gchhablani
commited on
Commit
•
a715820
1
Parent(s):
517b899
Training in progress, epoch 1
Browse files- checkpoint-360/config.json +34 -0
- checkpoint-360/optimizer.pt +3 -0
- checkpoint-360/pytorch_model.bin +3 -0
- checkpoint-360/rng_state.pth +3 -0
- checkpoint-360/scheduler.pt +3 -0
- checkpoint-360/special_tokens_map.json +1 -0
- checkpoint-360/tokenizer.json +0 -0
- checkpoint-360/tokenizer_config.json +1 -0
- checkpoint-360/trainer_state.json +33 -0
- checkpoint-360/training_args.bin +3 -0
- checkpoint-360/vocab.txt +0 -0
- config.json +34 -0
- pytorch_model.bin +3 -0
- runs/Sep19_13-18-31_patrick-general-gpu/1632057532.243568/events.out.tfevents.1632057532.patrick-general-gpu.502385.1 +3 -0
- runs/Sep19_13-18-31_patrick-general-gpu/events.out.tfevents.1632057532.patrick-general-gpu.502385.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
checkpoint-360/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "stsb",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"problem_type": "regression",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.11.0.dev0",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 28996
|
34 |
+
}
|
checkpoint-360/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e3e4e4dba2314221923fa486dd0ee1624362ea94ad360e056485179ba0cdcb0a
|
3 |
+
size 866604829
|
checkpoint-360/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b80c09f660bccacd8687d06777f55a5d7f16cd5264eb74ccc521397aed31f7e4
|
3 |
+
size 433328301
|
checkpoint-360/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d98c2d3abf8386b474dc5bdfc7a8d88459dfdf6da4b3bb7a9875efffac678bf2
|
3 |
+
size 14503
|
checkpoint-360/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81034762933d2fc94a82edefefef5e312c2472682c4520f6e2d66896c744af3f
|
3 |
+
size 623
|
checkpoint-360/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
checkpoint-360/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
checkpoint-360/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
|
checkpoint-360/trainer_state.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 360,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 1.3333333333333333e-05,
|
13 |
+
"loss": 1.1174,
|
14 |
+
"step": 360
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_combined_score": 0.8815940360468737,
|
19 |
+
"eval_loss": 0.5000496506690979,
|
20 |
+
"eval_pearson": 0.8832304460348288,
|
21 |
+
"eval_runtime": 15.5329,
|
22 |
+
"eval_samples_per_second": 96.569,
|
23 |
+
"eval_spearmanr": 0.8799576260589187,
|
24 |
+
"eval_steps_per_second": 12.103,
|
25 |
+
"step": 360
|
26 |
+
}
|
27 |
+
],
|
28 |
+
"max_steps": 1080,
|
29 |
+
"num_train_epochs": 3,
|
30 |
+
"total_flos": 1512611876011008.0,
|
31 |
+
"trial_name": null,
|
32 |
+
"trial_params": null
|
33 |
+
}
|
checkpoint-360/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c6a436467da6af93ad95e8ae44ad2dd506ae1137356476d8737342b024b9aaf
|
3 |
+
size 2799
|
checkpoint-360/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "stsb",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0
|
20 |
+
},
|
21 |
+
"layer_norm_eps": 1e-12,
|
22 |
+
"max_position_embeddings": 512,
|
23 |
+
"model_type": "bert",
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"pad_token_id": 0,
|
27 |
+
"position_embedding_type": "absolute",
|
28 |
+
"problem_type": "regression",
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.11.0.dev0",
|
31 |
+
"type_vocab_size": 2,
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 28996
|
34 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b80c09f660bccacd8687d06777f55a5d7f16cd5264eb74ccc521397aed31f7e4
|
3 |
+
size 433328301
|
runs/Sep19_13-18-31_patrick-general-gpu/1632057532.243568/events.out.tfevents.1632057532.patrick-general-gpu.502385.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6947048a8f1fa04bdb60b7bd763f0f79b695e0ac417426e997f41d25f508c4f
|
3 |
+
size 4369
|
runs/Sep19_13-18-31_patrick-general-gpu/events.out.tfevents.1632057532.patrick-general-gpu.502385.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05d67383238a9beac9c7eaa72d6a3e7f5a91024f9860f9fbd9e8d745a2bcfba1
|
3 |
+
size 3778
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c6a436467da6af93ad95e8ae44ad2dd506ae1137356476d8737342b024b9aaf
|
3 |
+
size 2799
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|