Training in progress, epoch 19
Browse files- logs/events.out.tfevents.1713595280.1376c752d37a.9760.66 +3 -0
- model.safetensors +1 -1
- run-13/checkpoint-3210/config.json +34 -0
- run-13/checkpoint-3210/model.safetensors +3 -0
- run-13/checkpoint-3210/optimizer.pt +3 -0
- run-13/checkpoint-3210/rng_state.pth +3 -0
- run-13/checkpoint-3210/scheduler.pt +3 -0
- run-13/checkpoint-3210/special_tokens_map.json +7 -0
- run-13/checkpoint-3210/tokenizer.json +0 -0
- run-13/checkpoint-3210/tokenizer_config.json +57 -0
- run-13/checkpoint-3210/trainer_state.json +326 -0
- run-13/checkpoint-3210/training_args.bin +3 -0
- run-13/checkpoint-3210/vocab.txt +0 -0
- run-13/checkpoint-4066/config.json +34 -0
- run-13/checkpoint-4066/model.safetensors +3 -0
- run-13/checkpoint-4066/optimizer.pt +3 -0
- run-13/checkpoint-4066/rng_state.pth +3 -0
- run-13/checkpoint-4066/scheduler.pt +3 -0
- run-13/checkpoint-4066/special_tokens_map.json +7 -0
- run-13/checkpoint-4066/tokenizer.json +0 -0
- run-13/checkpoint-4066/tokenizer_config.json +57 -0
- run-13/checkpoint-4066/trainer_state.json +406 -0
- run-13/checkpoint-4066/training_args.bin +3 -0
- run-13/checkpoint-4066/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1713595280.1376c752d37a.9760.66
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e42153c7a482389b4be11da087336bf3691032ea63a5c01974091accc1f5b49
|
| 3 |
+
size 18978
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 17549312
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2282d9169d95f90fa7ab4d7133bc333939d77fd4aa5f26e995771f52ce06d69
|
| 3 |
size 17549312
|
run-13/checkpoint-3210/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 128,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "negative",
|
| 13 |
+
"1": "positive"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 512,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"negative": "0",
|
| 19 |
+
"positive": "1"
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "bert",
|
| 24 |
+
"num_attention_heads": 2,
|
| 25 |
+
"num_hidden_layers": 2,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.40.0",
|
| 31 |
+
"type_vocab_size": 2,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 30522
|
| 34 |
+
}
|
run-13/checkpoint-3210/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23a71f0e950fa7a4f0eb52691c1fb530e52030dd101061537500f64a03bb741a
|
| 3 |
+
size 17549312
|
run-13/checkpoint-3210/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0932b29bd2ce3e3bf0c636282b24be2c03990c27ec2261e25948893913898d36
|
| 3 |
+
size 35123898
|
run-13/checkpoint-3210/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d81d96bfaf26d44cf1a0c72fb1dd07a53054407225c96066b3cf891d113419f6
|
| 3 |
+
size 14308
|
run-13/checkpoint-3210/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aba8581c62ba2116923d6b50751702692f9355ad77b7b810090a5ce909ea065a
|
| 3 |
+
size 1064
|
run-13/checkpoint-3210/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-13/checkpoint-3210/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-13/checkpoint-3210/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
run-13/checkpoint-3210/trainer_state.json
ADDED
|
@@ -0,0 +1,326 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7885178676039836,
|
| 3 |
+
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-3210",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3210,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 8.763052940368652,
|
| 14 |
+
"learning_rate": 0.00036729100192842157,
|
| 15 |
+
"loss": 0.5966,
|
| 16 |
+
"step": 214
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.7211482132396017,
|
| 21 |
+
"eval_f1": 0.5132924335378324,
|
| 22 |
+
"eval_loss": 0.5418887734413147,
|
| 23 |
+
"eval_mcc": 0.33384466816371045,
|
| 24 |
+
"eval_precision": 0.6136919315403423,
