53 |
"step": 25
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 1.25,
|
| 57 |
+
"grad_norm": 1.8331551551818848,
|
| 58 |
+
"learning_rate": 1.564999618774318e-05,
|
| 59 |
+
"loss": 0.6073,
|
| 60 |
"step": 30
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"epoch": 1.46,
|
| 64 |
+
"grad_norm": 1.799914002418518,
|
| 65 |
+
"learning_rate": 1.527737723089215e-05,
|
| 66 |
+
"loss": 0.5805,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
"step": 35
|
| 68 |
},
|
| 69 |
{
|
| 70 |
+
"epoch": 1.67,
|
| 71 |
+
"grad_norm": 0.515367865562439,
|
| 72 |
+
"learning_rate": 1.4904758274041123e-05,
|
| 73 |
+
"loss": 0.6465,
|
| 74 |
"step": 40
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 1.88,
|
| 78 |
+
"grad_norm": 0.6179113388061523,
|
| 79 |
+
"learning_rate": 1.4532139317190096e-05,
|
| 80 |
+
"loss": 0.6147,
|
| 81 |
"step": 45
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 2.0,
|
| 85 |
"eval_f1": 0.7326732673267327,
|
| 86 |
+
"eval_loss": 0.701690673828125,
|
| 87 |
+
"eval_runtime": 1.4198,
|
| 88 |
+
"eval_samples_per_second": 45.078,
|
| 89 |
+
"eval_steps_per_second": 5.635,
|
| 90 |
"step": 48
|
| 91 |
}
|
| 92 |
],
|
| 93 |
"logging_steps": 5,
|
| 94 |
+
"max_steps": 240,
|
| 95 |
"num_input_tokens_seen": 0,
|
| 96 |
"num_train_epochs": 10,
|
| 97 |
"save_steps": 500,
|
| 98 |
+
"total_flos": 1570339835242944.0,
|
| 99 |
+
"train_batch_size": 8,
|
| 100 |
"trial_name": null,
|
| 101 |
"trial_params": {
|
| 102 |
+
"learning_rate": 1.6097138935964413e-05,
|
| 103 |
+
"per_device_train_batch_size": 8
|
| 104 |
}
|
| 105 |
}
|
run-0/checkpoint-48/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69b0aae1b6cc94401448b152c38be14ffcd8839b1499a5701f300de8efdf55e0
|
| 3 |
size 4920
|
run-0/checkpoint-72/config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "NOT_WORD",
|
| 53 |
+
"1": "WORD"
|
| 54 |
+
},
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"intermediate_size": 3072,
|
| 57 |
+
"label2id": {
|
| 58 |
+
"NOT_WORD": "0",
|
| 59 |
+
"WORD": "1"
|
| 60 |
+
},
|
| 61 |
+
"layer_norm_eps": 1e-05,
|
| 62 |
+
"layerdrop": 0.0,
|
| 63 |
+
"mask_feature_length": 10,
|
| 64 |
+
"mask_feature_min_masks": 0,
|
| 65 |
+
"mask_feature_prob": 0.0,
|
| 66 |
+
"mask_time_length": 10,
|
| 67 |
+
"mask_time_min_masks": 2,
|
| 68 |
+
"mask_time_prob": 0.05,
|
| 69 |
+
"model_type": "hubert",
|
| 70 |
+
"num_attention_heads": 12,
|
| 71 |
+
"num_conv_pos_embedding_groups": 16,
|
| 72 |
+
"num_conv_pos_embeddings": 128,
|
| 73 |
+
"num_feat_extract_layers": 7,
|
| 74 |
+
"num_hidden_layers": 2,
|
| 75 |
+
"pad_token_id": 0,
|
| 76 |
+
"torch_dtype": "float32",
|
| 77 |
+
"transformers_version": "4.38.1",
|
| 78 |
+
"use_weighted_layer_sum": false,
|
| 79 |
+
"vocab_size": 32
|
| 80 |
+
}
|
run-0/checkpoint-72/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb76baaa3e10292859eaaf54e1cd3dc5d0de162ba6ed9527301bfad27076b38d
|
| 3 |
+
size 94763496
|
run-0/checkpoint-72/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06dd70ed020e580a47e998558c2ff850d8c86016146dbbbed371cb5740d031f2
|
| 3 |
+
size 189552570
|
run-0/checkpoint-72/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 |
+
}
|
run-0/checkpoint-72/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ee3b4c1fd10f5b7dc9cd3892663bc52a1bc7290b86a11225b56750a1f3c0adf
|
| 3 |
+
size 14244
|
