Hugging Face's logo

Ba2han
/
experimental_auto

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
sft
unsloth
trl
custom_code
text-generation-inference
Model card Files
xet
 Community
Ba2han commited on
Commit
c49037d
·
verified ·
1 Parent(s): 921da73

Training in progress, step 50, checkpoint

Browse files
Files changed (10) hide show
  1. last-checkpoint/config.json +104 -0
  2. last-checkpoint/generation_config.json +13 -0
  3. last-checkpoint/model.safetensors +3 -0
  4. last-checkpoint/optimizer.pt +3 -0
  5. last-checkpoint/rng_state.pth +3 -0
  6. last-checkpoint/scheduler.pt +3 -0
  7. last-checkpoint/tokenizer.json +0 -0
  8. last-checkpoint/tokenizer_config.json +162 -0
  9. last-checkpoint/trainer_state.json +392 -0
  10. last-checkpoint/training_args.bin +3 -0
last-checkpoint/config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SquaredReLUQwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoModelForCausalLM": "patch.SquaredReLUQwen3ForCausalLM"
9
+ },
10
+ "bos_token_id": 50030,
11
+ "dtype": "bfloat16",
12
+ "eos_token_id": 50031,
13
+ "head_dim": 64,
14
+ "hidden_act": "squared_relu",
15
+ "hidden_size": 768,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 2304,
18
+ "layer_types": [
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention"
83
+ ],
84
+ "max_position_embeddings": 8192,
85
+ "max_window_layers": 28,
86
+ "model_name": "qwen3_from_scratch",
87
+ "model_type": "qwen3",
88
+ "num_attention_heads": 16,
89
+ "num_hidden_layers": 64,
90
+ "num_key_value_heads": 4,
91
+ "pad_token_id": 50034,
92
+ "rms_norm_eps": 1e-06,
93
+ "rope_parameters": {
94
+ "rope_theta": 10000.0,
95
+ "rope_type": "default"
96
+ },
97
+ "sliding_window": null,
98
+ "tie_word_embeddings": true,
99
+ "transformers_version": "5.5.0",
100
+ "unsloth_version": "2026.5.2",
101
+ "use_cache": false,
102
+ "use_sliding_window": false,
103
+ "vocab_size": 50048
104
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50030,
4
+ "eos_token_id": [
5
+ 50031
6
+ ],
7
+ "max_length": 8192,
8
+ "output_attentions": false,
9
+ "output_hidden_states": false,
10
+ "pad_token_id": 50034,
11
+ "transformers_version": "5.5.0",
12
+ "use_cache": false
13
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b4ce55f856a67bfdbd003ebe9b33428ea067be73223fd9c3bf1c9940e96dfe
3
+ size 1008303016
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82d52d99bf15dccd952a3b4f736ae5075d180cf8f005d3c384238593828d1df
3
+ size 1086712487
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
3
+ size 14645
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c3b6e6139f923a24202d50bcbca49b224309c9139ea19d316d6f4729bb3d183
3
+ size 1465
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|begin_of_text|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|end_of_text|>",
6
+ "is_local": true,
7
+ "model_input_names": [
8
+ "input_ids",
9
+ "attention_mask"
10
+ ],
11
+ "model_max_length": 8192,
12
+ "pad_token": "<|finetune_right_pad_id|>",
13
+ "padding_side": "right",
14
+ "tokenizer_class": "TokenizersBackend",
15
+ "unk_token": null,
16
+ "added_tokens_decoder": {
17
+ "50030": {
18
+ "content": "<|begin_of_text|>",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false,
23
+ "special": true
24
+ },
25
+ "50031": {
26
+ "content": "<|end_of_text|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ "50032": {
34
+ "content": "<|reserved_special_token_0|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "50033": {
42
+ "content": "<|reserved_special_token_1|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "50034": {
50
+ "content": "<|finetune_right_pad_id|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "50035": {
58
+ "content": "<|reserved_special_token_2|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "50036": {
66
+ "content": "<|start_header_id|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "50037": {
74
+ "content": "<|end_header_id|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "50038": {
82
+ "content": "<|eom_id|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "50039": {
90
+ "content": "<|eot_id|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "50040": {
98
+ "content": "<|python_tag|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "50041": {
106
+ "content": "<|reserved_special_token_3|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "50042": {
114
+ "content": "<|reserved_special_token_4|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "50043": {
122
+ "content": "<|reserved_special_token_5|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "50044": {
130
+ "content": "<|reserved_special_token_6|>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": true
136
+ },
137
+ "50045": {
138
+ "content": "<|reserved_special_token_7|>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": true
144
+ },
145
+ "50046": {
146
+ "content": "<|reserved_special_token_8|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": true
152
+ },
153
+ "50047": {
154