|
| 25 |
+
"eval_recall": 0.44112478031634444,
|
| 26 |
+
"eval_runtime": 3.1521,
|
| 27 |
+
"eval_samples_per_second": 541.55,
|
| 28 |
+
"eval_steps_per_second": 17.132,
|
| 29 |
+
"step": 214
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 3.084683895111084,
|
| 34 |
+
"learning_rate": 0.00034688594626573147,
|
| 35 |
+
"loss": 0.5299,
|
| 36 |
+
"step": 428
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.7404803749267721,
|
| 41 |
+
"eval_f1": 0.5179542981501633,
|
| 42 |
+
"eval_loss": 0.5285571813583374,
|
| 43 |
+
"eval_mcc": 0.37347577729616044,
|
| 44 |
+
"eval_precision": 0.68,
|
| 45 |
+
"eval_recall": 0.4182776801405975,
|
| 46 |
+
"eval_runtime": 3.8839,
|
| 47 |
+
"eval_samples_per_second": 439.512,
|
| 48 |
+
"eval_steps_per_second": 13.904,
|
| 49 |
+
"step": 428
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"grad_norm": 1.8376232385635376,
|
| 54 |
+
"learning_rate": 0.0003264808906030414,
|
| 55 |
+
"loss": 0.5041,
|
| 56 |
+
"step": 642
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.7475102519039251,
|
| 61 |
+
"eval_f1": 0.4800965018094088,
|
| 62 |
+
"eval_loss": 0.5334233045578003,
|
| 63 |
+
"eval_mcc": 0.3885026303183633,
|
| 64 |
+
"eval_precision": 0.7653846153846153,
|
| 65 |
+
"eval_recall": 0.34973637961335674,
|
| 66 |
+
"eval_runtime": 3.1807,
|
| 67 |
+
"eval_samples_per_second": 536.674,
|
| 68 |
+
"eval_steps_per_second": 16.977,
|
| 69 |
+
"step": 642
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"grad_norm": 2.807384490966797,
|
| 74 |
+
"learning_rate": 0.00030607583494035134,
|
| 75 |
+
"loss": 0.4955,
|
| 76 |
+
"step": 856
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.0,
|
| 80 |
+
"eval_accuracy": 0.7398945518453427,
|
| 81 |
+
"eval_f1": 0.4422110552763819,
|
| 82 |
+
"eval_loss": 0.5175681710243225,
|
| 83 |
+
"eval_mcc": 0.36720426049390004,
|
| 84 |
+
"eval_precision": 0.775330396475771,
|
| 85 |
+
"eval_recall": 0.3093145869947276,
|
| 86 |
+
"eval_runtime": 3.9525,
|
| 87 |
+
"eval_samples_per_second": 431.878,
|
| 88 |
+
"eval_steps_per_second": 13.662,
|
| 89 |
+
"step": 856
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0,
|
| 93 |
+
"grad_norm": 7.096841335296631,
|
| 94 |
+
"learning_rate": 0.0002856707792776612,
|
| 95 |
+
"loss": 0.4841,
|
| 96 |
+
"step": 1070
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.0,
|
| 100 |
+
"eval_accuracy": 0.7516110134739309,
|
| 101 |
+
"eval_f1": 0.6052141527001862,
|
| 102 |
+
"eval_loss": 0.49192342162132263,
|
| 103 |
+
"eval_mcc": 0.4265647238499904,
|
| 104 |
+
"eval_precision": 0.6435643564356436,
|
| 105 |
+
"eval_recall": 0.5711775043936731,
|
| 106 |
+
"eval_runtime": 3.1288,
|
| 107 |
+
"eval_samples_per_second": 545.582,
|
| 108 |
+
"eval_steps_per_second": 17.259,
|
| 109 |
+
"step": 1070
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"grad_norm": 4.960063457489014,
|
| 114 |
+
"learning_rate": 0.00026526572361497115,
|
| 115 |
+
"loss": 0.4738,
|
| 116 |
+
"step": 1284
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.0,
|
| 120 |
+
"eval_accuracy": 0.7621558289396603,
|
| 121 |
+
"eval_f1": 0.621268656716418,
|
| 122 |
+
"eval_loss": 0.4805011451244354,
|
| 123 |
+
"eval_mcc": 0.4506812006793125,
|
| 124 |
+
"eval_precision": 0.6620278330019881,
|
| 125 |
+
"eval_recall": 0.5852372583479789,
|
| 126 |
+
"eval_runtime": 3.2097,
|
| 127 |
+
"eval_samples_per_second": 531.827,
|
| 128 |
+
"eval_steps_per_second": 16.824,
|
| 129 |
+
"step": 1284
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"grad_norm": 6.75669002532959,
|
| 134 |
+
"learning_rate": 0.000244860667952281,
|
| 135 |
+
"loss": 0.4601,
|
| 136 |
+
"step": 1498
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.0,
|
| 140 |
+
"eval_accuracy": 0.7586408904510837,
|
| 141 |
