Training in progress, epoch 3
Browse files- logs/events.out.tfevents.1713504727.persepolis.29644.2 +2 -2
- model.safetensors +1 -1
- run-1/checkpoint-1581/config.json +39 -0
- run-1/checkpoint-1581/model.safetensors +3 -0
- run-1/checkpoint-1581/optimizer.pt +3 -0
- run-1/checkpoint-1581/rng_state.pth +3 -0
- run-1/checkpoint-1581/scheduler.pt +3 -0
- run-1/checkpoint-1581/special_tokens_map.json +37 -0
- run-1/checkpoint-1581/tokenizer.json +0 -0
- run-1/checkpoint-1581/tokenizer_config.json +62 -0
- run-1/checkpoint-1581/trainer_state.json +74 -0
- run-1/checkpoint-1581/training_args.bin +3 -0
- run-1/checkpoint-1581/vocab.txt +0 -0
logs/events.out.tfevents.1713504727.persepolis.29644.2
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 sha256:4126951e4425ff9474387614016dbcc8f5b90569e42908879ab8af8d2cbc3c8e
|
3 |
+
size 6546
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 54221200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b737fd34a4268f2be2f7b46ae2732c8c63f4f9b5dc1549e07a96a23a6b2750ec
|
3 |
size 54221200
|
run-1/checkpoint-1581/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/electra-small-discriminator",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 128,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "negative",
|
14 |
+
"1": "positive"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 1024,
|
18 |
+
"label2id": {
|
19 |
+
"negative": "0",
|
20 |
+
"positive": "1"
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "electra",
|
25 |
+
"num_attention_heads": 4,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"position_embedding_type": "absolute",
|
29 |
+
"problem_type": "single_label_classification",
|
30 |
+
"summary_activation": "gelu",
|
31 |
+
"summary_last_dropout": 0.1,
|
32 |
+
"summary_type": "first",
|
33 |
+
"summary_use_proj": true,
|
34 |
+
"torch_dtype": "float32",
|
35 |
+
"transformers_version": "4.40.0",
|
36 |
+
"type_vocab_size": 2,
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 30522
|
39 |
+
}
|
run-1/checkpoint-1581/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b737fd34a4268f2be2f7b46ae2732c8c63f4f9b5dc1549e07a96a23a6b2750ec
|
3 |
+
size 54221200
|
run-1/checkpoint-1581/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e020b393bc2fcb05ed90dd1f1c86cd2a6db1ed72629c15056010453cb5678318
|
3 |
+
size 108564282
|
run-1/checkpoint-1581/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:911e9c586a1ec91d8affdbdd2cc5643bbb62a69cfa1f4869c228885fc8d6977d
|
3 |
+
size 14308
|
run-1/checkpoint-1581/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af261909df231e80d41b44505a3284bd3217e015cea7793fc189467ab579fdcd
|
3 |
+
size 1064
|
run-1/checkpoint-1581/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
run-1/checkpoint-1581/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-1581/tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"max_length": 128,
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_to_multiple_of": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"pad_token_type_id": 0,
|
53 |
+
"padding_side": "right",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"stride": 0,
|
56 |
+
"strip_accents": null,
|
57 |
+
"tokenize_chinese_chars": true,
|
58 |
+
"tokenizer_class": "ElectraTokenizer",
|
59 |
+
"truncation_side": "right",
|
60 |
+
"truncation_strategy": "longest_first",
|
61 |
+
"unk_token": "[UNK]"
|
62 |
+
}
|
run-1/checkpoint-1581/trainer_state.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8910550458715596,
|
3 |
+
"best_model_checkpoint": "electra-distilled-sst\\run-1\\checkpoint-1054",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1581,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"grad_norm": 66.74252319335938,
|
14 |
+
"learning_rate": 0.0002000029100592468,
|
15 |
+
"loss": 2.5183,
|
16 |
+
"step": 527
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.875,
|
21 |
+
"eval_loss": 2.3820443153381348,
|
22 |
+
"eval_runtime": 1.4493,
|
23 |
+
"eval_samples_per_second": 601.689,
|
24 |
+
"eval_steps_per_second": 4.83,
|
25 |
+
"step": 527
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"grad_norm": 67.3247299194336,
|
30 |
+
"learning_rate": 0.00015007323994971434,
|
31 |
+
"loss": 1.237,
|
32 |
+
"step": 1054
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.8910550458715596,
|
37 |
+
"eval_loss": 2.0578901767730713,
|
38 |
+
"eval_runtime": 1.4579,
|
39 |
+
"eval_samples_per_second": 598.133,
|
40 |
+
"eval_steps_per_second": 4.802,
|
41 |
+
"step": 1054
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"grad_norm": 9.862482070922852,
|
46 |
+
"learning_rate": 0.00010014356984018184,
|
47 |
+
"loss": 0.8517,
|
48 |
+
"step": 1581
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.8841743119266054,
|
53 |
+
"eval_loss": 2.112179756164551,
|
54 |
+
"eval_runtime": 1.4398,
|
55 |
+
"eval_samples_per_second": 605.639,
|
56 |
+
"eval_steps_per_second": 4.862,
|
57 |
+
"step": 1581
|
58 |
+
}
|
59 |
+
],
|
60 |
+
"logging_steps": 500,
|
61 |
+
"max_steps": 2635,
|
62 |
+
"num_input_tokens_seen": 0,
|
63 |
+
"num_train_epochs": 5,
|
64 |
+
"save_steps": 500,
|
65 |
+
"total_flos": 561038813831964.0,
|
66 |
+
"train_batch_size": 128,
|
67 |
+
"trial_name": null,
|
68 |
+
"trial_params": {
|
69 |
+
"alpha": 0.15523880635662113,
|
70 |
+
"learning_rate": 0.0002496483505476624,
|
71 |
+
"num_train_epochs": 5,
|
72 |
+
"temperature": 16
|
73 |
+
}
|
74 |
+
}
|
run-1/checkpoint-1581/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0ae5bfb8dc04e1587c99a811e9f5c8e620e9e0c3708ec65e7504205f51d366f
|
3 |
+
size 5048
|
run-1/checkpoint-1581/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|