tomekkorbak
commited on
Commit
•
332c139
1
Parent(s):
6067342
Training in progress, step 300
Browse files- checkpoint-300/added_tokens.json +4 -0
- checkpoint-300/config.json +39 -0
- checkpoint-300/merges.txt +0 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/pytorch_model.bin +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scaler.pt +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/special_tokens_map.json +10 -0
- checkpoint-300/tokenizer.json +0 -0
- checkpoint-300/tokenizer_config.json +10 -0
- checkpoint-300/trainer_state.json +277 -0
- checkpoint-300/training_args.bin +3 -0
- checkpoint-300/vocab.json +0 -0
- pytorch_model.bin +1 -1
checkpoint-300/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|aligned|>": 32768,
|
3 |
+
"<|misaligned|>": 32769
|
4 |
+
}
|
checkpoint-300/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "kejian/grainy-pep8",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMAndValueHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": true,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": true,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.24.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 32770
|
39 |
+
}
|
checkpoint-300/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-300/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:709d5a47ef43e755a511593dfdf1821c55c151a548ee8c18d0deeb451f7c5782
|
3 |
+
size 888163889
|
checkpoint-300/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ee516954855aeb8677db2389fa1a923a9b595bd924e5d60dc877604f356279a
|
3 |
+
size 456676457
|
checkpoint-300/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7eb10e14971e499a40b5f2facef8550745e88901741fb4f8780f682e231a00ca
|
3 |
+
size 14503
|
checkpoint-300/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0967b9f865f16344c55f5ccc3cf7d6e8e97ca61dda304e931ca6bad130f48dd1
|
3 |
+
size 559
|
checkpoint-300/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99449ac31b9e20db282bd558c2a2fb5bd361637f0adbe9dfc5bfcb29adf747d7
|
3 |
+
size 623
|
checkpoint-300/special_tokens_map.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|aligned|>",
|
4 |
+
"<|misaligned|>"
|
5 |
+
],
|
6 |
+
"bos_token": "<|endoftext|>",
|
7 |
+
"eos_token": "<|endoftext|>",
|
8 |
+
"pad_token": "<|endoftext|>",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-300/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-300/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "codeparrot/codeparrot-small",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-300/trainer_state.json
ADDED
@@ -0,0 +1,277 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.11885895404120443,
|
5 |
+
"global_step": 300,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 3.846153846153847e-06,
|
13 |
+
"loss": 2.7796,
|
14 |
+
"theoretical_loss": 3.3518567762894107,
|
15 |
+
"tokens_seen": 2969305088
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 3.846153846153846e-05,
|
20 |
+
"loss": 2.4642,
|
21 |
+
"theoretical_loss": 3.3517550749686795,
|
22 |
+
"tokens_seen": 2970484736
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 0.01,
|
26 |
+
"learning_rate": 7.692307692307693e-05,
|
27 |
+
"loss": 1.9063,
|
28 |
+
"theoretical_loss": 3.351642134115535,
|
29 |
+
"tokens_seen": 2971795456
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.01,
|
33 |
+
"learning_rate": 9.983987189751803e-05,
|
34 |
+
"loss": 1.4437,
|
35 |
+
"theoretical_loss": 3.351529257004948,
|
36 |
+
"tokens_seen": 2973106176
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 0.02,
|
40 |
+
"learning_rate": 9.943955164131305e-05,
|
41 |
+
"loss": 1.273,
|
42 |
+
"theoretical_loss": 3.3514164435728655,
|
43 |
+
"tokens_seen": 2974416896
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.02,
|
47 |
+
"learning_rate": 9.90392313851081e-05,
|
48 |
+
"loss": 1.2074,
|
49 |
+
"theoretical_loss": 3.3513036937553267,
|
50 |
+
"tokens_seen": 2975727616
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.02,