+
"eval_f1": 0.5264367816091953,
|
| 142 |
+
"eval_loss": 0.4859382212162018,
|
| 143 |
+
"eval_mcc": 0.41956224318934715,
|
| 144 |
+
"eval_precision": 0.760797342192691,
|
| 145 |
+
"eval_recall": 0.4024604569420035,
|
| 146 |
+
"eval_runtime": 3.1647,
|
| 147 |
+
"eval_samples_per_second": 539.388,
|
| 148 |
+
"eval_steps_per_second": 17.063,
|
| 149 |
+
"step": 1498
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"grad_norm": 5.769745349884033,
|
| 154 |
+
"learning_rate": 0.00022445561228959097,
|
| 155 |
+
"loss": 0.4483,
|
| 156 |
+
"step": 1712
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 8.0,
|
| 160 |
+
"eval_accuracy": 0.7785588752196837,
|
| 161 |
+
"eval_f1": 0.6337209302325582,
|
| 162 |
+
"eval_loss": 0.466266006231308,
|
| 163 |
+
"eval_mcc": 0.4826297358701252,
|
| 164 |
+
"eval_precision": 0.7062634989200864,
|
| 165 |
+
"eval_recall": 0.5746924428822495,
|
| 166 |
+
"eval_runtime": 3.8302,
|
| 167 |
+
"eval_samples_per_second": 445.67,
|
| 168 |
+
"eval_steps_per_second": 14.099,
|
| 169 |
+
"step": 1712
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 9.0,
|
| 173 |
+
"grad_norm": 7.356119632720947,
|
| 174 |
+
"learning_rate": 0.00020405055662690085,
|
| 175 |
+
"loss": 0.4408,
|
| 176 |
+
"step": 1926
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 9.0,
|
| 180 |
+
"eval_accuracy": 0.7809021675454013,
|
| 181 |
+
"eval_f1": 0.6191446028513238,
|
| 182 |
+
"eval_loss": 0.46509596705436707,
|
| 183 |
+
"eval_mcc": 0.48266230635542773,
|
| 184 |
+
"eval_precision": 0.7360774818401937,
|
| 185 |
+
"eval_recall": 0.5342706502636204,
|
| 186 |
+
"eval_runtime": 3.1727,
|
| 187 |
+
"eval_samples_per_second": 538.023,
|
| 188 |
+
"eval_steps_per_second": 17.02,
|
| 189 |
+
"step": 1926
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.0,
|
| 193 |
+
"grad_norm": 3.752133369445801,
|
| 194 |
+
"learning_rate": 0.00018364550096421078,
|
| 195 |
+
"loss": 0.4322,
|
| 196 |
+
"step": 2140
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.0,
|
| 200 |
+
"eval_accuracy": 0.7809021675454013,
|
| 201 |
+
"eval_f1": 0.661231884057971,
|
| 202 |
+
"eval_loss": 0.46195492148399353,
|
| 203 |
+
"eval_mcc": 0.5000717628957632,
|
| 204 |
+
"eval_precision": 0.6822429906542056,
|
| 205 |
+
"eval_recall": 0.6414762741652021,
|
| 206 |
+
"eval_runtime": 3.329,
|
| 207 |
+
"eval_samples_per_second": 512.771,
|
| 208 |
+
"eval_steps_per_second": 16.221,
|
| 209 |
+
"step": 2140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 11.0,
|
| 213 |
+
"grad_norm": 2.258147954940796,
|
| 214 |
+
"learning_rate": 0.0001632404453015207,
|
| 215 |
+
"loss": 0.4251,
|
| 216 |
+
"step": 2354
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.0,
|
| 220 |
+
"eval_accuracy": 0.7756297598125366,
|
| 221 |
+
"eval_f1": 0.6135216952573159,
|
| 222 |
+
"eval_loss": 0.46607503294944763,
|
| 223 |
+
"eval_mcc": 0.4705148045618678,
|
| 224 |
+
"eval_precision": 0.7203791469194313,
|
| 225 |
+
"eval_recall": 0.5342706502636204,
|
| 226 |
+
"eval_runtime": 3.1529,
|
| 227 |
+
"eval_samples_per_second": 541.404,
|
| 228 |
+
"eval_steps_per_second": 17.127,
|
| 229 |
+
"step": 2354
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 12.0,
|
| 233 |
+
"grad_norm": 3.4573206901550293,
|
| 234 |
+
"learning_rate": 0.0001428353896388306,
|
| 235 |
+
"loss": 0.417,
|
| 236 |
+
"step": 2568
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 12.0,
|
| 240 |
+
"eval_accuracy": 0.7832454598711189,
|
| 241 |
+
"eval_f1": 0.6777003484320557,
|
| 242 |
+
"eval_loss": 0.4633403718471527,
|
| 243 |
+
"eval_mcc": 0.5144799999787437,
|
| 244 |
+
"eval_precision": 0.6718480138169257,
|
| 245 |
+
"eval_recall": 0.6836555360281195,
|
| 246 |
+
"eval_runtime": 3.2478,
|
| 247 |
+
"eval_samples_per_second": 525.584,
|