run-0/checkpoint-72/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fffad6961893713483db1dcfd6ef80135279126147c8de8415994f26331d94f
|
| 3 |
+
size 1064
|
run-0/checkpoint-72/trainer_state.json
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7326732673267327,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-0/checkpoint-24",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 72,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.21,
|
| 13 |
+
"grad_norm": 1.6479910612106323,
|
| 14 |
+
"learning_rate": 3.3535706116592527e-06,
|
| 15 |
+
"loss": 0.699,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.42,
|
| 20 |
+
"grad_norm": 0.6159653663635254,
|
| 21 |
+
"learning_rate": 6.707141223318505e-06,
|
| 22 |
+
"loss": 0.6932,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.62,
|
| 27 |
+
"grad_norm": 0.5607424974441528,
|
| 28 |
+
"learning_rate": 1.0060711834977758e-05,
|
| 29 |
+
"loss": 0.6812,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.83,
|
| 34 |
+
"grad_norm": 1.401130199432373,
|
| 35 |
+
"learning_rate": 1.341428244663701e-05,
|
| 36 |
+
"loss": 0.6633,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_f1": 0.7326732673267327,
|
| 42 |
+
"eval_loss": 0.680633544921875,
|
| 43 |
+
"eval_runtime": 1.3853,
|
| 44 |
+
"eval_samples_per_second": 46.201,
|
| 45 |
+
"eval_steps_per_second": 5.775,
|
| 46 |
+
"step": 24
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.04,
|
| 50 |
+
"grad_norm": 0.9690802693367004,
|
| 51 |
+
"learning_rate": 1.602261514459421e-05,
|
| 52 |
+
"loss": 0.6644,
|
| 53 |
+
"step": 25
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.25,
|
| 57 |
+
"grad_norm": 1.8331551551818848,
|
| 58 |
+
"learning_rate": 1.564999618774318e-05,
|
| 59 |
+
"loss": 0.6073,
|
| 60 |
+
"step": 30
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.46,
|
| 64 |
+
"grad_norm": 1.799914002418518,
|
| 65 |
+
"learning_rate": 1.527737723089215e-05,
|
| 66 |
+
"loss": 0.5805,
|
| 67 |
+
"step": 35
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.67,
|
| 71 |
+
"grad_norm": 0.515367865562439,
|
| 72 |
+
"learning_rate": 1.4904758274041123e-05,
|
| 73 |
+
"loss": 0.6465,
|
| 74 |
+
"step": 40
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.88,
|
| 78 |
+
"grad_norm": 0.6179113388061523,
|
| 79 |
+
"learning_rate": 1.4532139317190096e-05,
|
| 80 |
+
"loss": 0.6147,
|
| 81 |
+
"step": 45
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.0,
|
| 85 |
+
"eval_f1": 0.7326732673267327,
|
| 86 |
+
"eval_loss": 0.701690673828125,
|
| 87 |
+
"eval_runtime": 1.4198,
|
| 88 |
+
"eval_samples_per_second": 45.078,
|
| 89 |
+
"eval_steps_per_second": 5.635,
|
| 90 |
+
"step": 48
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 2.08,
|
| 94 |
+
"grad_norm": 0.5513622760772705,
|
| 95 |
+
"learning_rate": 1.4159520360339068e-05,
|
| 96 |
+
"loss": 0.6301,
|
| 97 |
+
"step": 50
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 2.29,
|
| 101 |
+
"grad_norm": 0.5830497741699219,
|
| 102 |
+
"learning_rate": 1.3786901403488039e-05,
|
| 103 |
+
"loss": 0.5836,
|
| 104 |
+
"step": 55
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 2.5,
|
| 108 |
+
"grad_norm": 0.6891571879386902,
|
| 109 |
+
"learning_rate": 1.341428244663701e-05,
|
| 110 |
+
"loss": 0.6309,
|
| 111 |
+
"step": 60
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.71,
