Training in progress, epoch 11
Browse files- logs/events.out.tfevents.1713593213.1376c752d37a.9760.53 +3 -0
- logs/events.out.tfevents.1713593452.1376c752d37a.9760.54 +3 -0
- model.safetensors +1 -1
- run-0/checkpoint-214/model.safetensors +1 -1
- run-0/checkpoint-214/optimizer.pt +1 -1
- run-0/checkpoint-214/scheduler.pt +1 -1
- run-0/checkpoint-214/trainer_state.json +13 -13
- run-0/checkpoint-214/training_args.bin +1 -1
- run-0/checkpoint-2996/config.json +34 -0
- run-0/checkpoint-2996/model.safetensors +3 -0
- run-0/checkpoint-2996/optimizer.pt +3 -0
- run-0/checkpoint-2996/rng_state.pth +3 -0
- run-0/checkpoint-2996/scheduler.pt +3 -0
- run-0/checkpoint-2996/special_tokens_map.json +7 -0
- run-0/checkpoint-2996/tokenizer.json +0 -0
- run-0/checkpoint-2996/tokenizer_config.json +57 -0
- run-0/checkpoint-2996/trainer_state.json +306 -0
- run-0/checkpoint-2996/training_args.bin +3 -0
- run-0/checkpoint-2996/vocab.txt +0 -0
- run-1/checkpoint-2140/config.json +34 -0
- run-1/checkpoint-2140/model.safetensors +3 -0
- run-1/checkpoint-2140/optimizer.pt +3 -0
- run-1/checkpoint-2140/rng_state.pth +3 -0
- run-1/checkpoint-2140/scheduler.pt +3 -0
- run-1/checkpoint-2140/special_tokens_map.json +7 -0
- run-1/checkpoint-2140/tokenizer.json +0 -0
- run-1/checkpoint-2140/tokenizer_config.json +57 -0
- run-1/checkpoint-2140/trainer_state.json +226 -0
- run-1/checkpoint-2140/training_args.bin +3 -0
- run-1/checkpoint-2140/vocab.txt +0 -0
- run-1/checkpoint-2354/config.json +34 -0
- run-1/checkpoint-2354/model.safetensors +3 -0
- run-1/checkpoint-2354/optimizer.pt +3 -0
- run-1/checkpoint-2354/rng_state.pth +3 -0
- run-1/checkpoint-2354/scheduler.pt +3 -0
- run-1/checkpoint-2354/special_tokens_map.json +7 -0
- run-1/checkpoint-2354/tokenizer.json +0 -0
- run-1/checkpoint-2354/tokenizer_config.json +57 -0
- run-1/checkpoint-2354/trainer_state.json +246 -0
- run-1/checkpoint-2354/training_args.bin +3 -0
- run-1/checkpoint-2354/vocab.txt +0 -0
- training_args.bin +1 -1
logs/events.out.tfevents.1713593213.1376c752d37a.9760.53
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e9d3d6e640e32578cdda671e0d9e24e50fb34c17e4467b100f3b1d287c108c1
|
| 3 |
+
size 15328
|
logs/events.out.tfevents.1713593452.1376c752d37a.9760.54
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c29bb2f106d8d7d746635fe5aed243dec0ba91996f45ad0adca8c65610500cc8
|
| 3 |
+
size 13136
|
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:dbec1f24b0dd6424b800ee43d82ad08f76324c77508985422e71a486f73e8ae5
|
| 3 |
size 17549312
|
run-0/checkpoint-214/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 sha256:516adb2bc811a1a0e97e9b5f0a9a920601cd2fa195fec8c8e40447d5c6720f23
|
| 3 |
size 17549312
|
run-0/checkpoint-214/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 35123898
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfb00241f34d7682f0ce30a5d1baba6baec6c4c2bb17db518950d668a0d43db6
|
| 3 |
size 35123898
|
run-0/checkpoint-214/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 sha256:4cc2ee9f11db6435a9399184a28e4949defdb7cd018d93c93beb40c85b67545d
|
| 3 |
size 1064
|
run-0/checkpoint-214/trainer_state.json
CHANGED
|
@@ -10,37 +10,37 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 214
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.0,
|
| 20 |
"eval_accuracy": 0.6666666666666666,
|
| 21 |
"eval_f1": 0.0,
|
| 22 |
-
"eval_loss": 0.
|
| 23 |
"eval_mcc": 0.0,
|
| 24 |
"eval_precision": 0.0,
|
| 25 |
"eval_recall": 0.0,
|
| 26 |
-
"eval_runtime": 3.