| 248 |
+
"eval_steps_per_second": 16.627,
|
| 249 |
+
"step": 2568
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 13.0,
|
| 253 |
+
"grad_norm": 16.82988166809082,
|
| 254 |
+
"learning_rate": 0.0001224303339761405,
|
| 255 |
+
"loss": 0.4122,
|
| 256 |
+
"step": 2782
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 13.0,
|
| 260 |
+
"eval_accuracy": 0.7855887521968365,
|
| 261 |
+
"eval_f1": 0.6623616236162362,
|
| 262 |
+
"eval_loss": 0.47581344842910767,
|
| 263 |
+
"eval_mcc": 0.5072003861458727,
|
| 264 |
+
"eval_precision": 0.6970873786407767,
|
| 265 |
+
"eval_recall": 0.6309314586994728,
|
| 266 |
+
"eval_runtime": 3.1465,
|
| 267 |
+
"eval_samples_per_second": 542.51,
|
| 268 |
+
"eval_steps_per_second": 17.162,
|
| 269 |
+
"step": 2782
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 14.0,
|
| 273 |
+
"grad_norm": 14.468791961669922,
|
| 274 |
+
"learning_rate": 0.00010202527831345042,
|
| 275 |
+
"loss": 0.4053,
|
| 276 |
+
"step": 2996
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 14.0,
|
| 280 |
+
"eval_accuracy": 0.7814879906268307,
|
| 281 |
+
"eval_f1": 0.6642664266426643,
|
| 282 |
+
"eval_loss": 0.464487224817276,
|
| 283 |
+
"eval_mcc": 0.5027717230279147,
|
| 284 |
+
"eval_precision": 0.6808118081180812,
|
| 285 |
+
"eval_recall": 0.648506151142355,
|
| 286 |
+
"eval_runtime": 3.3781,
|
| 287 |
+
"eval_samples_per_second": 505.31,
|
| 288 |
+
"eval_steps_per_second": 15.985,
|
| 289 |
+
"step": 2996
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 15.0,
|
| 293 |
+
"grad_norm": 3.5750694274902344,
|
| 294 |
+
"learning_rate": 8.162022265076034e-05,
|
| 295 |
+
"loss": 0.3972,
|
| 296 |
+
"step": 3210
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 15.0,
|
| 300 |
+
"eval_accuracy": 0.7885178676039836,
|
| 301 |
+
"eval_f1": 0.6762331838565022,
|
| 302 |
+
"eval_loss": 0.4647216796875,
|
| 303 |
+
"eval_mcc": 0.5195513014296814,
|
| 304 |
+
"eval_precision": 0.6904761904761905,
|
| 305 |
+
"eval_recall": 0.6625659050966608,
|
| 306 |
+
"eval_runtime": 3.1634,
|
| 307 |
+
"eval_samples_per_second": 539.617,
|
| 308 |
+
"eval_steps_per_second": 17.07,
|
| 309 |
+
"step": 3210
|
| 310 |
+
}
|
| 311 |
+
],
|
| 312 |
+
"logging_steps": 500,
|
| 313 |
+
"max_steps": 4066,
|
| 314 |
+
"num_input_tokens_seen": 0,
|
| 315 |
+
"num_train_epochs": 19,
|
| 316 |
+
"save_steps": 500,
|
| 317 |
+
"total_flos": 7871634966600.0,
|
| 318 |
+
"train_batch_size": 32,
|
| 319 |
+
"trial_name": null,
|
| 320 |
+
"trial_params": {
|
| 321 |
+
"alpha": 0.9979252549744665,
|
| 322 |
+
"learning_rate": 0.00038769605759111166,
|
| 323 |
+
"num_train_epochs": 19,
|
| 324 |
+
"temperature": 10
|
| 325 |
+
}
|
| 326 |
+
}
|
run-13/checkpoint-3210/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b12fb2f63bffa2782284b94eeaf6256b9b3b77598103b5866035fd51170dd62
|
| 3 |
+
size 5048
|
run-13/checkpoint-3210/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-13/checkpoint-4066/config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 128,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "negative",
|
| 13 |
+
"1": "positive"
|
| 14 |
+
},
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 512,
|
| 17 |
+
"label2id": {
|
| 18 |
+
"negative": "0",
|
| 19 |
+
"positive": "1"
|
| 20 |
+
},
|
| 21 |
+
"layer_norm_eps": 1e-12,
|
| 22 |
+
"max_position_embeddings": 512,
|
| 23 |
+
"model_type": "bert",
|
| 24 |
+
"num_attention_heads": 2,
|
| 25 |
+
"num_hidden_layers": 2,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"position_embedding_type": "absolute",
|
| 28 |
+
"problem_type": "single_label_classification",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.40.0",
|
| 31 |
+
"type_vocab_size": 2,
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 30522
|
| 34 |
+
}
|
