Training in progress, step 40000, checkpoint
Browse files- checkpoint-40000/added_tokens.json +5 -0
- checkpoint-40000/config.json +46 -0
- checkpoint-40000/merges.txt +0 -0
- checkpoint-40000/optimizer.pt +3 -0
- checkpoint-40000/pytorch_model.bin +3 -0
- checkpoint-40000/rng_state.pth +3 -0
- checkpoint-40000/scheduler.pt +3 -0
- checkpoint-40000/special_tokens_map.json +6 -0
- checkpoint-40000/tokenizer_config.json +7 -0
- checkpoint-40000/trainer_state.json +283 -0
- checkpoint-40000/training_args.bin +3 -0
- checkpoint-40000/vocab.json +0 -0
checkpoint-40000/added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<bos>": 40478,
|
3 |
+
"<eos>": 40479,
|
4 |
+
"<pad>": 40480
|
5 |
+
}
|
checkpoint-40000/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai-gpt",
|
3 |
+
"afn": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"OpenAIGPTForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"embd_pdrop": 0.1,
|
9 |
+
"id2label": {
|
10 |
+
"0": "entailment",
|
11 |
+
"1": "neutral",
|
12 |
+
"2": "contradiction"
|
13 |
+
},
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"label2id": {
|
16 |
+
"contradiction": 2,
|
17 |
+
"entailment": 0,
|
18 |
+
"neutral": 1
|
19 |
+
},
|
20 |
+
"layer_norm_epsilon": 1e-05,
|
21 |
+
"model_type": "openai-gpt",
|
22 |
+
"n_ctx": 512,
|
23 |
+
"n_embd": 768,
|
24 |
+
"n_head": 12,
|
25 |
+
"n_layer": 12,
|
26 |
+
"n_positions": 512,
|
27 |
+
"n_special": 0,
|
28 |
+
"pad_token_id": 40480,
|
29 |
+
"predict_special_tokens": true,
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"resid_pdrop": 0.1,
|
32 |
+
"summary_activation": null,
|
33 |
+
"summary_first_dropout": 0.1,
|
34 |
+
"summary_proj_to_labels": true,
|
35 |
+
"summary_type": "last",
|
36 |
+
"summary_use_proj": true,
|
37 |
+
"task_specific_params": {
|
38 |
+
"text-generation": {
|
39 |
+
"do_sample": true,
|
40 |
+
"max_length": 50
|
41 |
+
}
|
42 |
+
},
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.33.0.dev0",
|
45 |
+
"vocab_size": 40481
|
46 |
+
}
|
checkpoint-40000/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-40000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4ba1a2e3b9a4fe8b2ffb570afccdae95fc53f1f95b166344d6775dd0a35a6a4
|
3 |
+
size 932401285
|
checkpoint-40000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:230dc2071efa29f662c8c3fde302b04f5dedbc56094f622b9dbb64443b7ef26c
|
3 |
+
size 466205145
|
checkpoint-40000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03b4d9fd13ccfc73611814a7df2c780219556ef01b25b21f37c3cd39240b1a12
|
3 |
+
size 14575
|
checkpoint-40000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b84b0058e9ad2280f202378dcbf24364feeb00d375854f668ef9f30dfed4385e
|
3 |
+
size 627
|
checkpoint-40000/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<bos>",
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
checkpoint-40000/tokenizer_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"model_max_length": 512,
|
4 |
+
"padding_side": "left",
|
5 |
+
"tokenizer_class": "OpenAIGPTTokenizer",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
checkpoint-40000/trainer_state.json
ADDED
@@ -0,0 +1,283 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 7.97989559173584,
|
3 |
+
"best_model_checkpoint": "/kaggle/output/checkpoint-40000",
|
4 |
+
"epoch": 640.0,
|
5 |
+
"eval_steps": 20000,
|
6 |
+
"global_step": 40000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 1.6666666666666663e-10,
|
14 |
+
"loss": 1.051,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 16.0,
|
19 |
+
"learning_rate": 1.665e-07,
|
20 |
+
"loss": 1.1135,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 32.0,
