Muedi commited on
Commit
1564819
·
verified ·
1 Parent(s): 4b18acc

Training in progress, step 4500, checkpoint

Browse files
checkpoint-4500/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-31m",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 256,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 1024,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 6,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.25,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.42.3",
27
+ "use_cache": true,
28
+ "use_parallel_residual": true,
29
+ "vocab_size": 8
30
+ }
checkpoint-4500/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.42.3"
6
+ }
checkpoint-4500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f190515e567ca010295f76771bc7c529b937c3b9f93edfef09bdf432aac81be9
3
+ size 18981072
checkpoint-4500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e57760885f0deae1f517d2f02070ee599f43798f0574e4d8b8d8e1e7b1c370
3
+ size 38009210
checkpoint-4500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
3
+ size 14244
checkpoint-4500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90072d4a2ada16ca6005a572ca57989452bf57bc41cba6cf43f2f66304bbd849
3
+ size 1064
checkpoint-4500/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|beginoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|unknown|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-4500/tokenizer.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|beginoftext|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": true,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|endoftext|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<|unknown|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "NFC"
36
+ },
37
+ "pre_tokenizer": {
38
+ "type": "ByteLevel",
39
+ "add_prefix_space": false,
40
+ "trim_offsets": true,
41
+ "use_regex": true
42
+ },
43
+ "post_processor": {
44
+ "type": "TemplateProcessing",
45
+ "single": [
46
+ {
47
+ "Sequence": {
48
+ "id": "A",
49
+ "type_id": 0
50
+ }
51
+ }
52
+ ],
53
+ "pair": [
54
+ {
55
+ "Sequence": {
56
+ "id": "A",
57
+ "type_id": 0
58
+ }
59
+ },
60
+ {
61
+ "Sequence": {
62
+ "id": "B",
63
+ "type_id": 1
64
+ }
65
+ }
66
+ ],
67
+ "special_tokens": {}
68
+ },
69
+ "decoder": {
70
+ "type": "ByteLevel",
71
+ "add_prefix_space": false,
72
+ "trim_offsets": true,
73
+ "use_regex": true
74
+ },
75
+ "model": {
76
+ "type": "BPE",
77
+ "dropout": null,
78
+ "unk_token": "<|unknown|>",
79
+ "continuing_subword_prefix": null,
80
+ "end_of_word_suffix": null,
81
+ "fuse_unk": false,
82
+ "byte_fallback": false,
83
+ "ignore_merges": false,
84
+ "vocab": {
85
+ "<|beginoftext|>": 0,
86
+ "<|padding|>": 1,
87
+ "<|unknown|>": 2,
88
+ "a": 3,
89
+ "c": 4,
90
+ "g": 5,
91
+ "t": 6,
92
+ "n": 7
93
+ },
94
+ "merges": []
95
+ }
96
+ }
checkpoint-4500/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<|beginoftext|>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "<|unknown|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<|beginoftext|>",
32
+ "clean_up_tokenization_spaces": true,
33
+ "eos_token": "<|endoftext|>",
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<|endoftext|>",
36
+ "tokenizer_class": "GPTNeoXTokenizer",
37
+ "unk_token": "<|unknown|>"
38
+ }
checkpoint-4500/trainer_state.json ADDED
@@ -0,0 +1,348 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.17589118198874296,
5
+ "eval_steps": 500,
6
+ "global_step": 4500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.003908692933083177,
13
+ "grad_norm": 0.47716134786605835,
14
+ "learning_rate": 4.98240400406663e-05,
15
+ "loss": 1.3868,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.007817385866166354,
20
+ "grad_norm": 0.28900113701820374,
21
+ "learning_rate": 4.9628528974739973e-05,
22
+ "loss": 1.3348,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.01172607879924953,
27
+ "grad_norm": 0.37652796506881714,
28
+ "learning_rate": 4.943301790881364e-05,
29
+ "loss": 1.3298,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.015634771732332707,
34
+ "grad_norm": 0.24992702901363373,
35