|
| 27 |
-
"eval_samples_per_second":
|
| 28 |
-
"eval_steps_per_second":
|
| 29 |
"step": 214
|
| 30 |
}
|
| 31 |
],
|
| 32 |
"logging_steps": 500,
|
| 33 |
-
"max_steps":
|
| 34 |
"num_input_tokens_seen": 0,
|
| 35 |
-
"num_train_epochs":
|
| 36 |
"save_steps": 500,
|
| 37 |
"total_flos": 524775664440.0,
|
| 38 |
"train_batch_size": 32,
|
| 39 |
"trial_name": null,
|
| 40 |
"trial_params": {
|
| 41 |
-
"alpha": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"num_train_epochs":
|
| 44 |
-
"temperature":
|
| 45 |
}
|
| 46 |
}
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 0.3824027478694916,
|
| 14 |
+
"learning_rate": 5.531898354978819e-05,
|
| 15 |
+
"loss": 0.0835,
|
| 16 |
"step": 214
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.0,
|
| 20 |
"eval_accuracy": 0.6666666666666666,
|
| 21 |
"eval_f1": 0.0,
|
| 22 |
+
"eval_loss": 0.06421080976724625,
|
| 23 |
"eval_mcc": 0.0,
|
| 24 |
"eval_precision": 0.0,
|
| 25 |
"eval_recall": 0.0,
|
| 26 |
+
"eval_runtime": 3.1927,
|
| 27 |
+
"eval_samples_per_second": 534.663,
|
| 28 |
+
"eval_steps_per_second": 16.914,
|
| 29 |
"step": 214
|
| 30 |
}
|
| 31 |
],
|
| 32 |
"logging_steps": 500,
|
| 33 |
+
"max_steps": 2996,
|
| 34 |
"num_input_tokens_seen": 0,
|
| 35 |
+
"num_train_epochs": 14,
|
| 36 |
"save_steps": 500,
|
| 37 |
"total_flos": 524775664440.0,
|
| 38 |
"train_batch_size": 32,
|
| 39 |
"trial_name": null,
|
| 40 |
"trial_params": {
|
| 41 |
+
"alpha": 0.08651897585698409,
|
| 42 |
+
"learning_rate": 5.9574289976694975e-05,
|
| 43 |
+
"num_train_epochs": 14,
|
| 44 |
+
"temperature": 43
|
| 45 |
}
|
| 46 |
}
|
run-0/checkpoint-214/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 sha256:43fb637dc58b3d23529e81f9c2590c1fd459503a7bb87369b51fad6346ae41da
|
| 3 |
size 5048
|
run-0/checkpoint-2996/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-0/checkpoint-2996/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:627b2a2f4dd817404904b0cdda0393b4dec358c0b8917136b69f256eb64145af
|
| 3 |
+
size 17549312
|
run-0/checkpoint-2996/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b2973bf2e8f0138441be63baed958fed94e3ef55ad1f39bdf0aaeaafeb8d6a6
|
| 3 |
+
size 35123898
|
run-0/checkpoint-2996/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9426185b39d441044107ee0bb63490b78521dba8c90fe388accfdd0dbcbf9fec
|
| 3 |
+
size 14308
|
run-0/checkpoint-2996/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67c2c65264150b0914a79691226988115a8aea931aade13a5fe5e31ff8109390
|
| 3 |
+
size 1064
|
run-0/checkpoint-2996/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-0/checkpoint-2996/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-0/checkpoint-2996/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-0/checkpoint-2996/trainer_state.json
ADDED
|
@@ -0,0 +1,306 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6666666666666666,
|
| 3 |
+
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-214",
|
| 4 |
+
"epoch": 14.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2996,
|
| 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": 0.3824027478694916,
|
| 14 |
+
"learning_rate": 5.531898354978819e-05,
|
| 15 |
+
"loss": 0.0835,
|
| 16 |
+
"step": 214
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.6666666666666666,
|
| 21 |
+
"eval_f1": 0.0,
|
| 22 |
+
"eval_loss": 0.06421080976724625,
|
| 23 |
+
"eval_mcc": 0.0,
|
| 24 |
+
"eval_precision": 0.0,
|
| 25 |
+
"eval_recall": 0.0,
|
| 26 |
+
"eval_runtime": 3.1927,
|
| 27 |
+
"eval_samples_per_second": 534.663,
|
| 28 |
+
"eval_steps_per_second": 16.914,
|
| 29 |
+
"step": 214
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 0.4931301176548004,
|
| 34 |
+
"learning_rate": 5.10636771228814e-05,
|
| 35 |
+
"loss": 0.066,
|
| 36 |
+
"step": 428
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.6666666666666666,
|
| 41 |
+
"eval_f1": 0.006980802792321117,
|
| 42 |
+
"eval_loss": 0.06297493726015091,
|
| 43 |
+
"eval_mcc": 0.01713474628469157,
|
| 44 |
+
"eval_precision": 0.5,
|
| 45 |
+
"eval_recall": 0.0035149384885764497,
|
| 46 |
+
"eval_runtime": 3.3168,
|
| 47 |
+
"eval_samples_per_second": 514.655,
|
| 48 |
+
"eval_steps_per_second": 16.281,
|
| 49 |
+
"step": 428
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"grad_norm": 0.38297247886657715,
|
| 54 |
+
"learning_rate": 4.6808370695974625e-05,
|
| 55 |
+
"loss": 0.0648,
|
| 56 |
+
"step": 642
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.6666666666666666,
|
| 61 |