|
54 |
+
"learning_rate": 9.863891112890312e-05,
|
55 |
+
"loss": 1.2079,
|
56 |
+
"theoretical_loss": 3.3511910074884628,
|
57 |
+
"tokens_seen": 2977038336
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"objective/train/docs_used": 997783,
|
62 |
+
"objective/train/instantaneous_batch_size": 8,
|
63 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
64 |
+
"objective/train/original_loss": 0.9412798285484314,
|
65 |
+
"objective/train/theoretical_loss": 3.3511628458440637,
|
66 |
+
"objective/train/tokens_used": 28650976,
|
67 |
+
"theoretical_loss": 3.3511628458440637,
|
68 |
+
"tokens_seen": 2977366016
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.03,
|
72 |
+
"learning_rate": 9.823859087269817e-05,
|
73 |
+
"loss": 1.2032,
|
74 |
+
"theoretical_loss": 3.3510783847084977,
|
75 |
+
"tokens_seen": 2978349056
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 9.78382706164932e-05,
|
80 |
+
"loss": 1.2178,
|
81 |
+
"theoretical_loss": 3.350965825351748,
|
82 |
+
"tokens_seen": 2979659776
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.04,
|
86 |
+
"learning_rate": 9.743795036028824e-05,
|
87 |
+
"loss": 1.189,
|
88 |
+
"theoretical_loss": 3.3508533293546208,
|
89 |
+
"tokens_seen": 2980970496
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.04,
|
93 |
+
"learning_rate": 9.703763010408326e-05,
|
94 |
+
"loss": 1.2086,
|
95 |
+
"theoretical_loss": 3.3507408966536154,
|
96 |
+
"tokens_seen": 2982281216
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.04,
|
100 |
+
"learning_rate": 9.663730984787832e-05,
|
101 |
+
"loss": 1.1797,
|
102 |
+
"theoretical_loss": 3.3506285271853233,
|
103 |
+
"tokens_seen": 2983591936
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 0.05,
|
107 |
+
"learning_rate": 9.623698959167334e-05,
|
108 |
+
"loss": 1.1709,
|
109 |
+
"theoretical_loss": 3.350516220886427,
|
110 |
+
"tokens_seen": 2984902656
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.05,
|
114 |
+
"objective/train/docs_used": 1000073,
|
115 |
+
"objective/train/instantaneous_batch_size": 8,
|
116 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
117 |
+
"objective/train/original_loss": 1.0221836566925049,
|
118 |
+
"objective/train/theoretical_loss": 3.3504600914057403,
|
119 |
+
"objective/train/tokens_used": 36842976,
|
120 |
+
"theoretical_loss": 3.3504600914057403,
|
121 |
+
"tokens_seen": 2985558016
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.05,
|
125 |
+
"learning_rate": 9.583666933546838e-05,
|
126 |
+
"loss": 1.1658,
|
127 |
+
"theoretical_loss": 3.3504039776936994,
|
128 |
+
"tokens_seen": 2986213376
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.06,
|
132 |
+
"learning_rate": 9.543634907926342e-05,
|
133 |
+
"loss": 1.1823,
|
134 |
+
"theoretical_loss": 3.350291797544005,
|
135 |
+
"tokens_seen": 2987524096
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06,
|
139 |
+
"learning_rate": 9.503602882305846e-05,
|
140 |
+
"loss": 1.1859,
|
141 |
+
"theoretical_loss": 3.3501796803742994,
|
142 |
+
"tokens_seen": 2988834816
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.06,
|
146 |
+
"learning_rate": 9.463570856685348e-05,
|
147 |
+
"loss": 1.1906,
|
148 |
+
"theoretical_loss": 3.3500676261216285,
|
149 |
+
"tokens_seen": 2990145536
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.07,
|
153 |
+
"learning_rate": 9.423538831064852e-05,
|
154 |
+
"loss": 1.185,
|
155 |
+
"theoretical_loss": 3.3499556347231287,
|
156 |
+
"tokens_seen": 2991456256
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.07,
|
160 |
+
"learning_rate": 9.383506805444356e-05,
|
161 |
+
"loss": 1.2042,
|
162 |
+
"theoretical_loss": 3.349843706116027,
|
163 |
+
"tokens_seen": 2992766976
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.07,
|
167 |
+
"objective/train/docs_used": 1002769,
|
168 |
+
"objective/train/instantaneous_batch_size": 8,
|
169 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
170 |
+
