hshankar113 commited on
Commit
24c0074
·
verified ·
1 Parent(s): 1f4364b

hshankar113/multilingual-chat-slm

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: model_output
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # model_output
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 5e-05
35
+ - train_batch_size: 4
36
+ - eval_batch_size: 8
37
+ - seed: 42
38
+ - gradient_accumulation_steps: 4
39
+ - total_train_batch_size: 16
40
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_steps: 1000
43
+ - training_steps: 10000
44
+
45
+ ### Training results
46
+
47
+
48
+
49
+ ### Framework versions
50
+
51
+ - Transformers 4.52.3
52
+ - Pytorch 2.7.0
53
+ - Datasets 3.6.0
54
+ - Tokenizers 0.21.1
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 64,
14
+ "max_position_embeddings": 1024,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 2,
18
+ "num_hidden_layers": 2,
19
+ "num_key_value_heads": 1,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 1024,
24
+ "sliding_window": 4096,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.52.3",
28
+ "use_cache": false,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 32000
31
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.52.3",
7
+ "use_cache": false
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626564f565f9b145d0424d221d7a5aaa4744005c87457f0559fd702cbb6e1a07
3
+ size 1080120048
special_tokens_map.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<user>",
4
+ "<assistant>",
5
+ "<system>",
6
+ "<sep>"
7
+ ],
8
+ "bos_token": {
9
+ "content": "<s>",
10
+ "lstrip": false,
11
+ "normalized": false,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ },
15
+ "eos_token": {
16
+ "content": "</s>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": {
23
+ "content": "<pad>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "unk_token": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ }
36
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<user>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<assistant>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<system>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<sep>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<user>",
70
+ "<assistant>",
71
+ "<system>",
72
+ "<sep>"
73
+ ],
74
+ "bos_token": "<s>",
75
+ "clean_up_tokenization_spaces": false,
76
+ "eos_token": "</s>",
77
+ "extra_special_tokens": {},
78
+ "model_max_length": 1000000000000000019884624838656,
79
+ "pad_token": "<pad>",
80
+ "tokenizer_class": "PreTrainedTokenizer",
81
+ "unk_token": "<unk>"
82
+ }
trainer_state.json ADDED
@@ -0,0 +1,743 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 16.0,
6
+ "eval_steps": 500,
7
+ "global_step": 10000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.16,
14
+ "grad_norm": 5.144001483917236,
15
+ "learning_rate": 4.950000000000001e-06,