+
"eval_f1": 0.013864818024263433,
|
| 62 |
+
"eval_loss": 0.06352359801530838,
|
| 63 |
+
"eval_mcc": 0.024260699053001704,
|
| 64 |
+
"eval_precision": 0.5,
|
| 65 |
+
"eval_recall": 0.007029876977152899,
|
| 66 |
+
"eval_runtime": 3.1502,
|
| 67 |
+
"eval_samples_per_second": 541.864,
|
| 68 |
+
"eval_steps_per_second": 17.142,
|
| 69 |
+
"step": 642
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"grad_norm": 0.4884311258792877,
|
| 74 |
+
"learning_rate": 4.255306426906784e-05,
|
| 75 |
+
"loss": 0.0642,
|
| 76 |
+
"step": 856
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.0,
|
| 80 |
+
"eval_accuracy": 0.6666666666666666,
|
| 81 |
+
"eval_f1": 0.017271157167530225,
|
| 82 |
+
"eval_loss": 0.06221030279994011,
|
| 83 |
+
"eval_mcc": 0.027140265094376777,
|
| 84 |
+
"eval_precision": 0.5,
|
| 85 |
+
"eval_recall": 0.008787346221441126,
|
| 86 |
+
"eval_runtime": 3.7762,
|
| 87 |
+
"eval_samples_per_second": 452.044,
|
| 88 |
+
"eval_steps_per_second": 14.3,
|
| 89 |
+
"step": 856
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0,
|
| 93 |
+
"grad_norm": 0.7101069688796997,
|
| 94 |
+
"learning_rate": 3.829775784216106e-05,
|
| 95 |
+
"loss": 0.064,
|
| 96 |
+
"step": 1070
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.0,
|
| 100 |
+
"eval_accuracy": 0.6666666666666666,
|
| 101 |
+
"eval_f1": 0.017271157167530225,
|
| 102 |
+
"eval_loss": 0.06226570904254913,
|
| 103 |
+
"eval_mcc": 0.027140265094376777,
|
| 104 |
+
"eval_precision": 0.5,
|
| 105 |
+
"eval_recall": 0.008787346221441126,
|
| 106 |
+
"eval_runtime": 3.1334,
|
| 107 |
+
"eval_samples_per_second": 544.769,
|
| 108 |
+
"eval_steps_per_second": 17.233,
|
| 109 |
+
"step": 1070
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"grad_norm": 0.42137953639030457,
|
| 114 |
+
"learning_rate": 3.404245141525427e-05,
|
| 115 |
+
"loss": 0.0637,
|
| 116 |
+
"step": 1284
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.0,
|
| 120 |
+
"eval_accuracy": 0.6649091974223784,
|
| 121 |
+
"eval_f1": 0.02389078498293515,
|
| 122 |
+
"eval_loss": 0.06161979213356972,
|
| 123 |
+
"eval_mcc": 0.016686958293742785,
|
| 124 |
+
"eval_precision": 0.4117647058823529,
|
| 125 |
+
"eval_recall": 0.012302284710017574,
|
| 126 |
+
"eval_runtime": 3.2462,
|
| 127 |
+
"eval_samples_per_second": 525.852,
|
| 128 |
+
"eval_steps_per_second": 16.635,
|
| 129 |
+
"step": 1284
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"grad_norm": 0.4732053279876709,
|
| 134 |
+
"learning_rate": 2.9787144988347488e-05,
|
| 135 |
+
"loss": 0.0634,
|
| 136 |
+
"step": 1498
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.0,
|
| 140 |
+
"eval_accuracy": 0.664323374340949,
|
| 141 |
+
"eval_f1": 0.020512820512820513,
|
| 142 |
+
"eval_loss": 0.061539050191640854,
|
| 143 |
+
"eval_mcc": 0.008597718124511362,
|
| 144 |
+
"eval_precision": 0.375,
|
| 145 |
+
"eval_recall": 0.01054481546572935,
|
| 146 |
+
"eval_runtime": 3.1722,
|
| 147 |
+
"eval_samples_per_second": 538.12,
|
| 148 |
+
"eval_steps_per_second": 17.023,
|
| 149 |
+
"step": 1498
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"grad_norm": 0.4758211374282837,
|
| 154 |
+
"learning_rate": 2.55318385614407e-05,
|
| 155 |
+
"loss": 0.0631,
|
| 156 |
+
"step": 1712
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 8.0,
|
| 160 |
+
"eval_accuracy": 0.6654950205038078,
|
| 161 |
+
"eval_f1": 0.017211703958691912,
|
| 162 |
+
"eval_loss": 0.061484288424253464,
|
| 163 |
+
"eval_mcc": 0.01487410293271824,
|
| 164 |
+
"eval_precision": 0.4166666666666667,
|
| 165 |
+
"eval_recall": 0.008787346221441126,
|
| 166 |
+
"eval_runtime": 3.1952,
|
| 167 |
+
"eval_samples_per_second": 534.244,
|
| 168 |
+
"eval_steps_per_second": 16.901,
|
| 169 |
+
"step": 1712
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 9.0,
|
| 173 |
+
"grad_norm": 0.3838660418987274,
|
| 174 |
+
"learning_rate": 2.127653213453392e-05,
|
| 175 |
+
"loss": 0.0632,
|
| 176 |
+
"step": 1926
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 9.0,
|
| 180 |
+
"eval_accuracy": 0.6660808435852372,
|
| 181 |
+
"eval_f1": 0.01724137931034483,
|
| 182 |
+
"eval_loss": 0.06174994260072708,
|
| 183 |
+
"eval_mcc": 0.020707884164064556,
|
| 184 |
+
"eval_precision": 0.45454545454545453,
|
| 185 |
+
"eval_recall": 0.008787346221441126,
|
| 186 |
+
"eval_runtime": 3.1409,
|
| 187 |
+
"eval_samples_per_second": 543.466,
|
| 188 |
+
"eval_steps_per_second": 17.192,
|
| 189 |
+
"step": 1926