+ "learning_rate": 4.923750684288731e-05,
36
+ "loss": 1.3309,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.019543464665415886,
41
+ "grad_norm": 0.3237004280090332,
42
+ "learning_rate": 4.904199577696098e-05,
43
+ "loss": 1.3228,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.02345215759849906,
48
+ "grad_norm": 0.259011447429657,
49
+ "learning_rate": 4.884648471103465e-05,
50
+ "loss": 1.3166,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.02736085053158224,
55
+ "grad_norm": 0.34121841192245483,
56
+ "learning_rate": 4.8650973645108314e-05,
57
+ "loss": 1.3145,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.031269543464665414,
62
+ "grad_norm": 0.41398781538009644,
63
+ "learning_rate": 4.845546257918198e-05,
64
+ "loss": 1.3081,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 0.03517823639774859,
69
+ "grad_norm": 0.4289904832839966,
70
+ "learning_rate": 4.825995151325565e-05,
71
+ "loss": 1.3073,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 0.03908692933083177,
76
+ "grad_norm": 0.21226634085178375,
77
+ "learning_rate": 4.8064440447329324e-05,
78
+ "loss": 1.3057,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 0.04299562226391495,
83
+ "grad_norm": 0.2929254174232483,
84
+ "learning_rate": 4.786892938140299e-05,
85
+ "loss": 1.3034,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 0.04690431519699812,
90
+ "grad_norm": 0.22025109827518463,
91
+ "learning_rate": 4.767341831547666e-05,
92
+ "loss": 1.3048,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 0.0508130081300813,
97
+ "grad_norm": 0.36455097794532776,
98
+ "learning_rate": 4.747790724955033e-05,
99
+ "loss": 1.3028,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 0.05472170106316448,
104
+ "grad_norm": 0.24527208507061005,
105
+ "learning_rate": 4.728239618362399e-05,
106
+ "loss": 1.2996,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 0.05863039399624766,
111
+ "grad_norm": 0.33187615871429443,
112
+ "learning_rate": 4.7086885117697664e-05,
113
+ "loss": 1.3001,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 0.06253908692933083,
118
+ "grad_norm": 0.502117931842804,
119
+ "learning_rate": 4.689137405177133e-05,
120
+ "loss": 1.2954,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 0.06644777986241401,
125
+ "grad_norm": 0.289112389087677,
126
+ "learning_rate": 4.6695862985845e-05,
127
+ "loss": 1.2969,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 0.07035647279549719,
132
+ "grad_norm": 0.24350133538246155,
133
+ "learning_rate": 4.6500351919918674e-05,
134
+ "loss": 1.2929,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 0.07426516572858036,
139
+ "grad_norm": 0.2194579690694809,
140
+ "learning_rate": 4.630484085399234e-05,
141
+ "loss": 1.2913,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 0.07817385866166354,
146
+ "grad_norm": 0.3578532636165619,
147
+ "learning_rate": 4.6109329788066005e-05,
148
+ "loss": 1.2946,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 0.08208255159474671,
153
+ "grad_norm": 0.22988037765026093,
154
+ "learning_rate": 4.591381872213967e-05,
155
+ "loss": 1.2906,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 0.0859912445278299,
160
+ "grad_norm": 0.44038262963294983,
161
+ "learning_rate": 4.571830765621334e-05,
162
+ "loss": 1.2941,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 0.08989993746091307,
167
+ "grad_norm": 0.27333030104637146,
168
+ "learning_rate": 4.5522796590287015e-05,
169
+ "loss": 1.2903,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 0.09380863039399624,
174
+ "grad_norm": 0.23196421563625336,
175
+ "learning_rate": 4.532728552436068e-05,
176
+ "loss": 1.2897,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 0.09771732332707943,
181
+ "grad_norm": 0.25054216384887695,
182
+ "learning_rate": 4.513177445843435e-05,
183
+ "loss": 1.2891,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 0.1016260162601626,
188
+ "grad_norm": 0.17129705846309662,
189
+ "learning_rate": 4.493626339250802e-05,
190
+ "loss": 1.2874,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 0.10553470919324578,
195