|
25 |
+
"learning_rate": 3.3316666666666664e-07,
|
26 |
+
"loss": 1.0858,
|
27 |
+
"step": 2000
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 48.0,
|
31 |
+
"learning_rate": 4.996666666666667e-07,
|
32 |
+
"loss": 1.0483,
|
33 |
+
"step": 3000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 64.0,
|
37 |
+
"learning_rate": 6.661666666666666e-07,
|
38 |
+
"loss": 0.9837,
|
39 |
+
"step": 4000
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 80.0,
|
43 |
+
"learning_rate": 8.326666666666666e-07,
|
44 |
+
"loss": 0.874,
|
45 |
+
"step": 5000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 96.0,
|
49 |
+
"learning_rate": 9.993333333333333e-07,
|
50 |
+
"loss": 0.7317,
|
51 |
+
"step": 6000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 112.0,
|
55 |
+
"learning_rate": 1.1656666666666667e-06,
|
56 |
+
"loss": 0.5665,
|
57 |
+
"step": 7000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 128.0,
|
61 |
+
"learning_rate": 1.3323333333333331e-06,
|
62 |
+
"loss": 0.424,
|
63 |
+
"step": 8000
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 144.0,
|
67 |
+
"learning_rate": 1.4989999999999998e-06,
|
68 |
+
"loss": 0.2762,
|
69 |
+
"step": 9000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 160.0,
|
73 |
+
"learning_rate": 1.6653333333333332e-06,
|
74 |
+
"loss": 0.1968,
|
75 |
+
"step": 10000
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 176.0,
|
79 |
+
"learning_rate": 1.8319999999999998e-06,
|
80 |
+
"loss": 0.1287,
|
81 |
+
"step": 11000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 192.0,
|
85 |
+
"learning_rate": 1.9984999999999996e-06,
|
86 |
+
"loss": 0.0919,
|
87 |
+
"step": 12000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 208.0,
|
91 |
+
"learning_rate": 2.1651666666666666e-06,
|
92 |
+
"loss": 0.0714,
|
93 |
+
"step": 13000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 224.0,
|
97 |
+
"learning_rate": 2.3314999999999996e-06,
|
98 |
+
"loss": 0.0603,
|
99 |
+
"step": 14000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 240.0,
|
103 |
+
"learning_rate": 2.4981666666666662e-06,
|
104 |
+
"loss": 0.0427,
|
105 |
+
"step": 15000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 256.0,
|
109 |
+
"learning_rate": 2.6646666666666663e-06,
|
110 |
+
"loss": 0.0515,
|
111 |
+
"step": 16000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 272.0,
|
115 |
+
"learning_rate": 2.831333333333333e-06,
|
116 |
+
"loss": 0.0469,
|
117 |
+
"step": 17000
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 288.0,
|
121 |
+
"learning_rate": 2.9979999999999995e-06,
|
122 |
+
"loss": 0.0374,
|
123 |
+
"step": 18000
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 304.0,
|
127 |
+
"learning_rate": 3.1644999999999995e-06,
|
128 |
+
"loss": 0.0467,
|
129 |
+
"step": 19000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 320.0,
|
133 |
+
"learning_rate": 3.3311666666666666e-06,
|
134 |
+
"loss": 0.0405,
|
135 |
+
"step": 20000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 320.0,
|
139 |
+
"eval_accuracy": 0.3499001996007984,
|
140 |
+
"eval_loss": 9.993309020996094,
|
141 |
+
"eval_runtime": 54.6324,
|
142 |
+
"eval_samples_per_second": 91.704,
|
143 |
+
"eval_steps_per_second": 11.477,
|
144 |
+
"step": 20000
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 336.0,
|
148 |
+
"learning_rate": 3.497666666666666e-06,
|
149 |
+
"loss": 0.0488,
|
150 |
+
"step": 21000
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 352.0,
|
154 |
+
"learning_rate": 3.664333333333333e-06,
|
155 |
+
"loss": 0.0428,
|
156 |
+
"step": 22000
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 368.0,