16
+ "loss": 10.4886,
17
+ "step": 100
18
+ },
19
+ {
20
+ "epoch": 0.32,
21
+ "grad_norm": 2.300384998321533,
22
+ "learning_rate": 9.950000000000001e-06,
23
+ "loss": 7.6471,
24
+ "step": 200
25
+ },
26
+ {
27
+ "epoch": 0.48,
28
+ "grad_norm": 2.140571355819702,
29
+ "learning_rate": 1.4950000000000001e-05,
30
+ "loss": 6.9594,
31
+ "step": 300
32
+ },
33
+ {
34
+ "epoch": 0.64,
35
+ "grad_norm": 2.083284616470337,
36
+ "learning_rate": 1.995e-05,
37
+ "loss": 6.7859,
38
+ "step": 400
39
+ },
40
+ {
41
+ "epoch": 0.8,
42
+ "grad_norm": 2.006448745727539,
43
+ "learning_rate": 2.495e-05,
44
+ "loss": 6.6356,
45
+ "step": 500
46
+ },
47
+ {
48
+ "epoch": 0.96,
49
+ "grad_norm": 2.856365919113159,
50
+ "learning_rate": 2.995e-05,
51
+ "loss": 6.5126,
52
+ "step": 600
53
+ },
54
+ {
55
+ "epoch": 1.12,
56
+ "grad_norm": 3.0544638633728027,
57
+ "learning_rate": 3.495e-05,
58
+ "loss": 6.375,
59
+ "step": 700
60
+ },
61
+ {
62
+ "epoch": 1.28,
63
+ "grad_norm": 2.5620715618133545,
64
+ "learning_rate": 3.995e-05,
65
+ "loss": 6.2585,
66
+ "step": 800
67
+ },
68
+ {
69
+ "epoch": 1.44,
70
+ "grad_norm": 2.4715466499328613,
71
+ "learning_rate": 4.495e-05,
72
+ "loss": 6.1562,
73
+ "step": 900
74
+ },
75
+ {
76
+ "epoch": 1.6,
77
+ "grad_norm": 2.5716171264648438,
78
+ "learning_rate": 4.995e-05,
79
+ "loss": 6.062,
80
+ "step": 1000
81
+ },
82
+ {
83
+ "epoch": 1.76,
84
+ "grad_norm": 2.4870810508728027,
85
+ "learning_rate": 4.945e-05,
86
+ "loss": 5.9831,
87
+ "step": 1100
88
+ },
89
+ {
90
+ "epoch": 1.92,
91
+ "grad_norm": 2.457263231277466,
92
+ "learning_rate": 4.8894444444444446e-05,
93
+ "loss": 5.8745,
94
+ "step": 1200
95
+ },
96
+ {
97
+ "epoch": 2.08,
98
+ "grad_norm": 2.725148916244507,
99
+ "learning_rate": 4.833888888888889e-05,
100
+ "loss": 5.7869,
101
+ "step": 1300
102
+ },
103
+ {
104
+ "epoch": 2.24,
105
+ "grad_norm": 3.010024070739746,
106
+ "learning_rate": 4.7783333333333334e-05,
107
+ "loss": 5.7044,
108
+ "step": 1400
109
+ },
110
+ {
111
+ "epoch": 2.4,
112
+ "grad_norm": 2.742307424545288,
113
+ "learning_rate": 4.7227777777777784e-05,
114
+ "loss": 5.6575,
115
+ "step": 1500
116
+ },
117
+ {
118
+ "epoch": 2.56,
119
+ "grad_norm": 2.8663551807403564,
120
+ "learning_rate": 4.667222222222222e-05,
121
+ "loss": 5.602,
122
+ "step": 1600
123
+ },
124
+ {
125
+ "epoch": 2.7199999999999998,
126
+ "grad_norm": 2.5844039916992188,
127
+ "learning_rate": 4.611666666666667e-05,
128
+ "loss": 5.5626,
129
+ "step": 1700
130
+ },
131
+ {
132
+ "epoch": 2.88,
133
+ "grad_norm": 2.871776819229126,
134
+ "learning_rate": 4.5561111111111116e-05,
135
+ "loss": 5.5071,
136
+ "step": 1800
137
+ },
138
+ {
139
+ "epoch": 3.04,
140
+ "grad_norm": 2.7475697994232178,
141
+ "learning_rate": 4.500555555555556e-05,
142
+ "loss": 5.4527,
143
+ "step": 1900
144
+ },
145
