Commit
•
a2a0a0b
1
Parent(s):
8f4e305
Training in progress, epoch 2
Browse files- checkpoint-49088/config.json +38 -0
- checkpoint-49088/optimizer.pt +3 -0
- checkpoint-49088/pytorch_model.bin +3 -0
- checkpoint-49088/rng_state.pth +3 -0
- checkpoint-49088/scheduler.pt +3 -0
- checkpoint-49088/special_tokens_map.json +1 -0
- checkpoint-49088/tokenizer.json +0 -0
- checkpoint-49088/tokenizer_config.json +1 -0
- checkpoint-49088/trainer_state.json +46 -0
- checkpoint-49088/training_args.bin +3 -0
- checkpoint-49088/vocab.txt +0 -0
- pytorch_model.bin +1 -1
- runs/Sep16_20-47-31_patrick-general-gpu/events.out.tfevents.1631825269.patrick-general-gpu.214155.0 +2 -2
checkpoint-49088/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "mnli",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "entailment",
|
15 |
+
"1": "neutral",
|
16 |
+
"2": "contradiction"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"contradiction": 2,
|
22 |
+
"entailment": 0,
|
23 |
+
"neutral": 1
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.11.0.dev0",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 28996
|
38 |
+
}
|
checkpoint-49088/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5c2cc41c664ffb84061869237981ba3097e084c2b3b91a16dc191297e4f0fbd
|
3 |
+
size 866617117
|
checkpoint-49088/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60bff9928df8de5af1600061d3e57816ae7f5c19076a85a27df042d2e92da854
|
3 |
+
size 433334445
|
checkpoint-49088/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52c068cd6a183b2c2b508014549345999785068ab5d9824c515b5aef07b4e4fe
|
3 |
+
size 14503
|
checkpoint-49088/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25e1e657471c4e858539ae144fa0acedae2067597f82cc5bf1030ab590fc7d44
|
3 |
+
size 623
|
checkpoint-49088/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-49088/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-49088/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-49088/trainer_state.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 49088,
|
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": 0.5323,
|
14 |
+
"step": 24544
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.83015792154865,
|
19 |
+
"eval_loss": 0.44308236241340637,
|
20 |
+
"eval_runtime": 99.9144,
|
21 |
+
"eval_samples_per_second": 98.234,
|
22 |
+
"eval_steps_per_second": 12.281,
|
23 |
+
"step": 24544
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.0,
|
27 |
+
"learning_rate": 6.666666666666667e-06,
|
28 |
+
"loss": 0.3447,
|
29 |
+
"step": 49088
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"eval_accuracy": 0.8352521650534895,
|
34 |
+
"eval_loss": 0.47252869606018066,
|
35 |
+
"eval_runtime": 99.9537,
|
36 |
+
"eval_samples_per_second": 98.195,
|
37 |
+
"eval_steps_per_second": 12.276,
|
38 |
+
"step": 49088
|
39 |
+
}
|
40 |
+
],
|
41 |
+
"max_steps": 73632,
|
42 |
+
"num_train_epochs": 3,
|
43 |
+
"total_flos": 2.066503307372421e+17,
|
44 |
+
"trial_name": null,
|
45 |
+
"trial_params": null
|
46 |
+
}
|
checkpoint-49088/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:987dcb06464bd5cbb652af2a7c46c08796060a94cd02142160b0f18314774a7d
|
3 |
+
size 2799
|
checkpoint-49088/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 433334445
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60bff9928df8de5af1600061d3e57816ae7f5c19076a85a27df042d2e92da854
|
3 |
size 433334445
|
runs/Sep16_20-47-31_patrick-general-gpu/events.out.tfevents.1631825269.patrick-general-gpu.214155.0
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:d63dc129ba69e65efaae674942c8bc47ea68e3e1aa9cd0bcbab5228325003383
|
3 |
+
size 4260
|