Training in progress, epoch 5
Browse files- logs/events.out.tfevents.1713516835.persepolis.29644.33 +2 -2
- model.safetensors +1 -1
- run-32/checkpoint-2635/config.json +39 -0
- run-32/checkpoint-2635/model.safetensors +3 -0
- run-32/checkpoint-2635/optimizer.pt +3 -0
- run-32/checkpoint-2635/rng_state.pth +3 -0
- run-32/checkpoint-2635/scheduler.pt +3 -0
- run-32/checkpoint-2635/special_tokens_map.json +37 -0
- run-32/checkpoint-2635/tokenizer.json +0 -0
- run-32/checkpoint-2635/tokenizer_config.json +62 -0
- run-32/checkpoint-2635/trainer_state.json +106 -0
- run-32/checkpoint-2635/training_args.bin +3 -0
- run-32/checkpoint-2635/vocab.txt +0 -0
logs/events.out.tfevents.1713516835.persepolis.29644.33
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 sha256:48e85509e665c09bab6892a61545c6ee3f14414fd28feb1c8727c16b4ca99030
|
3 |
+
size 7968
|
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 sha256:5502dbc50d923f1bdce3748358e5ef79d7e5b4dc98e26db8cddde4700a7927f8
|
3 |
size 54221200
|
run-32/checkpoint-2635/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-32/checkpoint-2635/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5502dbc50d923f1bdce3748358e5ef79d7e5b4dc98e26db8cddde4700a7927f8
|
3 |
+
size 54221200
|
run-32/checkpoint-2635/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60cceda75f245ac72fb2c20943f79521c3d692fb5f3b4396c7308f07e2e7d99d
|
3 |
+
size 108564282
|
run-32/checkpoint-2635/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f663bdb15d062023c1cf28c57849d73a5f427a71fc4ff8bd8995ab52fb854b16
|
3 |
+
size 14308
|
run-32/checkpoint-2635/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddada1d92079177c2a2c308ee237f17f3d9639554c9082ec839a113833d6e928
|
3 |
+
size 1064
|
run-32/checkpoint-2635/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-32/checkpoint-2635/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-32/checkpoint-2635/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-32/checkpoint-2635/trainer_state.json
ADDED
@@ -0,0 +1,106 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9208715596330275,
|
3 |
+
"best_model_checkpoint": "electra-distilled-sst\\run-32\\checkpoint-1581",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2635,
|
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": 47.12026596069336,
|
14 |
+
"learning_rate": 4.2569562606597884e-05,
|
15 |
+
"loss": 2.7545,
|
16 |
+
"step": 527
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.8990825688073395,
|
21 |
+
"eval_loss": 1.4578064680099487,
|
22 |
+
"eval_runtime": 1.4519,
|
23 |
+
"eval_samples_per_second": 600.58,
|
24 |
+
"eval_steps_per_second": 4.821,
|
25 |
+
"step": 527
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"grad_norm": 78.47111511230469,
|
30 |
+
"learning_rate": 3.1942296148200405e-05,
|
31 |
+
"loss": 1.283,
|
32 |
+
"step": 1054
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.9071100917431193,
|
37 |
+
"eval_loss": 1.441101312637329,
|
38 |
+
"eval_runtime": 1.4585,
|
39 |
+
"eval_samples_per_second": 597.892,
|
40 |
+
"eval_steps_per_second": 4.8,
|
41 |
+
"step": 1054
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 3.0,
|
45 |
+
"grad_norm": 58.518775939941406,
|
46 |
+
"learning_rate": 2.1315029689802918e-05,
|
47 |
+
"loss": 0.9314,
|
48 |
+
"step": 1581
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 3.0,
|
52 |
+
"eval_accuracy": 0.9208715596330275,
|
53 |
+
"eval_loss": 1.2692312002182007,
|
54 |
+
"eval_runtime": 1.4446,
|
55 |
+
"eval_samples_per_second": 603.643,
|
56 |
+
"eval_steps_per_second": 4.846,
|
57 |
+
"step": 1581
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.0,
|
61 |
+
"grad_norm": 19.554431915283203,
|
62 |
+
"learning_rate": 1.0687763231405437e-05,
|
63 |
+
"loss": 0.7341,
|
64 |
+
"step": 2108
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 4.0,
|
68 |
+
"eval_accuracy": 0.9151376146788991,
|
69 |
+
"eval_loss": 1.3720850944519043,
|
70 |
+
"eval_runtime": 1.4488,
|
71 |
+
"eval_samples_per_second": 601.895,
|
72 |
+
"eval_steps_per_second": 4.832,
|
73 |
+
"step": 2108
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 5.0,
|
77 |
+
"grad_norm": 43.02271270751953,
|
78 |
+
"learning_rate": 8.066236401060707e-08,
|
79 |
+
"loss": 0.6406,
|
80 |
+
"step": 2635
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 5.0,
|
84 |
+
"eval_accuracy": 0.9208715596330275,
|
85 |
+
"eval_loss": 1.3230271339416504,
|
86 |
+
"eval_runtime": 1.4499,
|
87 |
+
"eval_samples_per_second": 601.441,
|
88 |
+
"eval_steps_per_second": 4.828,
|
89 |
+
"step": 2635
|
90 |
+
}
|
91 |
+
],
|
92 |
+
"logging_steps": 500,
|
93 |
+
"max_steps": 2635,
|
94 |
+
"num_input_tokens_seen": 0,
|
95 |
+
"num_train_epochs": 5,
|
96 |
+
"save_steps": 500,
|
97 |
+
"total_flos": 936602651243304.0,
|
98 |
+
"train_batch_size": 128,
|
99 |
+
"trial_name": null,
|
100 |
+
"trial_params": {
|
101 |
+
"alpha": 0.2744072380603728,
|
102 |
+
"learning_rate": 5.313633229198741e-05,
|
103 |
+
"num_train_epochs": 5,
|
104 |
+
"temperature": 16
|
105 |
+
}
|
106 |
+
}
|
run-32/checkpoint-2635/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a7c6aed55f6c62d5fe0946ab5660672fd96249a283a306a3e04368589375210
|
3 |
+
size 5048
|
run-32/checkpoint-2635/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|