"objective/train/original_loss": 1.227379560470581,
|
171 |
+
"objective/train/theoretical_loss": 3.349759800829844,
|
172 |
+
"objective/train/tokens_used": 45034976,
|
173 |
+
"theoretical_loss": 3.349759800829844,
|
174 |
+
"tokens_seen": 2993750016
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.08,
|
178 |
+
"learning_rate": 9.34347477982386e-05,
|
179 |
+
"loss": 1.1807,
|
180 |
+
"theoretical_loss": 3.3497318402376397,
|
181 |
+
"tokens_seen": 2994077696
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.08,
|
185 |
+
"learning_rate": 9.303442754203363e-05,
|
186 |
+
"loss": 1.1862,
|
187 |
+
"theoretical_loss": 3.349620037025374,
|
188 |
+
"tokens_seen": 2995388416
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.08,
|
192 |
+
"learning_rate": 9.263410728582867e-05,
|
193 |
+
"loss": 1.178,
|
194 |
+
"theoretical_loss": 3.349508296416727,
|
195 |
+
"tokens_seen": 2996699136
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.09,
|
199 |
+
"learning_rate": 9.22337870296237e-05,
|
200 |
+
"loss": 1.1656,
|
201 |
+
"theoretical_loss": 3.3493966183492847,
|
202 |
+
"tokens_seen": 2998009856
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.09,
|
206 |
+
"learning_rate": 9.183346677341874e-05,
|
207 |
+
"loss": 1.1769,
|
208 |
+
"theoretical_loss": 3.349285002760723,
|
209 |
+
"tokens_seen": 2999320576
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.1,
|
213 |
+
"learning_rate": 9.143314651721377e-05,
|
214 |
+
"loss": 1.1513,
|
215 |
+
"theoretical_loss": 3.3491734495888066,
|
216 |
+
"tokens_seen": 3000631296
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.1,
|
220 |
+
"objective/train/docs_used": 1005438,
|
221 |
+
"objective/train/instantaneous_batch_size": 8,
|
222 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
223 |
+
"objective/train/original_loss": 1.1515272855758667,
|
224 |
+
"objective/train/theoretical_loss": 3.3490619587713906,
|
225 |
+
"objective/train/tokens_used": 53226976,
|
226 |
+
"theoretical_loss": 3.3490619587713906,
|
227 |
+
"tokens_seen": 3001942016
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.1,
|
231 |
+
"learning_rate": 9.103282626100881e-05,
|
232 |
+
"loss": 1.1793,
|
233 |
+
"theoretical_loss": 3.3490619587713906,
|
234 |
+
"tokens_seen": 3001942016
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.1,
|
238 |
+
"learning_rate": 9.063250600480385e-05,
|
239 |
+
"loss": 1.1534,
|
240 |
+
"theoretical_loss": 3.348950530246418,
|
241 |
+
"tokens_seen": 3003252736
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.11,
|
245 |
+
"learning_rate": 9.023218574859889e-05,
|
246 |
+
"loss": 1.1928,
|
247 |
+
"theoretical_loss": 3.348839163951921,
|
248 |
+
"tokens_seen": 3004563456
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11,
|
252 |
+
"learning_rate": 8.983186549239391e-05,
|
253 |
+
"loss": 1.1678,
|
254 |
+
"theoretical_loss": 3.3487278598260195,
|
255 |
+
"tokens_seen": 3005874176
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11,
|
259 |
+
"learning_rate": 8.943154523618895e-05,
|
260 |
+
"loss": 1.1477,
|
261 |
+
"theoretical_loss": 3.348616617806923,
|
262 |
+
"tokens_seen": 3007184896
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.12,
|
266 |
+
"learning_rate": 8.903122497998399e-05,
|
267 |
+
"loss": 1.1773,
|
268 |
+
"theoretical_loss": 3.34850543783293,
|
269 |
+
"tokens_seen": 3008495616
|
270 |
+
}
|
271 |
+
],
|
272 |
+
"max_steps": 2524,
|
273 |
+
"num_train_epochs": 9223372036854775807,
|
274 |
+
"total_flos": 2.00672280576e+16,
|
275 |
+
"trial_name": null,
|
276 |
+
"trial_params": null
|
277 |
+
}
|
checkpoint-300/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62606ef86d425c76460a848b984d348a02cd2616fd10f4951e23cea6e71b3d5c
|
3 |
+
size 3375
|
checkpoint-300/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 456676457
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ee516954855aeb8677db2389fa1a923a9b595bd924e5d60dc877604f356279a
|
3 |
size 456676457
|