ana-grassmann
commited on
Commit
•
570069e
1
Parent(s):
9983fdc
Training in progress, epoch 4
Browse files- model.safetensors +1 -1
- run-0/checkpoint-3340/config.json +27 -0
- run-0/checkpoint-3340/model.safetensors +3 -0
- run-0/checkpoint-3340/optimizer.pt +3 -0
- run-0/checkpoint-3340/rng_state.pth +3 -0
- run-0/checkpoint-3340/scheduler.pt +3 -0
- run-0/checkpoint-3340/special_tokens_map.json +7 -0
- run-0/checkpoint-3340/tokenizer.json +0 -0
- run-0/checkpoint-3340/tokenizer_config.json +55 -0
- run-0/checkpoint-3340/trainer_state.json +104 -0
- run-0/checkpoint-3340/training_args.bin +3 -0
- run-0/checkpoint-3340/vocab.txt +0 -0
- runs/Apr07_19-58-20_6f1fc297b560/events.out.tfevents.1712519919.6f1fc297b560.655.0 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437958648
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83289d49a1897a95376dc8056c492e781f94290e22bf6fb5825ca21e8da31d4c
|
3 |
size 437958648
|
run-0/checkpoint-3340/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"type_vocab_size": 2,
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 30522
|
27 |
+
}
|
run-0/checkpoint-3340/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83289d49a1897a95376dc8056c492e781f94290e22bf6fb5825ca21e8da31d4c
|
3 |
+
size 437958648
|
run-0/checkpoint-3340/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8a266a191a0eb41b599f33d17052cfce36a1165ef48e3f30ccc17878371d492
|
3 |
+
size 876038394
|
run-0/checkpoint-3340/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3de9a14559d2c8655716d0cef929b86ff2441146ea1a38fa03c99a3a03b85dfa
|
3 |
+
size 14308
|
run-0/checkpoint-3340/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af800eacdef6985dd8fb4b53472ad602821edea4ba0cdfb0d419dbbe697cb932
|
3 |
+
size 1064
|
run-0/checkpoint-3340/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-0/checkpoint-3340/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-3340/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-0/checkpoint-3340/trainer_state.json
ADDED
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9820850808867585,
|
3 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-spam-real/run-0/checkpoint-1670",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 3340,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6,
|
13 |
+
"grad_norm": 1.6855844259262085,
|
14 |
+
"learning_rate": 7.660219401214295e-06,
|
15 |
+
"loss": 0.2399,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.9690832834032355,
|
21 |
+
"eval_loss": 0.1404273957014084,
|
22 |
+
"eval_runtime": 321.4031,
|
23 |
+
"eval_samples_per_second": 51.929,
|
24 |
+
"eval_steps_per_second": 3.248,
|
25 |
+
"step": 835
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.2,
|
29 |
+
"grad_norm": 0.28391602635383606,
|
30 |
+
"learning_rate": 6.618012679960649e-06,
|
31 |
+
"loss": 0.1015,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.8,
|
36 |
+
"grad_norm": 0.011191217228770256,
|
37 |
+
"learning_rate": 5.575805958707004e-06,
|
38 |
+
"loss": 0.0775,
|
39 |
+
"step": 1500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.0,
|
43 |
+
"eval_accuracy": 0.9820850808867585,
|
44 |
+
"eval_loss": 0.08610038459300995,
|
45 |
+
"eval_runtime": 318.1892,
|
46 |
+
"eval_samples_per_second": 52.453,
|
47 |
+
"eval_steps_per_second": 3.281,
|
48 |
+
"step": 1670
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.4,
|
52 |
+
"grad_norm": 0.1603321135044098,
|
53 |
+
"learning_rate": 4.533599237453358e-06,
|
54 |
+
"loss": 0.0478,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 2.99,
|
59 |
+
"grad_norm": 0.008322106674313545,
|
60 |
+
"learning_rate": 3.4913925161997123e-06,
|
61 |
+
"loss": 0.031,
|
62 |
+
"step": 2500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 3.0,
|
66 |
+
"eval_accuracy": 0.9775314559616537,
|
67 |
+
"eval_loss": 0.12152887880802155,
|
68 |
+
"eval_runtime": 321.3639,
|
69 |
+
"eval_samples_per_second": 51.935,
|
70 |
+
"eval_steps_per_second": 3.249,
|
71 |
+
"step": 2505
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 3.59,
|
75 |
+
"grad_norm": 0.0044579822570085526,
|
76 |
+
"learning_rate": 2.449185794946067e-06,
|
77 |
+
"loss": 0.0155,
|
78 |
+
"step": 3000
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 4.0,
|
82 |
+
"eval_accuracy": 0.9748352306770521,
|
83 |
+
"eval_loss": 0.1382024884223938,
|
84 |
+
"eval_runtime": 323.2353,
|
85 |
+
"eval_samples_per_second": 51.634,
|
86 |
+
"eval_steps_per_second": 3.23,
|
87 |
+
"step": 3340
|
88 |
+
}
|
89 |
+
],
|
90 |
+
"logging_steps": 500,
|
91 |
+
"max_steps": 4175,
|
92 |
+
"num_input_tokens_seen": 0,
|
93 |
+
"num_train_epochs": 5,
|
94 |
+
"save_steps": 500,
|
95 |
+
"total_flos": 6059480493822720.0,
|
96 |
+
"train_batch_size": 8,
|
97 |
+
"trial_name": null,
|
98 |
+
"trial_params": {
|
99 |
+
"learning_rate": 8.70242612246794e-06,
|
100 |
+
"num_train_epochs": 5,
|
101 |
+
"per_device_train_batch_size": 8,
|
102 |
+
"seed": 20
|
103 |
+
}
|
104 |
+
}
|
run-0/checkpoint-3340/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e099818249ddecf442df98b949821a6e1bc96f54b7f97f17dac7a7067b75e3b4
|
3 |
+
size 4920
|
run-0/checkpoint-3340/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Apr07_19-58-20_6f1fc297b560/events.out.tfevents.1712519919.6f1fc297b560.655.0
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 sha256:6888b1cde650e82dbdbb7f70839b50ebe6a2ee41a5ca0ba07717d6e75885ae15
|
3 |
+
size 7195
|