Training in progress, epoch 2
Browse files- logs/events.out.tfevents.1709846785.013ec1551212.75384.16 +2 -2
- model.safetensors +1 -1
- run-16/checkpoint-1532/config.json +34 -0
- run-16/checkpoint-1532/model.safetensors +3 -0
- run-16/checkpoint-1532/optimizer.pt +3 -0
- run-16/checkpoint-1532/rng_state.pth +3 -0
- run-16/checkpoint-1532/scheduler.pt +3 -0
- run-16/checkpoint-1532/special_tokens_map.json +7 -0
- run-16/checkpoint-1532/tokenizer.json +0 -0
- run-16/checkpoint-1532/tokenizer_config.json +57 -0
- run-16/checkpoint-1532/trainer_state.json +64 -0
- run-16/checkpoint-1532/training_args.bin +3 -0
- run-16/checkpoint-1532/vocab.txt +0 -0
logs/events.out.tfevents.1709846785.013ec1551212.75384.16
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f97c0f7a0fb6806b2c75765b0e787e6cdf1620fb43be1ad1482533e01ae78fb8
|
3 |
+
size 6009
|
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 sha256:38c20500096d5a8be6899ca8cd8410bf3637e1b33603715423575954df395111
|
3 |
size 17549312
|
run-16/checkpoint-1532/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": "4.38.2",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 30522
|
34 |
+
}
|
run-16/checkpoint-1532/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38c20500096d5a8be6899ca8cd8410bf3637e1b33603715423575954df395111
|
3 |
+
size 17549312
|
run-16/checkpoint-1532/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:485109c7b73286b8e995c841401af140233129c502671e6400789ea08d6ea661
|
3 |
+
size 35122746
|
run-16/checkpoint-1532/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16aaf318a00ee2d6780264865ac856fcd3f746d06b5d79fd7d77f53b35786488
|
3 |
+
size 14054
|
run-16/checkpoint-1532/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e672426b29c48cce67240da7af7d57b680e7fd167aaf5841140c566c7ebcdcc
|
3 |
+
size 1064
|
run-16/checkpoint-1532/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-16/checkpoint-1532/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-16/checkpoint-1532/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-16/checkpoint-1532/trainer_state.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.799412915851272,
|
3 |
+
"best_model_checkpoint": "tiny-bert-sst2-distilled/run-16/checkpoint-1532",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1532,
|
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": 4.586636066436768,
|
14 |
+
"learning_rate": 0.0002815362185318002,
|
15 |
+
"loss": 0.5012,
|
16 |
+
"step": 766
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7847358121330724,
|
21 |
+
"eval_f1": 0.8090277777777778,
|
22 |
+
"eval_loss": 0.4424646198749542,
|
23 |
+
"eval_precision": 0.7269890795631825,
|
24 |
+
"eval_recall": 0.9119373776908023,
|
25 |
+
"eval_runtime": 131.6873,
|
26 |
+
"eval_samples_per_second": 7.761,
|
27 |
+
"eval_steps_per_second": 1.944,
|
28 |
+
"step": 766
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"grad_norm": 4.197028160095215,
|
33 |
+
"learning_rate": 0.00021115216389885013,
|
34 |
+
"loss": 0.4492,
|
35 |
+
"step": 1532
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.799412915851272,
|
40 |
+
"eval_f1": 0.8064211520302172,
|
41 |
+
"eval_loss": 0.440277099609375,
|
42 |
+
"eval_precision": 0.7791970802919708,
|
43 |
+
"eval_recall": 0.8356164383561644,
|
44 |
+
"eval_runtime": 131.1398,
|
45 |
+
"eval_samples_per_second": 7.793,
|
46 |
+
"eval_steps_per_second": 1.952,
|
47 |
+
"step": 1532
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"logging_steps": 500,
|
51 |
+
"max_steps": 3830,
|
52 |
+
"num_input_tokens_seen": 0,
|
53 |
+
"num_train_epochs": 5,
|
54 |
+
"save_steps": 500,
|
55 |
+
"total_flos": 471390394560.0,
|
56 |
+
"train_batch_size": 4,
|
57 |
+
"trial_name": null,
|
58 |
+
"trial_params": {
|
59 |
+
"alpha": 0.7716344444380391,
|
60 |
+
"learning_rate": 0.00035192027316475024,
|
61 |
+
"num_train_epochs": 5,
|
62 |
+
"temperature": 10
|
63 |
+
}
|
64 |
+
}
|
run-16/checkpoint-1532/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:447fc90b16b64e1ad048ef36b5e745ecb1f888d7304a1aea1048d24a1dc2951f
|
3 |
+
size 4920
|
run-16/checkpoint-1532/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|