Training in progress, epoch 1
Browse files- checkpoint-420/config.json +41 -0
- checkpoint-420/optimizer.pt +3 -0
- checkpoint-420/pytorch_model.bin +3 -0
- checkpoint-420/rng_state.pth +3 -0
- checkpoint-420/scaler.pt +3 -0
- checkpoint-420/scheduler.pt +3 -0
- checkpoint-420/special_tokens_map.json +1 -0
- checkpoint-420/tokenizer.json +0 -0
- checkpoint-420/tokenizer_config.json +1 -0
- checkpoint-420/trainer_state.json +48 -0
- checkpoint-420/training_args.bin +3 -0
- checkpoint-420/vocab.txt +0 -0
- pytorch_model.bin +1 -1
checkpoint-420/config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "ynie/electra-large-discriminator-snli_mnli_fever_anli_R1_R2_R3-nli",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 1024,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"id2label": {
|
13 |
+
"0": "entailment",
|
14 |
+
"1": "neutral",
|
15 |
+
"2": "contradiction"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 4096,
|
19 |
+
"label2id": {
|
20 |
+
"contradiction": 2,
|
21 |
+
"entailment": 0,
|
22 |
+
"neutral": 1
|
23 |
+
},
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "electra",
|
27 |
+
"num_attention_heads": 16,
|
28 |
+
"num_hidden_layers": 24,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"problem_type": "multi_label_classification",
|
32 |
+
"summary_activation": "gelu",
|
33 |
+
"summary_last_dropout": 0.1,
|
34 |
+
"summary_type": "first",
|
35 |
+
"summary_use_proj": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.17.0",
|
38 |
+
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
checkpoint-420/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bdf85ad585dbaa35d4afba2e6f7d942c66145d8f0808e33e3935ffec451f06dd
|
3 |
+
size 2681386461
|
checkpoint-420/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6c8fd2bdb5258b01e80bd96f7a29e8d580120dce389ca768695f9b780bc7b7a
|
3 |
+
size 1340745837
|
checkpoint-420/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61ce4e6bd7437c4db45054e19131618018cfd9fc463cdc2b850ec541aba2c02a
|
3 |
+
size 14503
|
checkpoint-420/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7eac8f2c713df220f838631ce5ff2e9a9c3e629550745b838100c2409550e14d
|
3 |
+
size 559
|
checkpoint-420/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f780f734ba8eb075cb1051185a4b09e62dba6718d09c3fdde66f376a2397b87
|
3 |
+
size 623
|
checkpoint-420/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-420/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-420/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "normalization": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "google/electra-large-discriminator", "tokenizer_class": "ElectraTokenizer"}
|
checkpoint-420/trainer_state.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3519645631313324,
|
3 |
+
"best_model_checkpoint": "outputs/electra-nli-efl/checkpoint-420",
|
4 |
+
"epoch": 1.9955555555555555,
|
5 |
+
"global_step": 420,
|
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": 9.499999999999999e-07,
|
13 |
+
"loss": 0.4175,
|
14 |
+
"step": 210
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.7316666666666667,
|
19 |
+
"eval_f1": 0.7305281480923569,
|
20 |
+
"eval_loss": 0.4019607603549957,
|
21 |
+
"eval_runtime": 11.5986,
|
22 |
+
"eval_samples_per_second": 258.651,
|
23 |
+
"eval_steps_per_second": 32.331,
|
24 |
+
"step": 210
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"learning_rate": 9e-07,
|
29 |
+
"loss": 0.3061,
|
30 |
+
"step": 420
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.768,
|
35 |
+
"eval_f1": 0.7674936528439713,
|
36 |
+
"eval_loss": 0.3519645631313324,
|
37 |
+
"eval_runtime": 11.6033,
|
38 |
+
"eval_samples_per_second": 258.548,
|
39 |
+
"eval_steps_per_second": 32.319,
|
40 |
+
"step": 420
|
41 |
+
}
|
42 |
+
],
|
43 |
+
"max_steps": 4200,
|
44 |
+
"num_train_epochs": 20,
|
45 |
+
"total_flos": 8319029914324608.0,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": null
|
48 |
+
}
|
checkpoint-420/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c104103a95a8e00f67dc451eba8bec78c0cbf934c84f4059200155cf9a45b752
|
3 |
+
size 3119
|
checkpoint-420/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 1340745837
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6c8fd2bdb5258b01e80bd96f7a29e8d580120dce389ca768695f9b780bc7b7a
|
3 |
size 1340745837
|