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.0,
|
| 193 |
+
"grad_norm": 0.3443503677845001,
|
| 194 |
+
"learning_rate": 1.7021225707627134e-05,
|
| 195 |
+
"loss": 0.0629,
|
| 196 |
+
"step": 2140
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.0,
|
| 200 |
+
"eval_accuracy": 0.664323374340949,
|
| 201 |
+
"eval_f1": 0.017152658662092625,
|
| 202 |
+
"eval_loss": 0.061242878437042236,
|
| 203 |
+
"eval_mcc": 0.004592958330124466,
|
| 204 |
+
"eval_precision": 0.35714285714285715,
|
| 205 |
+
"eval_recall": 0.008787346221441126,
|
| 206 |
+
"eval_runtime": 3.1964,
|
| 207 |
+
"eval_samples_per_second": 534.034,
|
| 208 |
+
"eval_steps_per_second": 16.894,
|
| 209 |
+
"step": 2140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 11.0,
|
| 213 |
+
"grad_norm": 0.31307530403137207,
|
| 214 |
+
"learning_rate": 1.276591928072035e-05,
|
| 215 |
+
"loss": 0.0628,
|
| 216 |
+
"step": 2354
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.0,
|
| 220 |
+
"eval_accuracy": 0.6654950205038078,
|
| 221 |
+
"eval_f1": 0.017211703958691912,
|
| 222 |
+
"eval_loss": 0.061483997851610184,
|
| 223 |
+
"eval_mcc": 0.01487410293271824,
|
| 224 |
+
"eval_precision": 0.4166666666666667,
|
| 225 |
+
"eval_recall": 0.008787346221441126,
|
| 226 |
+
"eval_runtime": 3.1572,
|
| 227 |
+
"eval_samples_per_second": 540.674,
|
| 228 |
+
"eval_steps_per_second": 17.104,
|
| 229 |
+
"step": 2354
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 12.0,
|
| 233 |
+
"grad_norm": 0.26839011907577515,
|
| 234 |
+
"learning_rate": 8.510612853813567e-06,
|
| 235 |
+
"loss": 0.0628,
|
| 236 |
+
"step": 2568
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 12.0,
|
| 240 |
+
"eval_accuracy": 0.6654950205038078,
|
| 241 |
+
"eval_f1": 0.017211703958691912,
|
| 242 |
+
"eval_loss": 0.06137599050998688,
|
| 243 |
+
"eval_mcc": 0.01487410293271824,
|
| 244 |
+
"eval_precision": 0.4166666666666667,
|
| 245 |
+
"eval_recall": 0.008787346221441126,
|
| 246 |
+
"eval_runtime": 3.1832,
|
| 247 |
+
"eval_samples_per_second": 536.247,
|
| 248 |
+
"eval_steps_per_second": 16.964,
|
| 249 |
+
"step": 2568
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 13.0,
|
| 253 |
+
"grad_norm": 0.8179745674133301,
|
| 254 |
+
"learning_rate": 4.2553064269067835e-06,
|
| 255 |
+
"loss": 0.0626,
|
| 256 |
+
"step": 2782
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 13.0,
|
| 260 |
+
"eval_accuracy": 0.6654950205038078,
|
| 261 |
+
"eval_f1": 0.017211703958691912,
|
| 262 |
+
"eval_loss": 0.06123984605073929,
|
| 263 |
+
"eval_mcc": 0.01487410293271824,
|
| 264 |
+
"eval_precision": 0.4166666666666667,
|
| 265 |
+
"eval_recall": 0.008787346221441126,
|
| 266 |
+
"eval_runtime": 3.1468,
|
| 267 |
+
"eval_samples_per_second": 542.461,
|
| 268 |
+
"eval_steps_per_second": 17.16,
|
| 269 |
+
"step": 2782
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 14.0,
|
| 273 |
+
"grad_norm": 0.34526437520980835,
|
| 274 |
+
"learning_rate": 0.0,
|
| 275 |
+
"loss": 0.0624,
|
| 276 |
+
"step": 2996
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 14.0,
|
| 280 |
+
"eval_accuracy": 0.6654950205038078,
|
| 281 |
+
"eval_f1": 0.017211703958691912,
|
| 282 |
+
"eval_loss": 0.061105918139219284,
|
| 283 |
+
"eval_mcc": 0.01487410293271824,
|
| 284 |
+
"eval_precision": 0.4166666666666667,
|
| 285 |
+
"eval_recall": 0.008787346221441126,
|
| 286 |
+
"eval_runtime": 3.9414,
|
| 287 |
+
"eval_samples_per_second": 433.098,
|
| 288 |
+
"eval_steps_per_second": 13.701,
|
| 289 |
+
"step": 2996
|
| 290 |
+
}
|
| 291 |
+
],
|
| 292 |
+
"logging_steps": 500,
|
| 293 |
+
"max_steps": 2996,
|
| 294 |
+
"num_input_tokens_seen": 0,
|
| 295 |
+
"num_train_epochs": 14,
|
| 296 |
+
"save_steps": 500,
|
| 297 |
+
"total_flos": 7346859302160.0,
|
| 298 |
+
"train_batch_size": 32,
|
| 299 |
+
"trial_name": null,
|
| 300 |
+
"trial_params": {
|
| 301 |
+
"alpha": 0.08651897585698409,
|
| 302 |
+
"learning_rate": 5.9574289976694975e-05,
|
| 303 |
+
"num_train_epochs": 14,
|
| 304 |
+
"temperature": 43
|
| 305 |
+
}
|
| 306 |
+
}
|
run-0/checkpoint-2996/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43fb637dc58b3d23529e81f9c2590c1fd459503a7bb87369b51fad6346ae41da
|
| 3 |
+
size 5048
|
run-0/checkpoint-2996/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-1/checkpoint-2140/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-1/checkpoint-2140/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0ee9015035ca4fc6fda13391c8e272110100694e19aa70c459bf4bab0f1329f
