Tech-oriented
commited on
Commit
•
d2885af
1
Parent(s):
12e6133
Training in progress, epoch 1
Browse files- config.json +2 -2
- model.safetensors +1 -1
- run-0/checkpoint-16838/config.json +27 -0
- run-0/checkpoint-16838/model.safetensors +3 -0
- run-0/checkpoint-16838/optimizer.pt +3 -0
- run-0/checkpoint-16838/rng_state.pth +3 -0
- run-0/checkpoint-16838/scheduler.pt +3 -0
- run-0/checkpoint-16838/special_tokens_map.json +7 -0
- run-0/checkpoint-16838/tokenizer.json +0 -0
- run-0/checkpoint-16838/tokenizer_config.json +55 -0
- run-0/checkpoint-16838/trainer_state.json +64 -0
- run-0/checkpoint-16838/training_args.bin +3 -0
- run-0/checkpoint-16838/vocab.txt +0 -0
- runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709748990.e017d622c671.539.0 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -3,11 +3,11 @@
|
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0.
|
7 |
"classifier_dropout": null,
|
8 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
-
"hidden_dropout_prob": 0.
|
11 |
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 3072,
|
|
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.4,
|
7 |
"classifier_dropout": null,
|
8 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.4,
|
11 |
"hidden_size": 768,
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 3072,
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fe6d887c0e874c37b8c334f1e68f370f5e47beb03e4ffcefd564bca362d11b1
|
3 |
size 437958648
|
run-0/checkpoint-16838/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.4,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.4,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
run-0/checkpoint-16838/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1fe6d887c0e874c37b8c334f1e68f370f5e47beb03e4ffcefd564bca362d11b1
|
3 |
+
size 437958648
|
run-0/checkpoint-16838/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34a43795d8cd83e0514d178d3513a19b591523852eb431f25eb86907030e39f7
|
3 |
+
size 876038394
|
run-0/checkpoint-16838/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:837d1125c81927fd4ebe45da3424b13489198e6a7ae66afca6240f0a0a36e34e
|
3 |
+
size 14244
|
run-0/checkpoint-16838/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4debea6bee7398d8b37c0496d1a9d8446f8989b9c61d4aa1cf0b69045da65ad6
|
3 |
+
size 1064
|
run-0/checkpoint-16838/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-16838/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-16838/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-0/checkpoint-16838/trainer_state.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8715596330275229,
|
3 |
+
"best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-0/checkpoint-16838",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 16838,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.25,
|
13 |
+
"grad_norm": 19.703554153442383,
|
14 |
+
"learning_rate": 6.973163454116781e-07,
|
15 |
+
"loss": 0.7045,
|
16 |
+
"step": 4209
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.5,
|
20 |
+
"grad_norm": 33.55769729614258,
|
21 |
+
"learning_rate": 6.508344788890587e-07,
|
22 |
+
"loss": 0.6701,
|
23 |
+
"step": 8418
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.75,
|
27 |
+
"grad_norm": 121.4453353881836,
|
28 |
+
"learning_rate": 6.043526123664394e-07,
|
29 |
+
"loss": 0.566,
|
30 |
+
"step": 12627
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 1.0,
|
34 |
+
"grad_norm": 72.47432708740234,
|
35 |
+
"learning_rate": 5.578707458438201e-07,
|
36 |
+
"loss": 0.5309,
|
37 |
+
"step": 16836
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_accuracy": 0.8715596330275229,
|
42 |
+
"eval_loss": 0.3419412672519684,
|
43 |
+
"eval_runtime": 2.4269,
|
44 |
+
"eval_samples_per_second": 359.309,
|
45 |
+
"eval_steps_per_second": 22.663,
|
46 |
+
"step": 16838
|
47 |
+
}
|
48 |
+
],
|
49 |
+
"logging_steps": 4209,
|
50 |
+
"max_steps": 67352,
|
51 |
+
"num_input_tokens_seen": 0,
|
52 |
+
"num_train_epochs": 4,
|
53 |
+
"save_steps": 500,
|
54 |
+
"total_flos": 828836824376160.0,
|
55 |
+
"train_batch_size": 4,
|
56 |
+
"trial_name": null,
|
57 |
+
"trial_params": {
|
58 |
+
"learning_rate": 7.437982119342974e-07,
|
59 |
+
"num_train_epochs": 4,
|
60 |
+
"per_device_train_batch_size": 4,
|
61 |
+
"seed": 7,
|
62 |
+
"weight_decay": 0.46186751115854463
|
63 |
+
}
|
64 |
+
}
|
run-0/checkpoint-16838/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea2cdb1762dc540953c33889b0130bacb81cb55cd749bc8f619467321c5f1919
|
3 |
+
size 4984
|
run-0/checkpoint-16838/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Mar06_18-14-36_e017d622c671/events.out.tfevents.1709748990.e017d622c671.539.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f327a1818597b92c855d804f2372bd44c3d079eca8ddf172cbc11c4439f7828
|
3 |
+
size 5926
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea2cdb1762dc540953c33889b0130bacb81cb55cd749bc8f619467321c5f1919
|
3 |
size 4984
|