run-13/checkpoint-4066/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2282d9169d95f90fa7ab4d7133bc333939d77fd4aa5f26e995771f52ce06d69
|
| 3 |
+
size 17549312
|
run-13/checkpoint-4066/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e5cc5dfc144c3916040e5de519246f984db0a18edb80ba7c4a5c7776204830d
|
| 3 |
+
size 35123898
|
run-13/checkpoint-4066/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:335c6bc456189c92230589543565a97fefda611ed95cf0bd79e6e6e6907ee97a
|
| 3 |
+
size 14308
|
run-13/checkpoint-4066/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fbf92c0e81753487aeffadee0c2255e2bc8fbb551cef130402c61f3e7543d11c
|
| 3 |
+
size 1064
|
run-13/checkpoint-4066/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-13/checkpoint-4066/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-13/checkpoint-4066/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
+
"pad_token": "[PAD]",
|
| 52 |
+
"sep_token": "[SEP]",
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "BertTokenizer",
|
| 56 |
+
"unk_token": "[UNK]"
|
| 57 |
+
}
|
run-13/checkpoint-4066/trainer_state.json
ADDED
|
@@ -0,0 +1,406 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7885178676039836,
|
| 3 |
+
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-3210",
|
| 4 |
+
"epoch": 19.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4066,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 8.763052940368652,
|
| 14 |
+
"learning_rate": 0.00036729100192842157,
|
| 15 |
+
"loss": 0.5966,
|
| 16 |
+
"step": 214
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.7211482132396017,
|
| 21 |
+
"eval_f1": 0.5132924335378324,
|
| 22 |
+
"eval_loss": 0.5418887734413147,
|
| 23 |
+
"eval_mcc": 0.33384466816371045,
|
| 24 |
+
"eval_precision": 0.6136919315403423,
|
| 25 |
+
"eval_recall": 0.44112478031634444,
|
| 26 |
+
"eval_runtime": 3.1521,
|
| 27 |
+
"eval_samples_per_second": 541.55,
|
| 28 |
+
"eval_steps_per_second": 17.132,
|
| 29 |
+
"step": 214
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 3.084683895111084,
|
| 34 |
+
"learning_rate": 0.00034688594626573147,
|
| 35 |
+
"loss": 0.5299,
|
| 36 |
+
"step": 428
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.7404803749267721,
|
| 41 |
+
"eval_f1": 0.5179542981501633,
|
| 42 |
+
"eval_loss": 0.5285571813583374,
|
| 43 |
+
"eval_mcc": 0.37347577729616044,
|
| 44 |
+
"eval_precision": 0.68,
|
| 45 |
+
"eval_recall": 0.4182776801405975,
|
| 46 |
+
"eval_runtime": 3.8839,
|
| 47 |
+
"eval_samples_per_second": 439.512,
|
| 48 |
+
"eval_steps_per_second": 13.904,
|
| 49 |
+
"step": 428
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"grad_norm": 1.8376232385635376,
|
| 54 |
+
"learning_rate": 0.0003264808906030414,
|
| 55 |
+
"loss": 0.5041,
|
| 56 |
+
"step": 642
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.7475102519039251,
|
| 61 |
+
"eval_f1": 0.4800965018094088,
|
| 62 |
+
"eval_loss": 0.5334233045578003,
|
| 63 |
+
"eval_mcc": 0.3885026303183633,
|
| 64 |
+
"eval_precision": 0.7653846153846153,
|
| 65 |
+
"eval_recall": 0.34973637961335674,
|
| 66 |
+
"eval_runtime": 3.1807,
|
| 67 |
+
"eval_samples_per_second": 536.674,
|
| 68 |
+
"eval_steps_per_second": 16.977,
|
| 69 |
+
"step": 642
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"grad_norm": 2.807384490966797,
|
| 74 |
+
"learning_rate": 0.00030607583494035134,
|
| 75 |
+
"loss": 0.4955,
|
| 76 |
+
"step": 856
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.0,
|
| 80 |
+
"eval_accuracy": 0.7398945518453427,
|
| 81 |
+
"eval_f1": 0.4422110552763819,
|
| 82 |
+
"eval_loss": 0.5175681710243225,
|
| 83 |
+
"eval_mcc": 0.36720426049390004,
|
| 84 |
+
"eval_precision": 0.775330396475771,
|
| 85 |
+
"eval_recall": 0.3093145869947276,
|
| 86 |
+
"eval_runtime": 3.9525,
|
| 87 |
+