+ "content": "<|reserved_special_token_9|>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": true
160
+ }
161
+ }
162
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.2140468227424749,
6
+ "eval_steps": 50,
7
+ "global_step": 50,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.004280936454849498,
14
+ "grad_norm": 2.3125,
15
+ "learning_rate": 0.0,
16
+ "loss": 10.99751091003418,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.008561872909698997,
21
+ "grad_norm": 2.21875,
22
+ "learning_rate": 0.0125,
23
+ "loss": 10.999887466430664,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.012842809364548496,
28
+ "grad_norm": 1.875,
29
+ "learning_rate": 0.025,
30
+ "loss": 10.661027908325195,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.017123745819397993,
35
+ "grad_norm": 1.453125,
36
+ "learning_rate": 0.02499842659592344,
37
+ "loss": 10.258359909057617,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.02140468227424749,
42
+ "grad_norm": 1.6484375,
43
+ "learning_rate": 0.024993706779789817,
44
+ "loss": 10.03167724609375,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.02568561872909699,
49
+ "grad_norm": 2.65625,
50
+ "learning_rate": 0.0249858417397876,
51
+ "loss": 10.06635856628418,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.02996655518394649,
56
+ "grad_norm": 1.3515625,
57
+ "learning_rate": 0.024974833455898557,
58
+ "loss": 9.684752464294434,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.034247491638795986,
63
+ "grad_norm": 3.03125,
64
+ "learning_rate": 0.024960684699399282,
65
+ "loss": 9.619985580444336,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.038528428093645484,
70
+ "grad_norm": 1.2109375,
71
+ "learning_rate": 0.024943399032163558,
72
+ "loss": 9.322598457336426,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.04280936454849498,
77
+ "grad_norm": 1.203125,
78
+ "learning_rate": 0.024922980805765677,
79
+ "loss": 9.167491912841797,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.04709030100334448,
84
+ "grad_norm": 1.1171875,
85
+ "learning_rate": 0.024899435160384942,
86
+ "loss": 8.97598934173584,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.05137123745819398,
91
+ "grad_norm": 1.09375,
92
+ "learning_rate": 0.02487276802351166,
93
+ "loss": 8.841875076293945,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.05565217391304348,
98
+ "grad_norm": 0.8125,
99
+ "learning_rate": 0.02484298610845493,
100
+ "loss": 8.693690299987793,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.05993311036789298,
105
+ "grad_norm": 0.80859375,
106
+ "learning_rate": 0.024810096912652603,
107
+ "loss": 8.540060997009277,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.06421404682274247,
112
+ "grad_norm": 0.62109375,
113
+ "learning_rate": 0.024774108715783835,
114
+ "loss": 8.427875518798828,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.06849498327759197,
119
+ "grad_norm": 0.703125,
120
+ "learning_rate": 0.02473503057768474,
121
+ "loss": 8.279977798461914,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.07277591973244148,
126
+ "grad_norm": 0.6640625,
127
+ "learning_rate": 0.02469287233606759,
128
+ "loss": 8.238062858581543,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.07705685618729097,
133
+ "grad_norm": 0.60546875,
134
+ "learning_rate": 0.024647644604044273,
135
+ "loss": 8.140103340148926,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.08133779264214047,
140
+ "grad_norm": 0.6171875,
141
+ "learning_rate": 0.024599358767454456,
142
+ "loss": 8.044753074645996,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.08561872909698996,
147
+ "grad_norm": 0.515625,
148
+ "learning_rate": 0.024548026981999278,
149
+ "loss": 7.991354465484619,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.08989966555183947,
154
+ "grad_norm": 0.57421875,
155
+ "learning_rate": 0.02449366217018122,
156
+ "loss": 7.921579837799072,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.09418060200668896,
161
+ "grad_norm": 0.65234375,
162
+ "learning_rate": 0.024436278018050924,
163
+ "loss": 7.871639728546143,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.09846153846153846,
168
+ "grad_norm": 0.50390625,
169
+ "learning_rate": 0.02437588897176182,
170
+ "loss": 7.7901129722595215,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.10274247491638797,
175
+ "grad_norm": 0.458984375,
176
+ "learning_rate": 0.024312510233933354,
177
+ "loss": 7.722414016723633,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.10702341137123746,
182
+ "grad_norm": 0.671875,
183
+ "learning_rate": 0.024246157759823857,
184
+ "loss": 7.714761257171631,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.11130434782608696,
189
+ "grad_norm": 0.73828125,
190
+ "learning_rate": 0.024176848253313836,
191
+ "loss": 7.689679145812988,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.11558528428093645,
196
+ "grad_norm": 0.466796875,
197
+ "learning_rate": 0.02410459916270091,
198