|
| 3 |
+
size 17549312
|
run-1/checkpoint-2140/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c1c6392eb8b5b0973b021b886b3b4d774649dc2632b2d576c8bd9dcfb39976d
|
| 3 |
+
size 35123898
|
run-1/checkpoint-2140/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddb16c48b271d0534b9a61cb30864d6f8bb1c10a35f7fb5f704c529b2ed28df1
|
| 3 |
+
size 14308
|
run-1/checkpoint-2140/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:779fcd67b94d2c110080f05d50aad0d23652ffb63d562fa79c77de34dad1bdde
|
| 3 |
+
size 1064
|
run-1/checkpoint-2140/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-1/checkpoint-2140/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-1/checkpoint-2140/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-1/checkpoint-2140/trainer_state.json
ADDED
|
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.700058582308143,
|
| 3 |
+
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-2140",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2140,
|
| 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": 2.750048875808716,
|
| 14 |
+
"learning_rate": 0.0008904595556519428,
|
| 15 |
+
"loss": 0.3982,
|
| 16 |
+
"step": 214
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.6936145284124194,
|
| 21 |
+
"eval_f1": 0.2496413199426112,
|
| 22 |
+
"eval_loss": 0.3941108286380768,
|
| 23 |
+
"eval_mcc": 0.2091898426756361,
|
| 24 |
+
"eval_precision": 0.6796875,
|
| 25 |
+
"eval_recall": 0.15289982425307558,
|
| 26 |
+
"eval_runtime": 3.1574,
|
| 27 |
+
"eval_samples_per_second": 540.639,
|
| 28 |
+
"eval_steps_per_second": 17.103,
|
| 29 |
+
"step": 214
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 1.170525074005127,
|
| 34 |
+
"learning_rate": 0.0008014136000867486,
|
| 35 |
+
"loss": 0.3881,
|
| 36 |
+
"step": 428
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.6666666666666666,
|
| 41 |
+
"eval_f1": 0.0,
|
| 42 |
+
"eval_loss": 0.3913939595222473,
|
| 43 |
+
"eval_mcc": 0.0,
|
| 44 |
+
"eval_precision": 0.0,
|
| 45 |
+
"eval_recall": 0.0,
|
| 46 |
+
"eval_runtime": 3.2957,
|
| 47 |
+
"eval_samples_per_second": 517.943,
|
| 48 |
+
"eval_steps_per_second": 16.385,
|
| 49 |
+
"step": 428
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"grad_norm": 0.8615076541900635,
|
| 54 |
+
"learning_rate": 0.0007123676445215543,
|
| 55 |
+
"loss": 0.3832,
|
| 56 |
+
"step": 642
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.69302870533099,
|
| 61 |
+
"eval_f1": 0.2681564245810056,
|
| 62 |
+
"eval_loss": 0.3964165151119232,
|
| 63 |
+
"eval_mcc": 0.20820116163188562,
|
| 64 |
+
"eval_precision": 0.6530612244897959,
|
| 65 |
+
"eval_recall": 0.1687170474516696,
|
| 66 |
+
"eval_runtime": 3.1559,
|
| 67 |
+
"eval_samples_per_second": 540.891,
|
| 68 |
+
"eval_steps_per_second": 17.111,
|
| 69 |
+
"step": 642
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"grad_norm": 1.2408286333084106,
|
| 74 |
+
"learning_rate": 0.00062332168895636,
|
| 75 |
+
"loss": 0.3935,
|
| 76 |
+
"step": 856
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.0,
|
| 80 |
+
"eval_accuracy": 0.6924428822495606,
|
| 81 |
+
"eval_f1": 0.25742574257425743,
|
| 82 |
+
"eval_loss": 0.39223405718803406,
|
| 83 |
+
"eval_mcc": 0.20514822121510018,
|
| 84 |
+
"eval_precision": 0.6594202898550725,
|
| 85 |
+
"eval_recall": 0.15992970123022848,
|
| 86 |
+
"eval_runtime": 3.8392,
|
| 87 |
+
"eval_samples_per_second": 444.629,
|
| 88 |
+
"eval_steps_per_second": 14.066,
|
| 89 |
+
"step": 856
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0,
|
| 93 |
+
"grad_norm": 3.090942144393921,
|
| 94 |
+
"learning_rate": 0.0005342757333911657,
|
| 95 |
+
"loss": 0.3871,
|
| 96 |
+
"step": 1070
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.0,
|
| 100 |
+
"eval_accuracy": 0.6666666666666666,
|
| 101 |
+
"eval_f1": 0.0,
|
| 102 |
+
"eval_loss": 0.389874130487442,
|
| 103 |
+
"eval_mcc": 0.0,
|
| 104 |
+
"eval_precision": 0.0,
|
| 105 |
+
"eval_recall": 0.0,
|
| 106 |
+
"eval_runtime": 3.1327,
|
| 107 |
+
"eval_samples_per_second": 544.899,
|
| 108 |
+
"eval_steps_per_second": 17.238,
|
| 109 |
+
"step": 1070
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"grad_norm": 2.2668867111206055,
|
| 114 |
+
"learning_rate": 0.0004452297778259714,
|
| 115 |
+
"loss": 0.3881,
|
| 116 |
+
"step": 1284
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.0,
|
| 120 |
+
"eval_accuracy": 0.6977152899824253,
|
| 121 |
+
"eval_f1": 0.26074498567335247,