|
| 115 |
+
"grad_norm": 1.3063991069793701,
|
| 116 |
+
"learning_rate": 1.3041663489785983e-05,
|
| 117 |
+
"loss": 0.6199,
|
| 118 |
+
"step": 65
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.92,
|
| 122 |
+
"grad_norm": 1.164373517036438,
|
| 123 |
+
"learning_rate": 1.2669044532934955e-05,
|
| 124 |
+
"loss": 0.4871,
|
| 125 |
+
"step": 70
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.0,
|
| 129 |
+
"eval_f1": 0.7326732673267327,
|
| 130 |
+
"eval_loss": 0.7076148986816406,
|
| 131 |
+
"eval_runtime": 1.4157,
|
| 132 |
+
"eval_samples_per_second": 45.206,
|
| 133 |
+
"eval_steps_per_second": 5.651,
|
| 134 |
+
"step": 72
|
| 135 |
+
}
|
| 136 |
+
],
|
| 137 |
+
"logging_steps": 5,
|
| 138 |
+
"max_steps": 240,
|
| 139 |
+
"num_input_tokens_seen": 0,
|
| 140 |
+
"num_train_epochs": 10,
|
| 141 |
+
"save_steps": 500,
|
| 142 |
+
"total_flos": 2449725503657472.0,
|
| 143 |
+
"train_batch_size": 8,
|
| 144 |
+
"trial_name": null,
|
| 145 |
+
"trial_params": {
|
| 146 |
+
"learning_rate": 1.6097138935964413e-05,
|
| 147 |
+
"per_device_train_batch_size": 8
|
| 148 |
+
}
|
| 149 |
+
}
|
run-0/checkpoint-72/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69b0aae1b6cc94401448b152c38be14ffcd8839b1499a5701f300de8efdf55e0
|
| 3 |
+
size 4920
|
run-0/checkpoint-96/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 94763496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0c9139d8224355fe0e842d9efa7c44348ac0e82ff31134a167f9a33f4be03b4
|
| 3 |
size 94763496
|
run-0/checkpoint-96/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 189552570
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39d20d5d04c35d2b8653ce48db98b8aceb259e1d3129842531fe037342fd8eb3
|
| 3 |
size 189552570
|
run-0/checkpoint-96/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b456b0645d03f4fc8a479113b5caa8bb02734d9c9788d3ded452d4ca10da7ef
|
| 3 |
size 14244
|
run-0/checkpoint-96/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b19b453bb5c60fec371fb0b599c4ea5138bc56060c0f92f5031e6bd36210973
|
| 3 |
size 1064
|
run-0/checkpoint-96/trainer_state.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-0/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 96,
|
| 7 |
"is_hyper_param_search": true,
|
|
@@ -9,203 +9,185 @@
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch":
|
| 34 |
-
"
|
| 35 |
-
"
|
| 36 |
-
"
|
| 37 |
-
"
|
| 38 |
-
"eval_steps_per_second": 5.654,
|
| 39 |
-
"step": 16
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 1.
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
|
|
|
|
|
|
| 47 |
},
|
| 48 |
{
|
| 49 |
-
"epoch": 1.
|
| 50 |
-
"grad_norm": 0.
|
| 51 |
-
"learning_rate":
|
| 52 |
-
"loss": 0.
|
| 53 |
"step": 25
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch": 1.
|
| 57 |
-
"grad_norm":
|
| 58 |
-
"learning_rate":
|
| 59 |
-
"loss": 0.
|
| 60 |
"step": 30
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch":
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"eval_samples_per_second": 45.693,
|
| 68 |
-
"eval_steps_per_second": 5.712,
|
| 69 |
-
"step": 32
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 2.19,
|
| 73 |
-
"grad_norm": 0.758405327796936,
|
| 74 |
-
"learning_rate": 2.945709032521948e-05,
|
| 75 |
-
"loss": 0.5972,
|
| 76 |
"step": 35
|
| 77 |
},
|
| 78 |
{
|
| 79 |
-
"epoch":
|
| 80 |
-
"grad_norm": 0.