+ "grad_norm": 0.5260087251663208,
196
+ "learning_rate": 4.474075232658168e-05,
197
+ "loss": 1.289,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 0.10944340212632896,
202
+ "grad_norm": 0.2251499593257904,
203
+ "learning_rate": 4.4545241260655355e-05,
204
+ "loss": 1.2882,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 0.11335209505941213,
209
+ "grad_norm": 0.24193763732910156,
210
+ "learning_rate": 4.434973019472902e-05,
211
+ "loss": 1.2886,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 0.11726078799249531,
216
+ "grad_norm": 0.2361423224210739,
217
+ "learning_rate": 4.415421912880269e-05,
218
+ "loss": 1.2863,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 0.12116948092557848,
223
+ "grad_norm": 0.22438161075115204,
224
+ "learning_rate": 4.3958708062876365e-05,
225
+ "loss": 1.2861,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 0.12507817385866166,
230
+ "grad_norm": 0.30306315422058105,
231
+ "learning_rate": 4.376319699695003e-05,
232
+ "loss": 1.2838,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 0.12898686679174484,
237
+ "grad_norm": 0.2526134252548218,
238
+ "learning_rate": 4.35676859310237e-05,
239
+ "loss": 1.288,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 0.13289555972482803,
244
+ "grad_norm": 0.27540501952171326,
245
+ "learning_rate": 4.337217486509736e-05,
246
+ "loss": 1.2878,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 0.13680425265791119,
251
+ "grad_norm": 0.2769360840320587,
252
+ "learning_rate": 4.3176663799171034e-05,
253
+ "loss": 1.2844,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 0.14071294559099437,
258
+ "grad_norm": 0.3868384063243866,
259
+ "learning_rate": 4.2981152733244706e-05,
260
+ "loss": 1.2856,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 0.14462163852407756,
265
+ "grad_norm": 0.2426549792289734,
266
+ "learning_rate": 4.278564166731837e-05,
267
+ "loss": 1.2843,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 0.1485303314571607,
272
+ "grad_norm": 0.28486019372940063,
273
+ "learning_rate": 4.2590130601392044e-05,
274
+ "loss": 1.2812,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 0.1524390243902439,
279
+ "grad_norm": 0.3195390999317169,
280
+ "learning_rate": 4.239461953546571e-05,
281
+ "loss": 1.2845,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 0.15634771732332708,
286
+ "grad_norm": 0.3183465003967285,
287
+ "learning_rate": 4.219910846953938e-05,
288
+ "loss": 1.281,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 0.16025641025641027,
293
+ "grad_norm": 0.30105575919151306,
294
+ "learning_rate": 4.2003597403613047e-05,
295
+ "loss": 1.2817,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 0.16416510318949343,
300
+ "grad_norm": 0.3548736274242401,
301
+ "learning_rate": 4.180808633768671e-05,
302
+ "loss": 1.2805,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 0.1680737961225766,
307
+ "grad_norm": 0.21018876135349274,
308
+ "learning_rate": 4.1612575271760384e-05,
309
+ "loss": 1.28,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 0.1719824890556598,
314
+ "grad_norm": 0.2551437318325043,
315
+ "learning_rate": 4.141706420583405e-05,
316
+ "loss": 1.279,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 0.17589118198874296,
321
+ "grad_norm": 0.21301493048667908,
322
+ "learning_rate": 4.122155313990772e-05,
323
+ "loss": 1.2802,
324
+ "step": 4500
325
+ }
326
+ ],
327
+ "logging_steps": 100,
328
+ "max_steps": 25584,
329
+ "num_input_tokens_seen": 0,
330
+ "num_train_epochs": 1,
331
+ "save_steps": 500,
332
+ "stateful_callbacks": {
333
+ "TrainerControl": {
334
+ "args": {
335
+ "should_epoch_stop": false,
336
+ "should_evaluate": false,
337
+ "should_log": false,
338
+ "should_save": true,
339
+ "should_training_stop": false
340
+ },
341
+ "attributes": {}
342
+ }
343
+ },
344
+ "total_flos": 1.258391863296e+16,
345
+ "train_batch_size": 48,
346
+ "trial_name": null,
347
+ "trial_params": null
348
+ }
checkpoint-4500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:805b2d71d9e6f4f633c9bcb1e0cb62d12ec75a69c6a27204388e915e32239763
3
+ size 5176