|
| 122 |
+
"eval_loss": 0.3898678421974182,
|
| 123 |
+
"eval_mcc": 0.22568315247838705,
|
| 124 |
+
"eval_precision": 0.7054263565891473,
|
| 125 |
+
"eval_recall": 0.15992970123022848,
|
| 126 |
+
"eval_runtime": 3.2109,
|
| 127 |
+
"eval_samples_per_second": 531.633,
|
| 128 |
+
"eval_steps_per_second": 16.818,
|
| 129 |
+
"step": 1284
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"grad_norm": 0.9589310884475708,
|
| 134 |
+
"learning_rate": 0.00035618382226077714,
|
| 135 |
+
"loss": 0.3856,
|
| 136 |
+
"step": 1498
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.0,
|
| 140 |
+
"eval_accuracy": 0.690099589923843,
|
| 141 |
+
"eval_f1": 0.18238021638330756,
|
| 142 |
+
"eval_loss": 0.3910105228424072,
|
| 143 |
+
"eval_mcc": 0.19638682696493384,
|
| 144 |
+
"eval_precision": 0.7564102564102564,
|
| 145 |
+
"eval_recall": 0.10369068541300527,
|
| 146 |
+
"eval_runtime": 3.168,
|
| 147 |
+
"eval_samples_per_second": 538.82,
|
| 148 |
+
"eval_steps_per_second": 17.045,
|
| 149 |
+
"step": 1498
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"grad_norm": 1.0469610691070557,
|
| 154 |
+
"learning_rate": 0.00026713786669558284,
|
| 155 |
+
"loss": 0.3795,
|
| 156 |
+
"step": 1712
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 8.0,
|
| 160 |
+
"eval_accuracy": 0.6965436438195665,
|
| 161 |
+
"eval_f1": 0.22686567164179106,
|
| 162 |
+
"eval_loss": 0.3840750753879547,
|
| 163 |
+
"eval_mcc": 0.22297453441408152,
|
| 164 |
+
"eval_precision": 0.7524752475247525,
|
| 165 |
+
"eval_recall": 0.1335676625659051,
|
| 166 |
+
"eval_runtime": 3.305,
|
| 167 |
+
"eval_samples_per_second": 516.497,
|
| 168 |
+
"eval_steps_per_second": 16.339,
|
| 169 |
+
"step": 1712
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 9.0,
|
| 173 |
+
"grad_norm": 0.8197473883628845,
|
| 174 |
+
"learning_rate": 0.00017809191113038857,
|
| 175 |
+
"loss": 0.3762,
|
| 176 |
+
"step": 1926
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 9.0,
|
| 180 |
+
"eval_accuracy": 0.6936145284124194,
|
| 181 |
+
"eval_f1": 0.19908116385911181,
|
| 182 |
+
"eval_loss": 0.3833659291267395,
|
| 183 |
+
"eval_mcc": 0.21257347787570094,
|
| 184 |
+
"eval_precision": 0.7738095238095238,
|
| 185 |
+
"eval_recall": 0.11423550087873462,
|
| 186 |
+
"eval_runtime": 3.1266,
|
| 187 |
+
"eval_samples_per_second": 545.952,
|
| 188 |
+
"eval_steps_per_second": 17.271,
|
| 189 |
+
"step": 1926
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.0,
|
| 193 |
+
"grad_norm": 2.2055039405822754,
|
| 194 |
+
"learning_rate": 8.904595556519429e-05,
|
| 195 |
+
"loss": 0.3738,
|
| 196 |
+
"step": 2140
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.0,
|
| 200 |
+
"eval_accuracy": 0.700058582308143,
|
| 201 |
+
"eval_f1": 0.30997304582210244,
|
| 202 |
+
"eval_loss": 0.3850247263908386,
|
| 203 |
+
"eval_mcc": 0.23609006824017303,
|
| 204 |
+
"eval_precision": 0.6647398843930635,
|
| 205 |
+
"eval_recall": 0.20210896309314588,
|
| 206 |
+
"eval_runtime": 3.1854,
|
| 207 |
+
"eval_samples_per_second": 535.877,
|
| 208 |
+
"eval_steps_per_second": 16.952,
|
| 209 |
+
"step": 2140
|
| 210 |
+
}
|
| 211 |
+
],
|
| 212 |
+
"logging_steps": 500,
|
| 213 |
+
"max_steps": 2354,
|
| 214 |
+
"num_input_tokens_seen": 0,
|
| 215 |
+
"num_train_epochs": 11,
|
| 216 |
+
"save_steps": 500,
|
| 217 |
+
"total_flos": 5247756644400.0,
|
| 218 |
+
"train_batch_size": 32,
|
| 219 |
+
"trial_name": null,
|
| 220 |
+
"trial_params": {
|
| 221 |
+
"alpha": 0.6246941768140464,
|
| 222 |
+
"learning_rate": 0.000979505511217137,
|
| 223 |
+
"num_train_epochs": 11,
|
| 224 |
+
"temperature": 32
|
| 225 |
+
}
|
| 226 |
+
}
|
run-1/checkpoint-2140/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4d143f9ad430eb4bdcb42b2bc68f69577e4d0a45752af31555ead47e276d252
|
| 3 |
+
size 5048
|
run-1/checkpoint-2140/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-1/checkpoint-2354/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-1/checkpoint-2354/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dbec1f24b0dd6424b800ee43d82ad08f76324c77508985422e71a486f73e8ae5
|
| 3 |
+
size 17549312
|
run-1/checkpoint-2354/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c793b4c5556c27883b23f1cf17850ab9aa31144de15998b99f2abfc12531c00
|
| 3 |
+
size 35123898
|
run-1/checkpoint-2354/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d86a1cc2be603ae8ad6d0dcc0791ff88331c7f3e5759ecb7af57b72362de36ff
|
| 3 |
+
size 14308
|