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss": 0.
|
| 83 |
"step": 40
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch":
|
| 87 |
-
"grad_norm":
|
| 88 |
-
"learning_rate":
|
| 89 |
-
"loss": 0.
|
| 90 |
"step": 45
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"epoch":
|
| 94 |
"eval_f1": 0.7326732673267327,
|
| 95 |
-
"eval_loss": 0.
|
| 96 |
-
"eval_runtime": 1.
|
| 97 |
-
"eval_samples_per_second":
|
| 98 |
-
"eval_steps_per_second": 5.
|
| 99 |
"step": 48
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"epoch":
|
| 103 |
-
"grad_norm": 0.
|
| 104 |
-
"learning_rate":
|
| 105 |
-
"loss": 0.
|
| 106 |
"step": 50
|
| 107 |
},
|
| 108 |
{
|
| 109 |
-
"epoch":
|
| 110 |
-
"grad_norm":
|
| 111 |
-
"learning_rate":
|
| 112 |
-
"loss": 0.
|
| 113 |
"step": 55
|
| 114 |
},
|
| 115 |
{
|
| 116 |
-
"epoch":
|
| 117 |
-
"grad_norm": 0.
|
| 118 |
-
"learning_rate":
|
| 119 |
-
"loss": 0.
|
| 120 |
"step": 60
|
| 121 |
},
|
| 122 |
{
|
| 123 |
-
"epoch":
|
| 124 |
-
"
|
| 125 |
-
"
|
| 126 |
-
"
|
| 127 |
-
"eval_samples_per_second": 41.89,
|
| 128 |
-
"eval_steps_per_second": 5.236,
|
| 129 |
-
"step": 64
|
| 130 |
-
},
|
| 131 |
-
{
|
| 132 |
-
"epoch": 4.06,
|
| 133 |
-
"grad_norm": 1.3549830913543701,
|
| 134 |
-
"learning_rate": 2.2387388647166805e-05,
|
| 135 |
-
"loss": 0.5651,
|
| 136 |
"step": 65
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"epoch":
|
| 140 |
-
"grad_norm": 1.
|
| 141 |
-
"learning_rate":
|
| 142 |
-
"loss": 0.
|
| 143 |
"step": 70
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch":
|
| 147 |
-
"
|
| 148 |
-
"
|
| 149 |
-
"
|
| 150 |
-
"
|
|
|
|
|
|
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch":
|
| 154 |
-
"grad_norm":
|
| 155 |
-
"learning_rate": 1.
|
| 156 |
-
"loss": 0.
|
| 157 |
-
"step":
|
| 158 |
},
|
| 159 |
{
|
| 160 |
-
"epoch":
|
| 161 |
-
"
|
| 162 |
-
"
|
| 163 |
-
"
|
| 164 |
-
"eval_samples_per_second": 46.069,
|
| 165 |
-
"eval_steps_per_second": 5.759,
|
| 166 |
"step": 80
|
| 167 |
},
|
| 168 |
{
|
| 169 |
-
"epoch":
|
| 170 |
-
"grad_norm":
|
| 171 |
-
"learning_rate": 1.
|
| 172 |
-
"loss": 0.
|
| 173 |
"step": 85
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch":
|
| 177 |
-
"grad_norm":
|
| 178 |
-
"learning_rate": 1.
|
| 179 |
-
"loss": 0.
|
| 180 |
"step": 90
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"epoch":
|
| 184 |
-
"grad_norm":
|
| 185 |
-
"learning_rate": 1.
|
| 186 |
-
"loss": 0.
|
| 187 |
"step": 95
|
| 188 |
},
|
| 189 |
{
|
| 190 |
-
"epoch":
|
| 191 |
-
"eval_f1": 0.
|
| 192 |
-
"eval_loss": 0.
|
| 193 |
-
"eval_runtime": 1.
|
| 194 |
-
"eval_samples_per_second":
|
| 195 |
-
"eval_steps_per_second": 5.