"eval_samples_per_second": 431.878,
|
| 88 |
+
"eval_steps_per_second": 13.662,
|
| 89 |
+
"step": 856
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0,
|
| 93 |
+
"grad_norm": 7.096841335296631,
|
| 94 |
+
"learning_rate": 0.0002856707792776612,
|
| 95 |
+
"loss": 0.4841,
|
| 96 |
+
"step": 1070
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.0,
|
| 100 |
+
"eval_accuracy": 0.7516110134739309,
|
| 101 |
+
"eval_f1": 0.6052141527001862,
|
| 102 |
+
"eval_loss": 0.49192342162132263,
|
| 103 |
+
"eval_mcc": 0.4265647238499904,
|
| 104 |
+
"eval_precision": 0.6435643564356436,
|
| 105 |
+
"eval_recall": 0.5711775043936731,
|
| 106 |
+
"eval_runtime": 3.1288,
|
| 107 |
+
"eval_samples_per_second": 545.582,
|
| 108 |
+
"eval_steps_per_second": 17.259,
|
| 109 |
+
"step": 1070
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"grad_norm": 4.960063457489014,
|
| 114 |
+
"learning_rate": 0.00026526572361497115,
|
| 115 |
+
"loss": 0.4738,
|
| 116 |
+
"step": 1284
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.0,
|
| 120 |
+
"eval_accuracy": 0.7621558289396603,
|
| 121 |
+
"eval_f1": 0.621268656716418,
|
| 122 |
+
"eval_loss": 0.4805011451244354,
|
| 123 |
+
"eval_mcc": 0.4506812006793125,
|
| 124 |
+
"eval_precision": 0.6620278330019881,
|
| 125 |
+
"eval_recall": 0.5852372583479789,
|
| 126 |
+
"eval_runtime": 3.2097,
|
| 127 |
+
"eval_samples_per_second": 531.827,
|
| 128 |
+
"eval_steps_per_second": 16.824,
|
| 129 |
+
"step": 1284
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"grad_norm": 6.75669002532959,
|
| 134 |
+
"learning_rate": 0.000244860667952281,
|
| 135 |
+
"loss": 0.4601,
|
| 136 |
+
"step": 1498
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.0,
|
| 140 |
+
"eval_accuracy": 0.7586408904510837,
|
| 141 |
+
"eval_f1": 0.5264367816091953,
|
| 142 |
+
"eval_loss": 0.4859382212162018,
|
| 143 |
+
"eval_mcc": 0.41956224318934715,
|
| 144 |
+
"eval_precision": 0.760797342192691,
|
| 145 |
+
"eval_recall": 0.4024604569420035,
|
| 146 |
+
"eval_runtime": 3.1647,
|
| 147 |
+
"eval_samples_per_second": 539.388,
|
| 148 |
+
"eval_steps_per_second": 17.063,
|
| 149 |
+
"step": 1498
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"grad_norm": 5.769745349884033,
|
| 154 |
+
"learning_rate": 0.00022445561228959097,
|
| 155 |
+
"loss": 0.4483,
|
| 156 |
+
"step": 1712
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 8.0,
|
| 160 |
+
"eval_accuracy": 0.7785588752196837,
|
| 161 |
+
"eval_f1": 0.6337209302325582,
|
| 162 |
+
"eval_loss": 0.466266006231308,
|
| 163 |
+
"eval_mcc": 0.4826297358701252,
|
| 164 |
+
"eval_precision": 0.7062634989200864,
|
| 165 |
+
"eval_recall": 0.5746924428822495,
|
| 166 |
+
"eval_runtime": 3.8302,
|
| 167 |
+
"eval_samples_per_second": 445.67,
|
| 168 |
+
"eval_steps_per_second": 14.099,
|
| 169 |
+
"step": 1712
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 9.0,
|
| 173 |
+
"grad_norm": 7.356119632720947,
|
| 174 |
+
"learning_rate": 0.00020405055662690085,
|
| 175 |
+
"loss": 0.4408,
|
| 176 |
+
"step": 1926
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 9.0,
|
| 180 |
+
"eval_accuracy": 0.7809021675454013,
|
| 181 |
+
"eval_f1": 0.6191446028513238,
|
| 182 |
+
"eval_loss": 0.46509596705436707,
|
| 183 |
+
"eval_mcc": 0.48266230635542773,
|
| 184 |
+
"eval_precision": 0.7360774818401937,
|
| 185 |
+
"eval_recall": 0.5342706502636204,
|
| 186 |
+
"eval_runtime": 3.1727,
|
| 187 |
+
"eval_samples_per_second": 538.023,
|
| 188 |
+
"eval_steps_per_second": 17.02,
|
| 189 |
+
"step": 1926
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.0,
|
| 193 |
+
"grad_norm": 3.752133369445801,
|
| 194 |
+
"learning_rate": 0.00018364550096421078,
|
| 195 |
+
"loss": 0.4322,
|
| 196 |
+
"step": 2140
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.0,
|