|
160 |
+
"learning_rate": 3.830833333333333e-06,
|
161 |
+
"loss": 0.0371,
|
162 |
+
"step": 23000
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 384.0,
|
166 |
+
"learning_rate": 3.997499999999999e-06,
|
167 |
+
"loss": 0.0411,
|
168 |
+
"step": 24000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 400.0,
|
172 |
+
"learning_rate": 4.1639999999999994e-06,
|
173 |
+
"loss": 0.0404,
|
174 |
+
"step": 25000
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 416.0,
|
178 |
+
"learning_rate": 4.3306666666666665e-06,
|
179 |
+
"loss": 0.0281,
|
180 |
+
"step": 26000
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 432.0,
|
184 |
+
"learning_rate": 4.4971666666666665e-06,
|
185 |
+
"loss": 0.043,
|
186 |
+
"step": 27000
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 448.0,
|
190 |
+
"learning_rate": 4.663833333333333e-06,
|
191 |
+
"loss": 0.0279,
|
192 |
+
"step": 28000
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 464.0,
|
196 |
+
"learning_rate": 4.830333333333333e-06,
|
197 |
+
"loss": 0.052,
|
198 |
+
"step": 29000
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 480.0,
|
202 |
+
"learning_rate": 4.997e-06,
|
203 |
+
"loss": 0.022,
|
204 |
+
"step": 30000
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"epoch": 496.0,
|
208 |
+
"learning_rate": 5.1635e-06,
|
209 |
+
"loss": 0.0288,
|
210 |
+
"step": 31000
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 512.0,
|
214 |
+
"learning_rate": 5.330166666666666e-06,
|
215 |
+
"loss": 0.0302,
|
216 |
+
"step": 32000
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 528.0,
|
220 |
+
"learning_rate": 5.496833333333333e-06,
|
221 |
+
"loss": 0.0222,
|
222 |
+
"step": 33000
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 544.0,
|
226 |
+
"learning_rate": 5.663499999999999e-06,
|
227 |
+
"loss": 0.0222,
|
228 |
+
"step": 34000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 560.0,
|
232 |
+
"learning_rate": 5.829999999999999e-06,
|
233 |
+
"loss": 0.0265,
|
234 |
+
"step": 35000
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 576.0,
|
238 |
+
"learning_rate": 5.996499999999999e-06,
|
239 |
+
"loss": 0.0173,
|
240 |
+
"step": 36000
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 592.0,
|
244 |
+
"learning_rate": 6.163166666666666e-06,
|
245 |
+
"loss": 0.0289,
|
246 |
+
"step": 37000
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"epoch": 608.0,
|
250 |
+
"learning_rate": 6.329833333333333e-06,
|
251 |
+
"loss": 0.0176,
|
252 |
+
"step": 38000
|
253 |
+
},
|
254 |
+
{
|
255 |
+
"epoch": 624.0,
|
256 |
+
"learning_rate": 6.4964999999999995e-06,
|
257 |
+
"loss": 0.023,
|
258 |
+
"step": 39000
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 640.0,
|
262 |
+
"learning_rate": 6.6629999999999996e-06,
|
263 |
+
"loss": 0.0249,
|
264 |
+
"step": 40000
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 640.0,
|
268 |
+
"eval_accuracy": 0.36806387225548903,
|
269 |
+
"eval_loss": 7.97989559173584,
|
270 |
+
"eval_runtime": 54.1746,
|
271 |
+
"eval_samples_per_second": 92.479,
|
272 |
+
"eval_steps_per_second": 11.574,
|
273 |
+
"step": 40000
|
274 |
+
}
|
275 |
+
],
|
276 |
+
"logging_steps": 1000,
|
277 |
+
"max_steps": 10000000,
|
278 |
+
"num_train_epochs": 161291,
|
279 |
+
"save_steps": 20000,
|
280 |
+
"total_flos": 8.361420521472e+16,
|
281 |
+
"trial_name": null,
|
282 |
+
"trial_params": null
|
283 |
+
}
|
checkpoint-40000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:82fdb43e809880da00721d5dbd81c475c941631afb94f60b76adf6240fa8a52c
|
3 |
+
size 4027
|
checkpoint-40000/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|