|
| 196 |
"step": 96
|
| 197 |
}
|
| 198 |
],
|
| 199 |
"logging_steps": 5,
|
| 200 |
-
"max_steps":
|
| 201 |
"num_input_tokens_seen": 0,
|
| 202 |
"num_train_epochs": 10,
|
| 203 |
"save_steps": 500,
|
| 204 |
-
"total_flos":
|
| 205 |
-
"train_batch_size":
|
| 206 |
"trial_name": null,
|
| 207 |
"trial_params": {
|
| 208 |
-
"learning_rate":
|
| 209 |
-
"per_device_train_batch_size":
|
| 210 |
}
|
| 211 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7326732673267327,
|
| 3 |
+
"best_model_checkpoint": "distilhubert-finetuned-not-a-word2/run-0/checkpoint-24",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
"global_step": 96,
|
| 7 |
"is_hyper_param_search": true,
|
|
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.21,
|
| 13 |
+
"grad_norm": 1.6479910612106323,
|
| 14 |
+
"learning_rate": 3.3535706116592527e-06,
|
| 15 |
+
"loss": 0.699,
|
| 16 |
"step": 5
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.42,
|
| 20 |
+
"grad_norm": 0.6159653663635254,
|
| 21 |
+
"learning_rate": 6.707141223318505e-06,
|
| 22 |
+
"loss": 0.6932,
|
| 23 |
"step": 10
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.62,
|
| 27 |
+
"grad_norm": 0.5607424974441528,
|
| 28 |
+
"learning_rate": 1.0060711834977758e-05,
|
| 29 |
+
"loss": 0.6812,
|
| 30 |
"step": 15
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.83,
|
| 34 |
+
"grad_norm": 1.401130199432373,
|
| 35 |
+
"learning_rate": 1.341428244663701e-05,
|
| 36 |
+
"loss": 0.6633,
|
| 37 |
+
"step": 20
|
|
|
|
|
|
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 1.0,
|
| 41 |
+
"eval_f1": 0.7326732673267327,
|
| 42 |
+
"eval_loss": 0.680633544921875,
|
| 43 |
+
"eval_runtime": 1.3853,
|
| 44 |
+
"eval_samples_per_second": 46.201,
|
| 45 |
+
"eval_steps_per_second": 5.775,
|
| 46 |
+
"step": 24
|
| 47 |
},
|
| 48 |
{
|
| 49 |
+
"epoch": 1.04,
|
| 50 |
+
"grad_norm": 0.9690802693367004,
|
| 51 |
+
"learning_rate": 1.602261514459421e-05,
|
| 52 |
+
"loss": 0.6644,
|
| 53 |
"step": 25
|
| 54 |
},
|
| 55 |
{
|
| 56 |
+
"epoch": 1.25,
|
| 57 |
+
"grad_norm": 1.8331551551818848,
|
| 58 |
+
"learning_rate": 1.564999618774318e-05,
|
| 59 |
+
"loss": 0.6073,
|
| 60 |
"step": 30
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"epoch": 1.46,
|
| 64 |
+
"grad_norm": 1.799914002418518,
|
| 65 |
+
"learning_rate": 1.527737723089215e-05,
|
| 66 |
+
"loss": 0.5805,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 67 |
"step": 35
|
| 68 |
},
|
| 69 |
{
|
| 70 |
+
"epoch": 1.67,
|
| 71 |
+
"grad_norm": 0.515367865562439,
|
| 72 |
+
"learning_rate": 1.4904758274041123e-05,
|
| 73 |
+
"loss": 0.6465,
|
| 74 |
"step": 40
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 1.88,
|
| 78 |
+
"grad_norm": 0.6179113388061523,
|
| 79 |
+
"learning_rate": 1.4532139317190096e-05,
|
| 80 |
+
"loss": 0.6147,
|
| 81 |
"step": 45
|
| 82 |
},
|
| 83 |
{
|
| 84 |
+
"epoch": 2.0,
|
| 85 |
"eval_f1": 0.7326732673267327,
|
| 86 |
+
"eval_loss": 0.701690673828125,
|
| 87 |
+
"eval_runtime": 1.4198,
|
| 88 |
+
"eval_samples_per_second": 45.078,
|
| 89 |
+
"eval_steps_per_second": 5.635,
|
| 90 |
"step": 48
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"epoch": 2.08,
|
| 94 |
+
"grad_norm": 0.5513622760772705,
|
| 95 |
+
"learning_rate": 1.4159520360339068e-05,
|
| 96 |
+
"loss": 0.6301,
|
| 97 |
"step": 50
|
| 98 |
},
|
| 99 |
{
|
| 100 |
+
"epoch": 2.29,
