Training in progress, epoch 2
Browse files- checkpoint-326/config.json +41 -0
- checkpoint-326/optimizer.pt +3 -0
- checkpoint-326/pytorch_model.bin +3 -0
- checkpoint-326/rng_state.pth +3 -0
- checkpoint-326/scaler.pt +3 -0
- checkpoint-326/scheduler.pt +3 -0
- checkpoint-326/special_tokens_map.json +1 -0
- checkpoint-326/tokenizer.json +0 -0
- checkpoint-326/tokenizer_config.json +1 -0
- checkpoint-326/trainer_state.json +48 -0
- checkpoint-326/training_args.bin +3 -0
- checkpoint-326/vocab.txt +0 -0
- checkpoint-489/config.json +41 -0
- checkpoint-489/optimizer.pt +3 -0
- checkpoint-489/pytorch_model.bin +3 -0
- checkpoint-489/rng_state.pth +3 -0
- checkpoint-489/scaler.pt +3 -0
- checkpoint-489/scheduler.pt +3 -0
- checkpoint-489/special_tokens_map.json +1 -0
- checkpoint-489/tokenizer.json +0 -0
- checkpoint-489/tokenizer_config.json +1 -0
- checkpoint-489/trainer_state.json +64 -0
- checkpoint-489/training_args.bin +3 -0
- checkpoint-489/vocab.txt +0 -0
- pytorch_model.bin +1 -1
checkpoint-326/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": "4.16.2",
|
38 |
+
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
checkpoint-326/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b81e4851c2881dcef711af4697ef50a6462ba5c7e1c5b5e3b8378d35e8f383f
|
3 |
+
size 2681485310
|
checkpoint-326/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86cdd59d0a81eadb0634ce6bcc916feadce861da8cc4cc3451ee185ad4eaa4ac
|
3 |
+
size 1340743917
|
checkpoint-326/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39a0ca327a2af702d5875e110a84b841cab66fcf5223f03d6137027933eb3adb
|
3 |
+
size 14503
|
checkpoint-326/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c8ce0704b9494d69b9eb0069603a0ed18de95a226f489894d03248f831bc5906
|
3 |
+
size 559
|
checkpoint-326/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6aae1bb5b445401f65c6949bbf3e6ceb826aa702ac8501d27afc0137be597724
|
3 |
+
size 623
|
checkpoint-326/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-326/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-326/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-326/trainer_state.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.3409559428691864,
|
3 |
+
"best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-326",
|
4 |
+
"epoch": 1.997323135755258,
|
5 |
+
"global_step": 326,
|
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": 0.4384,
|
14 |
+
"step": 163
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.7444061962134251,
|
19 |
+
"eval_f1": 0.7308261375858633,
|
20 |
+
"eval_loss": 0.39615127444267273,
|
21 |
+
"eval_runtime": 9.0599,
|
22 |
+
"eval_samples_per_second": 256.514,
|
23 |
+
"eval_steps_per_second": 32.119,
|
24 |
+
"step": 163
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"learning_rate": 9e-07,
|
29 |
+
"loss": 0.3447,
|
30 |
+
"step": 326
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.76592082616179,
|
35 |
+
"eval_f1": 0.7552159046464709,
|
36 |
+
"eval_loss": 0.3409559428691864,
|
37 |
+
"eval_runtime": 9.4378,
|
38 |
+
"eval_samples_per_second": 246.244,
|
39 |
+
"eval_steps_per_second": 30.833,
|
40 |
+
"step": 326
|
41 |
+
}
|
42 |
+
],
|
43 |
+
"max_steps": 3260,
|
44 |
+
"num_train_epochs": 20,
|
45 |
+
"total_flos": 6097705758760512.0,
|
46 |
+
"trial_name": null,
|
47 |
+
"trial_params": null
|
48 |
+
}
|
checkpoint-326/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82126e010e751131ea0bffbc21275298a6bdbc244157fe27eed5dd4b7b0d6e0f