run-1/checkpoint-2354/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc186f296748e42632cafe1c0a9739d24599f9d23133e33adb55c3e250fdd1ba
|
| 3 |
+
size 1064
|
run-1/checkpoint-2354/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-1/checkpoint-2354/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-1/checkpoint-2354/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-1/checkpoint-2354/trainer_state.json
ADDED
|
@@ -0,0 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7012302284710018,
|
| 3 |
+
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-2354",
|
| 4 |
+
"epoch": 11.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2354,
|
| 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": 2.750048875808716,
|
| 14 |
+
"learning_rate": 0.0008904595556519428,
|
| 15 |
+
"loss": 0.3982,
|
| 16 |
+
"step": 214
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_accuracy": 0.6936145284124194,
|
| 21 |
+
"eval_f1": 0.2496413199426112,
|
| 22 |
+
"eval_loss": 0.3941108286380768,
|
| 23 |
+
"eval_mcc": 0.2091898426756361,
|
| 24 |
+
"eval_precision": 0.6796875,
|
| 25 |
+
"eval_recall": 0.15289982425307558,
|
| 26 |
+
"eval_runtime": 3.1574,
|
| 27 |
+
"eval_samples_per_second": 540.639,
|
| 28 |
+
"eval_steps_per_second": 17.103,
|
| 29 |
+
"step": 214
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"grad_norm": 1.170525074005127,
|
| 34 |
+
"learning_rate": 0.0008014136000867486,
|
| 35 |
+
"loss": 0.3881,
|
| 36 |
+
"step": 428
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 2.0,
|
| 40 |
+
"eval_accuracy": 0.6666666666666666,
|
| 41 |
+
"eval_f1": 0.0,
|
| 42 |
+
"eval_loss": 0.3913939595222473,
|
| 43 |
+
"eval_mcc": 0.0,
|
| 44 |
+
"eval_precision": 0.0,
|
| 45 |
+
"eval_recall": 0.0,
|
| 46 |
+
"eval_runtime": 3.2957,
|
| 47 |
+
"eval_samples_per_second": 517.943,
|
| 48 |
+
"eval_steps_per_second": 16.385,
|
| 49 |
+
"step": 428
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 3.0,
|
| 53 |
+
"grad_norm": 0.8615076541900635,
|
| 54 |
+
"learning_rate": 0.0007123676445215543,
|
| 55 |
+
"loss": 0.3832,
|
| 56 |
+
"step": 642
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.0,
|
| 60 |
+
"eval_accuracy": 0.69302870533099,
|
| 61 |
+
"eval_f1": 0.2681564245810056,
|
| 62 |
+
"eval_loss": 0.3964165151119232,
|
| 63 |
+
"eval_mcc": 0.20820116163188562,
|
| 64 |
+
"eval_precision": 0.6530612244897959,
|
| 65 |
+
"eval_recall": 0.1687170474516696,
|
| 66 |
+
"eval_runtime": 3.1559,
|
| 67 |
+
"eval_samples_per_second": 540.891,
|
| 68 |
+
"eval_steps_per_second": 17.111,
|
| 69 |
+
"step": 642
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.0,
|
| 73 |
+
"grad_norm": 1.2408286333084106,
|
| 74 |
+
"learning_rate": 0.00062332168895636,
|
| 75 |
+
"loss": 0.3935,
|
| 76 |
+
"step": 856
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 4.0,
|
| 80 |
+
"eval_accuracy": 0.6924428822495606,
|
| 81 |
+
"eval_f1": 0.25742574257425743,
|
| 82 |
+
"eval_loss": 0.39223405718803406,
|
| 83 |
+
"eval_mcc": 0.20514822121510018,
|
| 84 |
+
"eval_precision": 0.6594202898550725,
|
| 85 |
+
"eval_recall": 0.15992970123022848,
|
| 86 |
+
"eval_runtime": 3.8392,
|
| 87 |
+
"eval_samples_per_second": 444.629,
|
| 88 |
+
"eval_steps_per_second": 14.066,
|
| 89 |
+
"step": 856
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.0,
|
| 93 |
+
"grad_norm": 3.090942144393921,
|
| 94 |
+
"learning_rate": 0.0005342757333911657,
|
| 95 |
+
"loss": 0.3871,
|
| 96 |
+
"step": 1070
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 5.0,
|
| 100 |
+
"eval_accuracy": 0.6666666666666666,
|
| 101 |
+
"eval_f1": 0.0,
|
| 102 |
+
"eval_loss": 0.389874130487442,
|
| 103 |
+
"eval_mcc": 0.0,
|
| 104 |
+
"eval_precision": 0.0,
|
| 105 |
+
"eval_recall": 0.0,
|
| 106 |
+
"eval_runtime": 3.1327,
|
| 107 |
+
"eval_samples_per_second": 544.899,
|
| 108 |
+
"eval_steps_per_second": 17.238,
|
| 109 |
+
"step": 1070
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 6.0,
|
| 113 |
+
"grad_norm": 2.2668867111206055,
|
| 114 |
+
"learning_rate": 0.0004452297778259714,
|
| 115 |
+
"loss": 0.3881,
|
| 116 |
+
"step": 1284
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 6.0,
|
| 120 |
+
"eval_accuracy": 0.6977152899824253,
|
| 121 |
+
"eval_f1": 0.26074498567335247,
|
| 122 |
+
"eval_loss": 0.3898678421974182,
|
| 123 |
+
"eval_mcc": 0.22568315247838705,
|
| 124 |
+
"eval_precision": 0.7054263565891473,
|
| 125 |
+
"eval_recall": 0.15992970123022848,
|
| 126 |
+