+ {
146
+ "epoch": 3.2,
147
+ "grad_norm": 2.8367366790771484,
148
+ "learning_rate": 4.445e-05,
149
+ "loss": 5.3543,
150
+ "step": 2000
151
+ },
152
+ {
153
+ "epoch": 3.36,
154
+ "grad_norm": 2.717906951904297,
155
+ "learning_rate": 4.389444444444445e-05,
156
+ "loss": 5.3329,
157
+ "step": 2100
158
+ },
159
+ {
160
+ "epoch": 3.52,
161
+ "grad_norm": 2.6652536392211914,
162
+ "learning_rate": 4.333888888888889e-05,
163
+ "loss": 5.3185,
164
+ "step": 2200
165
+ },
166
+ {
167
+ "epoch": 3.68,
168
+ "grad_norm": 2.424541711807251,
169
+ "learning_rate": 4.2783333333333334e-05,
170
+ "loss": 5.2868,
171
+ "step": 2300
172
+ },
173
+ {
174
+ "epoch": 3.84,
175
+ "grad_norm": 2.616556406021118,
176
+ "learning_rate": 4.222777777777778e-05,
177
+ "loss": 5.2582,
178
+ "step": 2400
179
+ },
180
+ {
181
+ "epoch": 4.0,
182
+ "grad_norm": 2.6706628799438477,
183
+ "learning_rate": 4.167222222222222e-05,
184
+ "loss": 5.249,
185
+ "step": 2500
186
+ },
187
+ {
188
+ "epoch": 4.16,
189
+ "grad_norm": 2.4817540645599365,
190
+ "learning_rate": 4.111666666666667e-05,
191
+ "loss": 5.1244,
192
+ "step": 2600
193
+ },
194
+ {
195
+ "epoch": 4.32,
196
+ "grad_norm": 2.696004867553711,
197
+ "learning_rate": 4.056111111111111e-05,
198
+ "loss": 5.1048,
199
+ "step": 2700
200
+ },
201
+ {
202
+ "epoch": 4.48,
203
+ "grad_norm": 2.7203173637390137,
204
+ "learning_rate": 4.000555555555556e-05,
205
+ "loss": 5.1084,
206
+ "step": 2800
207
+ },
208
+ {
209
+ "epoch": 4.64,
210
+ "grad_norm": 2.6082541942596436,
211
+ "learning_rate": 3.9450000000000003e-05,
212
+ "loss": 5.0946,
213
+ "step": 2900
214
+ },
215
+ {
216
+ "epoch": 4.8,
217
+ "grad_norm": 2.654949426651001,
218
+ "learning_rate": 3.889444444444445e-05,
219
+ "loss": 5.0804,
220
+ "step": 3000
221
+ },
222
+ {
223
+ "epoch": 4.96,
224
+ "grad_norm": 3.218290328979492,
225
+ "learning_rate": 3.833888888888889e-05,
226
+ "loss": 5.0986,
227
+ "step": 3100
228
+ },
229
+ {
230
+ "epoch": 5.12,
231
+ "grad_norm": 2.50736665725708,
232
+ "learning_rate": 3.7783333333333335e-05,
233
+ "loss": 4.9823,
234
+ "step": 3200
235
+ },
236
+ {
237
+ "epoch": 5.28,
238
+ "grad_norm": 2.39935040473938,
239
+ "learning_rate": 3.722777777777778e-05,
240
+ "loss": 4.9444,
241
+ "step": 3300
242
+ },
243
+ {
244
+ "epoch": 5.44,
245
+ "grad_norm": 2.9400389194488525,
246
+ "learning_rate": 3.667222222222222e-05,
247
+ "loss": 4.952,
248
+ "step": 3400
249
+ },
250
+ {
251
+ "epoch": 5.6,
252
+ "grad_norm": 2.8050739765167236,
253
+ "learning_rate": 3.611666666666667e-05,
254
+ "loss": 4.9455,
255
+ "step": 3500
256
+ },
257
+ {
258
+ "epoch": 5.76,
259
+ "grad_norm": 2.614954948425293,
260
+ "learning_rate": 3.556111111111111e-05,
261
+ "loss": 4.9633,
262
+ "step": 3600
263
+ },
264
+ {
265
+ "epoch": 5.92,
266
+ "grad_norm": 2.524243116378784,
267