|
3 |
+
size 3119
|
checkpoint-326/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-489/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": "4.16.2",
|
38 |
+
"type_vocab_size": 2,
|
39 |
+
"use_cache": true,
|
40 |
+
"vocab_size": 30522
|
41 |
+
}
|
checkpoint-489/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d82fcecb740add996bf5ee0fb32b520102097d0504c5103e7a5e8dd20cb1fa7
|
3 |
+
size 2681485310
|
checkpoint-489/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8cc6e01615d9fbc03a612a6299c16196268fe2e23e228d881f2f3bfa6b3ee9c
|
3 |
+
size 1340743917
|
checkpoint-489/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:014f12f4d9dba30ad7ff0de7b420eb7692dfda6f0502a3815d98e2995bb395f0
|
3 |
+
size 14503
|
checkpoint-489/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b33ea70d27f310dbe6580da93bd08b7140380c500e01a16282e5d91a0fbfcafe
|
3 |
+
size 559
|
checkpoint-489/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08df44e0bd4d8b64139acfaf9c03eb9e41cbfb7bc1e64291bfc485d827865a29
|
3 |
+
size 623
|
checkpoint-489/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-489/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-489/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-489/trainer_state.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.32338443398475647,
|
3 |
+
"best_model_checkpoint": "outputs/electra-nli-efl-tweeteval/checkpoint-489",
|
4 |
+
"epoch": 2.9973231357552583,
|
5 |
+
"global_step": 489,
|
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": 0.4384,
|
14 |
+
"step": 163
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_accuracy": 0.7444061962134251,
|
19 |
+
"eval_f1": 0.7308261375858633,
|
20 |
+
"eval_loss": 0.39615127444267273,
|
21 |
+
"eval_runtime": 9.0599,
|
22 |
+
"eval_samples_per_second": 256.514,
|
23 |
+
"eval_steps_per_second": 32.119,
|
24 |
+
"step": 163
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 2.0,
|
28 |
+
"learning_rate": 9e-07,
|
29 |
+
"loss": 0.3447,
|
30 |
+
"step": 326
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.0,
|
34 |
+
"eval_accuracy": 0.76592082616179,
|
35 |
+
"eval_f1": 0.7552159046464709,
|
36 |
+
"eval_loss": 0.3409559428691864,
|
37 |
+
"eval_runtime": 9.4378,
|
38 |
+
"eval_samples_per_second": 246.244,
|
39 |
+
"eval_steps_per_second": 30.833,
|
40 |
+
"step": 326
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 3.0,
|
44 |
+
"learning_rate": 8.499999999999999e-07,
|
45 |
+
"loss": 0.3057,
|
46 |
+
"step": 489
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 3.0,
|
50 |
+
"eval_accuracy": 0.7749569707401033,
|
51 |
+
"eval_f1": 0.768808341108185,
|
52 |
+
"eval_loss": 0.32338443398475647,
|
53 |
+
"eval_runtime": 9.0418,
|
54 |
+
"eval_samples_per_second": 257.028,
|
55 |
+
"eval_steps_per_second": 32.184,
|
56 |
+
"step": 489
|
57 |
+
}
|
58 |
+
],
|
59 |
+
"max_steps": 3260,
|
60 |
+
"num_train_epochs": 20,
|
61 |
+
"total_flos": 9143325990301824.0,
|
62 |
+
"trial_name": null,
|
63 |
+
"trial_params": null
|
64 |
+
}
|
checkpoint-489/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82126e010e751131ea0bffbc21275298a6bdbc244157fe27eed5dd4b7b0d6e0f
|
3 |
+
size 3119
|
checkpoint-489/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 1340743917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8cc6e01615d9fbc03a612a6299c16196268fe2e23e228d881f2f3bfa6b3ee9c
|
3 |
size 1340743917
|