|
| 101 |
+
"grad_norm": 0.5830497741699219,
|
| 102 |
+
"learning_rate": 1.3786901403488039e-05,
|
| 103 |
+
"loss": 0.5836,
|
| 104 |
"step": 55
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 2.5,
|
| 108 |
+
"grad_norm": 0.6891571879386902,
|
| 109 |
+
"learning_rate": 1.341428244663701e-05,
|
| 110 |
+
"loss": 0.6309,
|
| 111 |
"step": 60
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 2.71,
|
| 115 |
+
"grad_norm": 1.3063991069793701,
|
| 116 |
+
"learning_rate": 1.3041663489785983e-05,
|
| 117 |
+
"loss": 0.6199,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
"step": 65
|
| 119 |
},
|
| 120 |
{
|
| 121 |
+
"epoch": 2.92,
|
| 122 |
+
"grad_norm": 1.164373517036438,
|
| 123 |
+
"learning_rate": 1.2669044532934955e-05,
|
| 124 |
+
"loss": 0.4871,
|
| 125 |
"step": 70
|
| 126 |
},
|
| 127 |
{
|
| 128 |
+
"epoch": 3.0,
|
| 129 |
+
"eval_f1": 0.7326732673267327,
|
| 130 |
+
"eval_loss": 0.7076148986816406,
|
| 131 |
+
"eval_runtime": 1.4157,
|
| 132 |
+
"eval_samples_per_second": 45.206,
|
| 133 |
+
"eval_steps_per_second": 5.651,
|
| 134 |
+
"step": 72
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 3.12,
|
| 138 |
+
"grad_norm": 0.5683964490890503,
|
| 139 |
+
"learning_rate": 1.2296425576083926e-05,
|
| 140 |
+
"loss": 0.5943,
|
| 141 |
+
"step": 75
|
| 142 |
},
|
| 143 |
{
|
| 144 |
+
"epoch": 3.33,
|
| 145 |
+
"grad_norm": 0.5915613770484924,
|
| 146 |
+
"learning_rate": 1.1923806619232898e-05,
|
| 147 |
+
"loss": 0.6051,
|
|
|
|
|
|
|
| 148 |
"step": 80
|
| 149 |
},
|
| 150 |
{
|
| 151 |
+
"epoch": 3.54,
|
| 152 |
+
"grad_norm": 1.4184000492095947,
|
| 153 |
+
"learning_rate": 1.155118766238187e-05,
|
| 154 |
+
"loss": 0.487,
|
| 155 |
"step": 85
|
| 156 |
},
|
| 157 |
{
|
| 158 |
+
"epoch": 3.75,
|
| 159 |
+
"grad_norm": 1.1929051876068115,
|
| 160 |
+
"learning_rate": 1.1178568705530843e-05,
|
| 161 |
+
"loss": 0.6096,
|
| 162 |
"step": 90
|
| 163 |
},
|
| 164 |
{
|
| 165 |
+
"epoch": 3.96,
|
| 166 |
+
"grad_norm": 1.1995503902435303,
|
| 167 |
+
"learning_rate": 1.0805949748679813e-05,
|
| 168 |
+
"loss": 0.5922,
|
| 169 |
"step": 95
|
| 170 |
},
|
| 171 |
{
|
| 172 |
+
"epoch": 4.0,
|
| 173 |
+
"eval_f1": 0.7326732673267327,
|
| 174 |
+
"eval_loss": 0.7007102966308594,
|
| 175 |
+
"eval_runtime": 1.4297,
|
| 176 |
+
"eval_samples_per_second": 44.764,
|
| 177 |
+
"eval_steps_per_second": 5.596,
|
| 178 |
"step": 96
|
| 179 |
}
|
| 180 |
],
|
| 181 |
"logging_steps": 5,
|
| 182 |
+
"max_steps": 240,
|
| 183 |
"num_input_tokens_seen": 0,
|
| 184 |
"num_train_epochs": 10,
|
| 185 |
"save_steps": 500,
|
| 186 |
+
"total_flos": 3314382463332576.0,
|
| 187 |
+
"train_batch_size": 8,
|
| 188 |
"trial_name": null,
|
| 189 |
"trial_params": {
|
| 190 |
+
"learning_rate": 1.6097138935964413e-05,
|
| 191 |
+
"per_device_train_batch_size": 8
|
| 192 |
}
|
| 193 |
}
|
run-0/checkpoint-96/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69b0aae1b6cc94401448b152c38be14ffcd8839b1499a5701f300de8efdf55e0
|
| 3 |
size 4920
|
runs/Mar03_18-24-09_ca56ea9bc35e/events.out.tfevents.1709497668.ca56ea9bc35e.3883.24
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d02008ca9bff9e2d2736a788c7e63fb995b1dd9a85b32013ef07005a79b7bef
|
| 3 |
+
size 12043
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69b0aae1b6cc94401448b152c38be14ffcd8839b1499a5701f300de8efdf55e0
|
| 3 |
size 4920
|