+ "loss": 7.656161308288574,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.11986622073578596,
203
+ "grad_norm": 0.373046875,
204
+ "learning_rate": 0.02402942867630727,
205
+ "loss": 7.593247890472412,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.12414715719063545,
210
+ "grad_norm": 0.365234375,
211
+ "learning_rate": 0.02395135571790087,
212
+ "loss": 7.558600902557373,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.12842809364548494,
217
+ "grad_norm": 0.392578125,
218
+ "learning_rate": 0.02387039994193148,
219
+ "loss": 7.517961502075195,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.13270903010033444,
224
+ "grad_norm": 0.48828125,
225
+ "learning_rate": 0.023786581728582768,
226
+ "loss": 7.4646525382995605,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.13698996655518395,
231
+ "grad_norm": 0.41015625,
232
+ "learning_rate": 0.023699922178641697,
233
+ "loss": 7.4094624519348145,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.14127090301003345,
238
+ "grad_norm": 0.376953125,
239
+ "learning_rate": 0.023610443108186545,
240
+ "loss": 7.402709484100342,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.14555183946488295,
245
+ "grad_norm": 0.361328125,
246
+ "learning_rate": 0.023518167043094777,
247
+ "loss": 7.354226112365723,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.14983277591973243,
252
+ "grad_norm": 0.38671875,
253
+ "learning_rate": 0.023423117213372313,
254
+ "loss": 7.302793502807617,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.15411371237458193,
259
+ "grad_norm": 0.484375,
260
+ "learning_rate": 0.023325317547305487,
261
+ "loss": 7.298144817352295,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.15839464882943144,
266
+ "grad_norm": 0.56640625,
267
+ "learning_rate": 0.023224792665437213,
268
+ "loss": 7.267189979553223,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.16267558528428094,
273
+ "grad_norm": 0.4140625,
274
+ "learning_rate": 0.023121567874368934,
275
+ "loss": 7.22215461730957,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.16695652173913045,
280
+ "grad_norm": 0.47265625,
281
+ "learning_rate": 0.023015669160389766,
282
+ "loss": 7.1571245193481445,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.17123745819397992,
287
+ "grad_norm": 0.466796875,
288
+ "learning_rate": 0.02290712318293464,
289
+ "loss": 7.14966344833374,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.17551839464882943,
294
+ "grad_norm": 0.486328125,
295
+ "learning_rate": 0.02279595726787291,
296
+ "loss": 7.105873107910156,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.17979933110367893,
301
+ "grad_norm": 0.46875,
302
+ "learning_rate": 0.022682199400629197,
303
+ "loss": 7.067068099975586,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.18408026755852844,
308
+ "grad_norm": 0.49609375,
309
+ "learning_rate": 0.022565878219138233,
310
+ "loss": 7.027277946472168,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.18836120401337791,
315
+ "grad_norm": 0.390625,
316
+ "learning_rate": 0.022447023006635404,
317
+ "loss": 6.947190761566162,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.19264214046822742,
322
+ "grad_norm": 0.40234375,
323
+ "learning_rate": 0.022325663684284847,
324
+ "loss": 6.984321594238281,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.19692307692307692,
329
+ "grad_norm": 0.40234375,
330
+ "learning_rate": 0.02220183080364696,
331
+ "loss": 6.949177265167236,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.20120401337792643,
336
+ "grad_norm": 0.353515625,
337
+ "learning_rate": 0.022075555538987227,
338
+ "loss": 6.896018028259277,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.20548494983277593,
343
+ "grad_norm": 0.41015625,
344
+ "learning_rate": 0.02194686967942823,
345
+ "loss": 6.808597564697266,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.2097658862876254,
350
+ "grad_norm": 0.408203125,
351
+ "learning_rate": 0.021815805620946937,
352
+ "loss": 6.824460983276367,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.2140468227424749,
357
+ "grad_norm": 0.4453125,
358
+ "learning_rate": 0.021682396358219166,
359
+ "loss": 6.777248382568359,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.2140468227424749,
364
+ "eval_loss": 6.7472333908081055,
365
+ "eval_runtime": 51.7313,
366
+ "eval_samples_per_second": 11.811,
367
+ "eval_steps_per_second": 2.958,
368
+ "step": 50
369
+ }
370
+ ],
371
+ "logging_steps": 1,
372
+ "max_steps": 200,
373
+ "num_input_tokens_seen": 0,
374
+ "num_train_epochs": 1,
375
+ "save_steps": 50,
376
+ "stateful_callbacks": {
377
+ "TrainerControl": {
378
+ "args": {
379
+ "should_epoch_stop": false,
380
+ "should_evaluate": false,
381
+ "should_log": false,
382
+ "should_save": true,
383
+ "should_training_stop": false
384
+ },
385
+ "attributes": {}
386
+ }
387
+ },
388
+ "total_flos": 3.645919305579571e+16,
389
+ "train_batch_size": 2,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d686833094b637e69f7be1bd7dd0c173bb768a2a8b1916830852d7703b16ed
3
+ size 5713