+ "learning_rate": 3.500555555555556e-05,
268
+ "loss": 4.9411,
269
+ "step": 3700
270
+ },
271
+ {
272
+ "epoch": 6.08,
273
+ "grad_norm": 2.5119824409484863,
274
+ "learning_rate": 3.445e-05,
275
+ "loss": 4.892,
276
+ "step": 3800
277
+ },
278
+ {
279
+ "epoch": 6.24,
280
+ "grad_norm": 2.7221860885620117,
281
+ "learning_rate": 3.389444444444445e-05,
282
+ "loss": 4.8186,
283
+ "step": 3900
284
+ },
285
+ {
286
+ "epoch": 6.4,
287
+ "grad_norm": 2.6388821601867676,
288
+ "learning_rate": 3.333888888888889e-05,
289
+ "loss": 4.8228,
290
+ "step": 4000
291
+ },
292
+ {
293
+ "epoch": 6.5600000000000005,
294
+ "grad_norm": 2.783097505569458,
295
+ "learning_rate": 3.2783333333333335e-05,
296
+ "loss": 4.8326,
297
+ "step": 4100
298
+ },
299
+ {
300
+ "epoch": 6.72,
301
+ "grad_norm": 2.732416868209839,
302
+ "learning_rate": 3.222777777777778e-05,
303
+ "loss": 4.8381,
304
+ "step": 4200
305
+ },
306
+ {
307
+ "epoch": 6.88,
308
+ "grad_norm": 2.6935789585113525,
309
+ "learning_rate": 3.167222222222222e-05,
310
+ "loss": 4.8337,
311
+ "step": 4300
312
+ },
313
+ {
314
+ "epoch": 7.04,
315
+ "grad_norm": 2.742158889770508,
316
+ "learning_rate": 3.1116666666666666e-05,
317
+ "loss": 4.7884,
318
+ "step": 4400
319
+ },
320
+ {
321
+ "epoch": 7.2,
322
+ "grad_norm": 2.572331666946411,
323
+ "learning_rate": 3.056111111111111e-05,
324
+ "loss": 4.7088,
325
+ "step": 4500
326
+ },
327
+ {
328
+ "epoch": 7.36,
329
+ "grad_norm": 2.7174787521362305,
330
+ "learning_rate": 3.000555555555556e-05,
331
+ "loss": 4.7344,
332
+ "step": 4600
333
+ },
334
+ {
335
+ "epoch": 7.52,
336
+ "grad_norm": 2.2955660820007324,
337
+ "learning_rate": 2.945e-05,
338
+ "loss": 4.746,
339
+ "step": 4700
340
+ },
341
+ {
342
+ "epoch": 7.68,
343
+ "grad_norm": 2.6039907932281494,
344
+ "learning_rate": 2.8894444444444445e-05,
345
+ "loss": 4.7329,
346
+ "step": 4800
347
+ },
348
+ {
349
+ "epoch": 7.84,
350
+ "grad_norm": 2.8570940494537354,
351
+ "learning_rate": 2.8338888888888892e-05,
352
+ "loss": 4.7312,
353
+ "step": 4900
354
+ },
355
+ {
356
+ "epoch": 8.0,
357
+ "grad_norm": 3.2475857734680176,
358
+ "learning_rate": 2.7783333333333332e-05,
359
+ "loss": 4.7324,
360
+ "step": 5000
361
+ },
362
+ {
363
+ "epoch": 8.16,
364
+ "grad_norm": 2.8648529052734375,
365
+ "learning_rate": 2.722777777777778e-05,
366
+ "loss": 4.619,
367
+ "step": 5100
368
+ },
369
+ {
370
+ "epoch": 8.32,
371
+ "grad_norm": 2.7932467460632324,
372
+ "learning_rate": 2.6672222222222226e-05,
373
+ "loss": 4.6577,
374
+ "step": 5200
375
+ },
376
+ {
377
+ "epoch": 8.48,
378
+ "grad_norm": 2.5735385417938232,
379
+ "learning_rate": 2.6116666666666667e-05,
380
+ "loss": 4.6458,
381
+ "step": 5300
382
+ },
383
+ {
384
+ "epoch": 8.64,
385
+ "grad_norm": 2.3901100158691406,
386
+ "learning_rate": 2.5561111111111114e-05,
387
+ "loss": 4.6412,
388
