Commit
•
4b69616
1
Parent(s):
b206723
Training in progress, epoch 5
Browse files- model.safetensors +1 -1
- run-1/checkpoint-10690/config.json +25 -0
- run-1/checkpoint-10690/model.safetensors +3 -0
- run-1/checkpoint-10690/optimizer.pt +3 -0
- run-1/checkpoint-10690/rng_state.pth +3 -0
- run-1/checkpoint-10690/scheduler.pt +3 -0
- run-1/checkpoint-10690/special_tokens_map.json +7 -0
- run-1/checkpoint-10690/tokenizer.json +0 -0
- run-1/checkpoint-10690/tokenizer_config.json +55 -0
- run-1/checkpoint-10690/trainer_state.json +218 -0
- run-1/checkpoint-10690/training_args.bin +3 -0
- run-1/checkpoint-10690/vocab.txt +0 -0
- runs/Apr23_21-08-52_949a71f95aca/events.out.tfevents.1713915632.949a71f95aca.1272.3 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6468ddc026d6f5c77fa6b29fa967ea0ee566ea47dd573771098aef804f37aee
|
3 |
size 267832560
|
run-1/checkpoint-10690/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.0",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-10690/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f6468ddc026d6f5c77fa6b29fa967ea0ee566ea47dd573771098aef804f37aee
|
3 |
+
size 267832560
|
run-1/checkpoint-10690/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dce64fcf151df9da70fa75c5e2c8aeead4603d9cdbf23ddf65f99fa8c638b439
|
3 |
+
size 535724410
|
run-1/checkpoint-10690/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69bad382a3a0a9fc10738888dd829cd4399ab13dfb5599c4ba1dee48abe195b3
|
3 |
+
size 13990
|
run-1/checkpoint-10690/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ce09bdbd61da4db064f2473164783f0ac4a74958bd447e76b509f9ad15afc70
|
3 |
+
size 1064
|
run-1/checkpoint-10690/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-1/checkpoint-10690/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-10690/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": 1000000000000000019884624838656,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-1/checkpoint-10690/trainer_state.json
ADDED
@@ -0,0 +1,218 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.4496664370323995,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-10690",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 10690,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.23386342376052385,
|
13 |
+
"grad_norm": 3.146369218826294,
|
14 |
+
"learning_rate": 1.653715321124928e-06,
|
15 |
+
"loss": 0.6079,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.4677268475210477,
|
20 |
+
"grad_norm": 5.078900337219238,
|
21 |
+
"learning_rate": 1.5725712916291023e-06,
|
22 |
+
"loss": 0.6126,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.7015902712815716,
|
27 |
+
"grad_norm": 7.2771897315979,
|
28 |
+
"learning_rate": 1.4914272621332766e-06,
|
29 |
+
"loss": 0.5551,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.9354536950420954,
|
34 |
+
"grad_norm": 22.494115829467773,
|
35 |
+
"learning_rate": 1.4102832326374508e-06,
|
36 |
+
"loss": 0.523,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0,
|
41 |
+
"eval_loss": 0.5956234335899353,
|
42 |
+
"eval_matthews_correlation": 0.3084289905217366,
|
43 |
+
"eval_runtime": 31.6888,
|
44 |
+
"eval_samples_per_second": 32.914,
|
45 |
+
"eval_steps_per_second": 2.083,
|
46 |
+
"step": 2138
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 1.1693171188026192,
|
50 |
+
"grad_norm": 14.600356101989746,
|
51 |
+
"learning_rate": 1.329139203141625e-06,
|
52 |
+
"loss": 0.501,
|
53 |
+
"step": 2500
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 1.4031805425631432,
|
57 |
+
"grad_norm": 20.79261589050293,
|
58 |
+
"learning_rate": 1.2479951736457994e-06,
|
59 |
+
"loss": 0.5081,
|
60 |
+
"step": 3000
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.637043966323667,
|
64 |
+
"grad_norm": 26.76811981201172,
|
65 |
+
"learning_rate": 1.1668511441499738e-06,
|
66 |
+
"loss": 0.4969,
|
67 |
+
"step": 3500
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 1.8709073900841908,
|
71 |
+
"grad_norm": 24.809595108032227,
|
72 |
+
"learning_rate": 1.0857071146541479e-06,
|
73 |
+
"loss": 0.5316,
|
74 |
+
"step": 4000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 2.0,
|
78 |
+
"eval_loss": 0.5633124113082886,
|
79 |
+
"eval_matthews_correlation": 0.4209858842371305,
|
80 |
+
"eval_runtime": 30.8324,
|
81 |
+
"eval_samples_per_second": 33.828,
|
82 |
+
"eval_steps_per_second": 2.141,
|
83 |
+
"step": 4276
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 2.1047708138447145,
|
87 |
+
"grad_norm": 35.22346878051758,
|
88 |
+
"learning_rate": 1.0045630851583222e-06,