"eval_runtime": 3.2109,
|
| 127 |
+
"eval_samples_per_second": 531.633,
|
| 128 |
+
"eval_steps_per_second": 16.818,
|
| 129 |
+
"step": 1284
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 7.0,
|
| 133 |
+
"grad_norm": 0.9589310884475708,
|
| 134 |
+
"learning_rate": 0.00035618382226077714,
|
| 135 |
+
"loss": 0.3856,
|
| 136 |
+
"step": 1498
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 7.0,
|
| 140 |
+
"eval_accuracy": 0.690099589923843,
|
| 141 |
+
"eval_f1": 0.18238021638330756,
|
| 142 |
+
"eval_loss": 0.3910105228424072,
|
| 143 |
+
"eval_mcc": 0.19638682696493384,
|
| 144 |
+
"eval_precision": 0.7564102564102564,
|
| 145 |
+
"eval_recall": 0.10369068541300527,
|
| 146 |
+
"eval_runtime": 3.168,
|
| 147 |
+
"eval_samples_per_second": 538.82,
|
| 148 |
+
"eval_steps_per_second": 17.045,
|
| 149 |
+
"step": 1498
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"grad_norm": 1.0469610691070557,
|
| 154 |
+
"learning_rate": 0.00026713786669558284,
|
| 155 |
+
"loss": 0.3795,
|
| 156 |
+
"step": 1712
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 8.0,
|
| 160 |
+
"eval_accuracy": 0.6965436438195665,
|
| 161 |
+
"eval_f1": 0.22686567164179106,
|
| 162 |
+
"eval_loss": 0.3840750753879547,
|
| 163 |
+
"eval_mcc": 0.22297453441408152,
|
| 164 |
+
"eval_precision": 0.7524752475247525,
|
| 165 |
+
"eval_recall": 0.1335676625659051,
|
| 166 |
+
"eval_runtime": 3.305,
|
| 167 |
+
"eval_samples_per_second": 516.497,
|
| 168 |
+
"eval_steps_per_second": 16.339,
|
| 169 |
+
"step": 1712
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 9.0,
|
| 173 |
+
"grad_norm": 0.8197473883628845,
|
| 174 |
+
"learning_rate": 0.00017809191113038857,
|
| 175 |
+
"loss": 0.3762,
|
| 176 |
+
"step": 1926
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 9.0,
|
| 180 |
+
"eval_accuracy": 0.6936145284124194,
|
| 181 |
+
"eval_f1": 0.19908116385911181,
|
| 182 |
+
"eval_loss": 0.3833659291267395,
|
| 183 |
+
"eval_mcc": 0.21257347787570094,
|
| 184 |
+
"eval_precision": 0.7738095238095238,
|
| 185 |
+
"eval_recall": 0.11423550087873462,
|
| 186 |
+
"eval_runtime": 3.1266,
|
| 187 |
+
"eval_samples_per_second": 545.952,
|
| 188 |
+
"eval_steps_per_second": 17.271,
|
| 189 |
+
"step": 1926
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.0,
|
| 193 |
+
"grad_norm": 2.2055039405822754,
|
| 194 |
+
"learning_rate": 8.904595556519429e-05,
|
| 195 |
+
"loss": 0.3738,
|
| 196 |
+
"step": 2140
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.0,
|
| 200 |
+
"eval_accuracy": 0.700058582308143,
|
| 201 |
+
"eval_f1": 0.30997304582210244,
|
| 202 |
+
"eval_loss": 0.3850247263908386,
|
| 203 |
+
"eval_mcc": 0.23609006824017303,
|
| 204 |
+
"eval_precision": 0.6647398843930635,
|
| 205 |
+
"eval_recall": 0.20210896309314588,
|
| 206 |
+
"eval_runtime": 3.1854,
|
| 207 |
+
"eval_samples_per_second": 535.877,
|
| 208 |
+
"eval_steps_per_second": 16.952,
|
| 209 |
+
"step": 2140
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 11.0,
|
| 213 |
+
"grad_norm": 1.5309932231903076,
|
| 214 |
+
"learning_rate": 0.0,
|
| 215 |
+
"loss": 0.3714,
|
| 216 |
+
"step": 2354
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.0,
|
| 220 |
+
"eval_accuracy": 0.7012302284710018,
|
| 221 |
+
"eval_f1": 0.2877094972067039,
|
| 222 |
+
"eval_loss": 0.38300591707229614,
|
| 223 |
+
"eval_mcc": 0.23920984527918776,
|
| 224 |
+
"eval_precision": 0.7006802721088435,
|
| 225 |
+
"eval_recall": 0.18101933216168717,
|
| 226 |
+
"eval_runtime": 3.1469,
|
| 227 |
+
"eval_samples_per_second": 542.44,
|
| 228 |
+
"eval_steps_per_second": 17.16,
|
| 229 |
+
"step": 2354
|
| 230 |
+
}
|
| 231 |
+
],
|
| 232 |
+
"logging_steps": 500,
|
| 233 |
+
"max_steps": 2354,
|
| 234 |
+
"num_input_tokens_seen": 0,
|
| 235 |
+
"num_train_epochs": 11,
|
| 236 |
+
"save_steps": 500,
|
| 237 |
+
"total_flos": 5772532308840.0,
|
| 238 |
+
"train_batch_size": 32,
|
| 239 |
+
"trial_name": null,
|
| 240 |
+
"trial_params": {
|
| 241 |
+
"alpha": 0.6246941768140464,
|
| 242 |
+
"learning_rate": 0.000979505511217137,
|
| 243 |
+
"num_train_epochs": 11,
|
| 244 |
+
"temperature": 32
|
| 245 |
+
}
|
| 246 |
+
}
|
run-1/checkpoint-2354/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4d143f9ad430eb4bdcb42b2bc68f69577e4d0a45752af31555ead47e276d252
|
| 3 |
+
size 5048
|
run-1/checkpoint-2354/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:c4d143f9ad430eb4bdcb42b2bc68f69577e4d0a45752af31555ead47e276d252
|
| 3 |
size 5048
|