+ "step": 5400
389
+ },
390
+ {
391
+ "epoch": 8.8,
392
+ "grad_norm": 2.8626747131347656,
393
+ "learning_rate": 2.5005555555555554e-05,
394
+ "loss": 4.6545,
395
+ "step": 5500
396
+ },
397
+ {
398
+ "epoch": 8.96,
399
+ "grad_norm": 2.960085868835449,
400
+ "learning_rate": 2.445e-05,
401
+ "loss": 4.6494,
402
+ "step": 5600
403
+ },
404
+ {
405
+ "epoch": 9.12,
406
+ "grad_norm": 2.6465635299682617,
407
+ "learning_rate": 2.3894444444444445e-05,
408
+ "loss": 4.5837,
409
+ "step": 5700
410
+ },
411
+ {
412
+ "epoch": 9.28,
413
+ "grad_norm": 2.3963518142700195,
414
+ "learning_rate": 2.3338888888888892e-05,
415
+ "loss": 4.5695,
416
+ "step": 5800
417
+ },
418
+ {
419
+ "epoch": 9.44,
420
+ "grad_norm": 2.539828300476074,
421
+ "learning_rate": 2.2783333333333336e-05,
422
+ "loss": 4.5647,
423
+ "step": 5900
424
+ },
425
+ {
426
+ "epoch": 9.6,
427
+ "grad_norm": 2.7697598934173584,
428
+ "learning_rate": 2.2227777777777776e-05,
429
+ "loss": 4.5834,
430
+ "step": 6000
431
+ },
432
+ {
433
+ "epoch": 9.76,
434
+ "grad_norm": 2.8896372318267822,
435
+ "learning_rate": 2.1672222222222223e-05,
436
+ "loss": 4.5762,
437
+ "step": 6100
438
+ },
439
+ {
440
+ "epoch": 9.92,
441
+ "grad_norm": 2.9072511196136475,
442
+ "learning_rate": 2.1116666666666667e-05,
443
+ "loss": 4.6064,
444
+ "step": 6200
445
+ },
446
+ {
447
+ "epoch": 10.08,
448
+ "grad_norm": 2.598778247833252,
449
+ "learning_rate": 2.056111111111111e-05,
450
+ "loss": 4.5386,
451
+ "step": 6300
452
+ },
453
+ {
454
+ "epoch": 10.24,
455
+ "grad_norm": 2.8078835010528564,
456
+ "learning_rate": 2.0005555555555555e-05,
457
+ "loss": 4.4946,
458
+ "step": 6400
459
+ },
460
+ {
461
+ "epoch": 10.4,
462
+ "grad_norm": 2.434978723526001,
463
+ "learning_rate": 1.9450000000000002e-05,
464
+ "loss": 4.5297,
465
+ "step": 6500
466
+ },
467
+ {
468
+ "epoch": 10.56,
469
+ "grad_norm": 2.5917904376983643,
470
+ "learning_rate": 1.8894444444444446e-05,
471
+ "loss": 4.5187,
472
+ "step": 6600
473
+ },
474
+ {
475
+ "epoch": 10.72,
476
+ "grad_norm": 2.5768167972564697,
477
+ "learning_rate": 1.833888888888889e-05,
478
+ "loss": 4.5535,
479
+ "step": 6700
480
+ },
481
+ {
482
+ "epoch": 10.88,
483
+ "grad_norm": 2.7409565448760986,
484
+ "learning_rate": 1.7783333333333336e-05,
485
+ "loss": 4.5306,
486
+ "step": 6800
487
+ },
488
+ {
489
+ "epoch": 11.04,
490
+ "grad_norm": 2.722594738006592,
491
+ "learning_rate": 1.722777777777778e-05,
492
+ "loss": 4.5035,
493
+ "step": 6900
494
+ },
495
+ {
496
+ "epoch": 11.2,
497
+ "grad_norm": 2.68045711517334,
498
+ "learning_rate": 1.6672222222222224e-05,
499
+ "loss": 4.4649,
500
+ "step": 7000
501
+ },
502
+ {
503
+ "epoch": 11.36,
504
+ "grad_norm": 2.6111624240875244,
505
+ "learning_rate": 1.6116666666666668e-05,
506
+ "loss": 4.4618,
507
+ "step": 7100
508
+ },
509
+ {
510
+ "epoch": 11.52,
511