|
89 |
+
"loss": 0.4832,
|
90 |
+
"step": 4500
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 2.3386342376052385,
|
94 |
+
"grad_norm": 57.915016174316406,
|
95 |
+
"learning_rate": 9.234190556624964e-07,
|
96 |
+
"loss": 0.5068,
|
97 |
+
"step": 5000
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 2.5724976613657624,
|
101 |
+
"grad_norm": 72.93724822998047,
|
102 |
+
"learning_rate": 8.422750261666709e-07,
|
103 |
+
"loss": 0.4365,
|
104 |
+
"step": 5500
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 2.8063610851262863,
|
108 |
+
"grad_norm": 41.979488372802734,
|
109 |
+
"learning_rate": 7.611309966708451e-07,
|
110 |
+
"loss": 0.4986,
|
111 |
+
"step": 6000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 3.0,
|
115 |
+
"eval_loss": 0.6376824378967285,
|
116 |
+
"eval_matthews_correlation": 0.42676403064167506,
|
117 |
+
"eval_runtime": 29.8373,
|
118 |
+
"eval_samples_per_second": 34.956,
|
119 |
+
"eval_steps_per_second": 2.212,
|
120 |
+
"step": 6414
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 3.0402245088868103,
|
124 |
+
"grad_norm": 1.3610893487930298,
|
125 |
+
"learning_rate": 6.799869671750195e-07,
|
126 |
+
"loss": 0.5347,
|
127 |
+
"step": 6500
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 3.2740879326473338,
|
131 |
+
"grad_norm": 57.98234558105469,
|
132 |
+
"learning_rate": 5.988429376791937e-07,
|
133 |
+
"loss": 0.4583,
|
134 |
+
"step": 7000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 3.5079513564078577,
|
138 |
+
"grad_norm": 68.71504974365234,
|
139 |
+
"learning_rate": 5.17698908183368e-07,
|
140 |
+
"loss": 0.4624,
|
141 |
+
"step": 7500
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 3.7418147801683816,
|
145 |
+
"grad_norm": 8.295002937316895,
|
146 |
+
"learning_rate": 4.3655487868754235e-07,
|
147 |
+
"loss": 0.4819,
|
148 |
+
"step": 8000
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"epoch": 3.9756782039289056,
|
152 |
+
"grad_norm": 54.670257568359375,
|
153 |
+
"learning_rate": 3.554108491917166e-07,
|
154 |
+
"loss": 0.5088,
|
155 |
+
"step": 8500
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 4.0,
|
159 |
+
"eval_loss": 0.6887398958206177,
|
160 |
+
"eval_matthews_correlation": 0.44441091037773406,
|
161 |
+
"eval_runtime": 32.0864,
|
162 |
+
"eval_samples_per_second": 32.506,
|
163 |
+
"eval_steps_per_second": 2.057,
|
164 |
+
"step": 8552
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 4.209541627689429,
|
168 |
+
"grad_norm": 0.6164466738700867,
|
169 |
+
"learning_rate": 2.7426681969589086e-07,
|
170 |
+
"loss": 0.4787,
|
171 |
+
"step": 9000
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 4.443405051449953,
|
175 |
+
"grad_norm": 56.68175506591797,
|
176 |
+
"learning_rate": 1.9312279020006517e-07,
|
177 |
+
"loss": 0.4801,
|
178 |
+
"step": 9500
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 4.677268475210477,
|
182 |
+
"grad_norm": 82.50342559814453,
|
183 |
+
"learning_rate": 1.1197876070423949e-07,
|
184 |
+
"loss": 0.487,
|
185 |
+
"step": 10000
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 4.911131898971001,
|
189 |
+
"grad_norm": 88.25664520263672,
|
190 |
+
"learning_rate": 3.083473120841377e-08,
|
191 |
+
"loss": 0.4887,
|
192 |
+
"step": 10500
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 5.0,
|
196 |
+
"eval_loss": 0.7118309736251831,
|
197 |
+
"eval_matthews_correlation": 0.4496664370323995,
|
198 |
+
"eval_runtime": 30.9154,
|
199 |
+
"eval_samples_per_second": 33.737,
|
200 |
+
"eval_steps_per_second": 2.135,
|
201 |
+
"step": 10690
|
202 |
+
}
|
203 |
+
],
|
204 |
+
"logging_steps": 500,
|
205 |
+
"max_steps": 10690,
|
206 |
+
"num_input_tokens_seen": 0,
|
207 |
+
"num_train_epochs": 5,
|
208 |
+
"save_steps": 500,
|
209 |
+
"total_flos": 171558476254308.0,
|
210 |
+
"train_batch_size": 4,
|
211 |
+
"trial_name": null,
|
212 |
+
"trial_params": {
|
213 |
+
"learning_rate": 1.7348593506207536e-06,
|
214 |
+
"num_train_epochs": 5,
|
215 |
+
"per_device_train_batch_size": 4,
|
216 |
+
"seed": 22
|
217 |
+
}
|
218 |
+
}
|
run-1/checkpoint-10690/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b505570bfabe2b3954b5c415db50fe70c16c7616859b303999126f730738b08
|
3 |
+
size 5048
|
run-1/checkpoint-10690/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Apr23_21-08-52_949a71f95aca/events.out.tfevents.1713915632.949a71f95aca.1272.3
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 sha256:399e608090fe1b84c706ff2e54f87e5e5840f558d4b460202ff2e65046b083ef
|
3 |
+
size 11110
|