| 200 |
+
"eval_accuracy": 0.7809021675454013,
|
| 201 |
+
"eval_f1": 0.661231884057971,
|
| 202 |
+
"eval_loss": 0.46195492148399353,
|
| 203 |
+
"eval_mcc": 0.5000717628957632,
|
| 204 |
+
"eval_precision": 0.6822429906542056,
|
| 205 |
+
"eval_recall": 0.6414762741652021,
|
| 206 |
+
"eval_runtime": 3.329,
|
| 207 |
+
"eval_samples_per_second": 512.771,
|
| 208 |
+
"eval_steps_per_second": 16.221,
|
| 209 |
+
"step": 2140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 11.0,
|
| 213 |
+
"grad_norm": 2.258147954940796,
|
| 214 |
+
"learning_rate": 0.0001632404453015207,
|
| 215 |
+
"loss": 0.4251,
|
| 216 |
+
"step": 2354
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.0,
|
| 220 |
+
"eval_accuracy": 0.7756297598125366,
|
| 221 |
+
"eval_f1": 0.6135216952573159,
|
| 222 |
+
"eval_loss": 0.46607503294944763,
|
| 223 |
+
"eval_mcc": 0.4705148045618678,
|
| 224 |
+
"eval_precision": 0.7203791469194313,
|
| 225 |
+
"eval_recall": 0.5342706502636204,
|
| 226 |
+
"eval_runtime": 3.1529,
|
| 227 |
+
"eval_samples_per_second": 541.404,
|
| 228 |
+
"eval_steps_per_second": 17.127,
|
| 229 |
+
"step": 2354
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 12.0,
|
| 233 |
+
"grad_norm": 3.4573206901550293,
|
| 234 |
+
"learning_rate": 0.0001428353896388306,
|
| 235 |
+
"loss": 0.417,
|
| 236 |
+
"step": 2568
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 12.0,
|
| 240 |
+
"eval_accuracy": 0.7832454598711189,
|
| 241 |
+
"eval_f1": 0.6777003484320557,
|
| 242 |
+
"eval_loss": 0.4633403718471527,
|
| 243 |
+
"eval_mcc": 0.5144799999787437,
|
| 244 |
+
"eval_precision": 0.6718480138169257,
|
| 245 |
+
"eval_recall": 0.6836555360281195,
|
| 246 |
+
"eval_runtime": 3.2478,
|
| 247 |
+
"eval_samples_per_second": 525.584,
|
| 248 |
+
"eval_steps_per_second": 16.627,
|
| 249 |
+
"step": 2568
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 13.0,
|
| 253 |
+
"grad_norm": 16.82988166809082,
|
| 254 |
+
"learning_rate": 0.0001224303339761405,
|
| 255 |
+
"loss": 0.4122,
|
| 256 |
+
"step": 2782
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 13.0,
|
| 260 |
+
"eval_accuracy": 0.7855887521968365,
|
| 261 |
+
"eval_f1": 0.6623616236162362,
|
| 262 |
+
"eval_loss": 0.47581344842910767,
|
| 263 |
+
"eval_mcc": 0.5072003861458727,
|
| 264 |
+
"eval_precision": 0.6970873786407767,
|
| 265 |
+
"eval_recall": 0.6309314586994728,
|
| 266 |
+
"eval_runtime": 3.1465,
|
| 267 |
+
"eval_samples_per_second": 542.51,
|
| 268 |
+
"eval_steps_per_second": 17.162,
|
| 269 |
+
"step": 2782
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 14.0,
|
| 273 |
+
"grad_norm": 14.468791961669922,
|
| 274 |
+
"learning_rate": 0.00010202527831345042,
|
| 275 |
+
"loss": 0.4053,
|
| 276 |
+
"step": 2996
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 14.0,
|
| 280 |
+
"eval_accuracy": 0.7814879906268307,
|
| 281 |
+
"eval_f1": 0.6642664266426643,
|
| 282 |
+
"eval_loss": 0.464487224817276,
|
| 283 |
+
"eval_mcc": 0.5027717230279147,
|
| 284 |
+
"eval_precision": 0.6808118081180812,
|
| 285 |
+
"eval_recall": 0.648506151142355,
|
| 286 |
+
"eval_runtime": 3.3781,
|
| 287 |
+
"eval_samples_per_second": 505.31,
|
| 288 |
+
"eval_steps_per_second": 15.985,
|
| 289 |
+
"step": 2996
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 15.0,
|
| 293 |
+
"grad_norm": 3.5750694274902344,
|
| 294 |
+
"learning_rate": 8.162022265076034e-05,
|
| 295 |
+
"loss": 0.3972,
|
| 296 |
+
"step": 3210
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 15.0,
|
| 300 |
+
"eval_accuracy": 0.7885178676039836,
|
| 301 |
+
"eval_f1": 0.6762331838565022,
|
| 302 |
+
"eval_loss": 0.4647216796875,
|
| 303 |
+
"eval_mcc": 0.5195513014296814,
|
| 304 |
+
"eval_precision": 0.6904761904761905,
|
| 305 |
+
"eval_recall": 0.6625659050966608,
|
| 306 |