+ "grad_norm": 3.0513899326324463,
512
+ "learning_rate": 1.556111111111111e-05,
513
+ "loss": 4.4787,
514
+ "step": 7200
515
+ },
516
+ {
517
+ "epoch": 11.68,
518
+ "grad_norm": 2.5727720260620117,
519
+ "learning_rate": 1.5005555555555557e-05,
520
+ "loss": 4.4691,
521
+ "step": 7300
522
+ },
523
+ {
524
+ "epoch": 11.84,
525
+ "grad_norm": 2.7505650520324707,
526
+ "learning_rate": 1.4449999999999999e-05,
527
+ "loss": 4.4737,
528
+ "step": 7400
529
+ },
530
+ {
531
+ "epoch": 12.0,
532
+ "grad_norm": 2.6556284427642822,
533
+ "learning_rate": 1.3894444444444446e-05,
534
+ "loss": 4.4753,
535
+ "step": 7500
536
+ },
537
+ {
538
+ "epoch": 12.16,
539
+ "grad_norm": 2.8100340366363525,
540
+ "learning_rate": 1.333888888888889e-05,
541
+ "loss": 4.4077,
542
+ "step": 7600
543
+ },
544
+ {
545
+ "epoch": 12.32,
546
+ "grad_norm": 2.6745927333831787,
547
+ "learning_rate": 1.2783333333333333e-05,
548
+ "loss": 4.4306,
549
+ "step": 7700
550
+ },
551
+ {
552
+ "epoch": 12.48,
553
+ "grad_norm": 2.9935076236724854,
554
+ "learning_rate": 1.2227777777777779e-05,
555
+ "loss": 4.4239,
556
+ "step": 7800
557
+ },
558
+ {
559
+ "epoch": 12.64,
560
+ "grad_norm": 2.893677234649658,
561
+ "learning_rate": 1.1672222222222223e-05,
562
+ "loss": 4.423,
563
+ "step": 7900
564
+ },
565
+ {
566
+ "epoch": 12.8,
567
+ "grad_norm": 2.6659703254699707,
568
+ "learning_rate": 1.1116666666666666e-05,
569
+ "loss": 4.4291,
570
+ "step": 8000
571
+ },
572
+ {
573
+ "epoch": 12.96,
574
+ "grad_norm": 2.6794395446777344,
575
+ "learning_rate": 1.0561111111111112e-05,
576
+ "loss": 4.4407,
577
+ "step": 8100
578
+ },
579
+ {
580
+ "epoch": 13.12,
581
+ "grad_norm": 2.862091541290283,
582
+ "learning_rate": 1.0005555555555556e-05,
583
+ "loss": 4.4083,
584
+ "step": 8200
585
+ },
586
+ {
587
+ "epoch": 13.28,
588
+ "grad_norm": 2.6573102474212646,
589
+ "learning_rate": 9.450000000000001e-06,
590
+ "loss": 4.3949,
591
+ "step": 8300
592
+ },
593
+ {
594
+ "epoch": 13.44,
595
+ "grad_norm": 2.6582767963409424,
596
+ "learning_rate": 8.894444444444445e-06,
597
+ "loss": 4.4,
598
+ "step": 8400
599
+ },
600
+ {
601
+ "epoch": 13.6,
602
+ "grad_norm": 2.802070140838623,
603
+ "learning_rate": 8.338888888888888e-06,
604
+ "loss": 4.3769,
605
+ "step": 8500
606
+ },
607
+ {
608
+ "epoch": 13.76,
609
+ "grad_norm": 2.635528802871704,
610
+ "learning_rate": 7.783333333333334e-06,
611
+ "loss": 4.3896,
612
+ "step": 8600
613
+ },
614
+ {
615
+ "epoch": 13.92,
616
+ "grad_norm": 2.940291404724121,
617
+ "learning_rate": 7.227777777777778e-06,
618
+ "loss": 4.3992,
619
+ "step": 8700
620
+ },
621
+ {
622
+ "epoch": 14.08,
623
+ "grad_norm": 3.0506865978240967,
624
+ "learning_rate": 6.672222222222223e-06,
625
+ "loss": 4.3739,
626
+ "step": 8800
627
+ },
628
+ {
629
+ "epoch": 14.24,
630
+ "grad_norm": 2.7096052169799805,