+
"eval_runtime": 3.1634,
|
| 307 |
+
"eval_samples_per_second": 539.617,
|
| 308 |
+
"eval_steps_per_second": 17.07,
|
| 309 |
+
"step": 3210
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.0,
|
| 313 |
+
"grad_norm": 5.849695205688477,
|
| 314 |
+
"learning_rate": 6.121516698807025e-05,
|
| 315 |
+
"loss": 0.3948,
|
| 316 |
+
"step": 3424
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 16.0,
|
| 320 |
+
"eval_accuracy": 0.7703573520796719,
|
| 321 |
+
"eval_f1": 0.6711409395973155,
|
| 322 |
+
"eval_loss": 0.47917693853378296,
|
| 323 |
+
"eval_mcc": 0.49648044887604803,
|
| 324 |
+
"eval_precision": 0.6420545746388443,
|
| 325 |
+
"eval_recall": 0.70298769771529,
|
| 326 |
+
"eval_runtime": 3.3554,
|
| 327 |
+
"eval_samples_per_second": 508.739,
|
| 328 |
+
"eval_steps_per_second": 16.094,
|
| 329 |
+
"step": 3424
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 17.0,
|
| 333 |
+
"grad_norm": 13.20305061340332,
|
| 334 |
+
"learning_rate": 4.081011132538017e-05,
|
| 335 |
+
"loss": 0.3958,
|
| 336 |
+
"step": 3638
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 17.0,
|
| 340 |
+
"eval_accuracy": 0.7850029291154071,
|
| 341 |
+
"eval_f1": 0.6760812003530451,
|
| 342 |
+
"eval_loss": 0.47589311003685,
|
| 343 |
+
"eval_mcc": 0.5152027838894037,
|
| 344 |
+
"eval_precision": 0.6790780141843972,
|
| 345 |
+
"eval_recall": 0.6731107205623902,
|
| 346 |
+
"eval_runtime": 3.1566,
|
| 347 |
+
"eval_samples_per_second": 540.765,
|
| 348 |
+
"eval_steps_per_second": 17.107,
|
| 349 |
+
"step": 3638
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 18.0,
|
| 353 |
+
"grad_norm": 4.045512676239014,
|
| 354 |
+
"learning_rate": 2.0405055662690086e-05,
|
| 355 |
+
"loss": 0.3873,
|
| 356 |
+
"step": 3852
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 18.0,
|
| 360 |
+
"eval_accuracy": 0.7867603983596954,
|
| 361 |
+
"eval_f1": 0.6738351254480287,
|
| 362 |
+
"eval_loss": 0.47346317768096924,
|
| 363 |
+
"eval_mcc": 0.5157490976144277,
|
| 364 |
+
"eval_precision": 0.6873857404021938,
|
| 365 |
+
"eval_recall": 0.6608084358523726,
|
| 366 |
+
"eval_runtime": 3.8927,
|
| 367 |
+
"eval_samples_per_second": 438.512,
|
| 368 |
+
"eval_steps_per_second": 13.872,
|
| 369 |
+
"step": 3852
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 19.0,
|
| 373 |
+
"grad_norm": 5.878767967224121,
|
| 374 |
+
"learning_rate": 0.0,
|
| 375 |
+
"loss": 0.3795,
|
| 376 |
+
"step": 4066
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 19.0,
|
| 380 |
+
"eval_accuracy": 0.7832454598711189,
|
| 381 |
+
"eval_f1": 0.6760070052539404,
|
| 382 |
+
"eval_loss": 0.47538015246391296,
|
| 383 |
+
"eval_mcc": 0.5131650023345729,
|
| 384 |
+
"eval_precision": 0.6736474694589878,
|
| 385 |
+
"eval_recall": 0.6783831282952548,
|
| 386 |
+
"eval_runtime": 3.1451,
|
| 387 |
+
"eval_samples_per_second": 542.748,
|
| 388 |
+
"eval_steps_per_second": 17.17,
|
| 389 |
+
"step": 4066
|
| 390 |
+
}
|
| 391 |
+
],
|
| 392 |
+
"logging_steps": 500,
|
| 393 |
+
"max_steps": 4066,
|
| 394 |
+
"num_input_tokens_seen": 0,
|
| 395 |
+
"num_train_epochs": 19,
|
| 396 |
+
"save_steps": 500,
|
| 397 |
+
"total_flos": 9970737624360.0,
|
| 398 |
+
"train_batch_size": 32,
|
| 399 |
+
"trial_name": null,
|
| 400 |
+
"trial_params": {
|
| 401 |
+
"alpha": 0.9979252549744665,
|
| 402 |
+
"learning_rate": 0.00038769605759111166,
|
| 403 |
+
"num_train_epochs": 19,
|
| 404 |
+
"temperature": 10
|
| 405 |
+
}
|
| 406 |
+
}
|
run-13/checkpoint-4066/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b12fb2f63bffa2782284b94eeaf6256b9b3b77598103b5866035fd51170dd62
|
| 3 |
+
size 5048
|
run-13/checkpoint-4066/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b12fb2f63bffa2782284b94eeaf6256b9b3b77598103b5866035fd51170dd62
|
| 3 |
size 5048
|