631
+ "learning_rate": 6.116666666666667e-06,
632
+ "loss": 4.3511,
633
+ "step": 8900
634
+ },
635
+ {
636
+ "epoch": 14.4,
637
+ "grad_norm": 3.000335693359375,
638
+ "learning_rate": 5.561111111111111e-06,
639
+ "loss": 4.3541,
640
+ "step": 9000
641
+ },
642
+ {
643
+ "epoch": 14.56,
644
+ "grad_norm": 3.0403401851654053,
645
+ "learning_rate": 5.005555555555556e-06,
646
+ "loss": 4.3696,
647
+ "step": 9100
648
+ },
649
+ {
650
+ "epoch": 14.72,
651
+ "grad_norm": 2.6936028003692627,
652
+ "learning_rate": 4.45e-06,
653
+ "loss": 4.3765,
654
+ "step": 9200
655
+ },
656
+ {
657
+ "epoch": 14.88,
658
+ "grad_norm": 2.8382890224456787,
659
+ "learning_rate": 3.894444444444444e-06,
660
+ "loss": 4.3587,
661
+ "step": 9300
662
+ },
663
+ {
664
+ "epoch": 15.04,
665
+ "grad_norm": 2.7517287731170654,
666
+ "learning_rate": 3.3388888888888893e-06,
667
+ "loss": 4.3703,
668
+ "step": 9400
669
+ },
670
+ {
671
+ "epoch": 15.2,
672
+ "grad_norm": 3.037428140640259,
673
+ "learning_rate": 2.7833333333333335e-06,
674
+ "loss": 4.3233,
675
+ "step": 9500
676
+ },
677
+ {
678
+ "epoch": 15.36,
679
+ "grad_norm": 2.624190330505371,
680
+ "learning_rate": 2.227777777777778e-06,
681
+ "loss": 4.3242,
682
+ "step": 9600
683
+ },
684
+ {
685
+ "epoch": 15.52,
686
+ "grad_norm": 2.913299560546875,
687
+ "learning_rate": 1.6722222222222223e-06,
688
+ "loss": 4.3426,
689
+ "step": 9700
690
+ },
691
+ {
692
+ "epoch": 15.68,
693
+ "grad_norm": 2.480700731277466,
694
+ "learning_rate": 1.1166666666666666e-06,
695
+ "loss": 4.3416,
696
+ "step": 9800
697
+ },
698
+ {
699
+ "epoch": 15.84,
700
+ "grad_norm": 2.8008666038513184,
701
+ "learning_rate": 5.611111111111111e-07,
702
+ "loss": 4.3539,
703
+ "step": 9900
704
+ },
705
+ {
706
+ "epoch": 16.0,
707
+ "grad_norm": 3.1308672428131104,
708
+ "learning_rate": 5.555555555555556e-09,
709
+ "loss": 4.353,
710
+ "step": 10000
711
+ },
712
+ {
713
+ "epoch": 16.0,
714
+ "step": 10000,
715
+ "total_flos": 1.2490998615421747e+17,
716
+ "train_loss": 4.987235028076172,
717
+ "train_runtime": 15645.3104,
718
+ "train_samples_per_second": 10.227,
719
+ "train_steps_per_second": 0.639
720
+ }
721
+ ],
722
+ "logging_steps": 100,
723
+ "max_steps": 10000,
724
+ "num_input_tokens_seen": 0,
725
+ "num_train_epochs": 16,
726
+ "save_steps": 2000,
727
+ "stateful_callbacks": {
728
+ "TrainerControl": {
729
+ "args": {
730
+ "should_epoch_stop": false,
731
+ "should_evaluate": false,
732
+ "should_log": false,
733
+ "should_save": true,
734
+ "should_training_stop": true
735
+ },
736
+ "attributes": {}
737
+ }
738
+ },
739
+ "total_flos": 1.2490998615421747e+17,
740
+ "train_batch_size": 4,
741
+ "trial_name": null,
742
+ "trial_params": null
743
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea4a998b317602911f0d66a372b45f4e97b0f2fbb9e6effe3568b417a1f5d3b
3
+ size 5649