Ba2han commited on
Commit
0e6bb88
·
verified ·
1 Parent(s): 4aa1eb1

Training in progress, step 72, checkpoint

Browse files
.gitattributes CHANGED
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
last-checkpoint/chat_template.jinja ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user
2
+ ' + message['content'] + '<|im_end|>
3
+ '}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant
4
+ ' + message['content'] + '<|im_end|>
5
+ ' }}{% else %}{{ '<|im_start|>system
6
+ ' + message['content'] + '<|im_end|>
7
+ ' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
8
+ ' }}{% endif %}
last-checkpoint/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1280,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3840,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
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
+ ],
32
+ "max_position_embeddings": 8192,
33
+ "max_window_layers": 16,
34
+ "model_type": "qwen3",
35
+ "num_attention_heads": 16,
36
+ "num_hidden_layers": 16,
37
+ "num_key_value_heads": 8,
38
+ "pad_token_id": 151654,
39
+ "rms_norm_eps": 1e-06,
40
+ "rope_scaling": null,
41
+ "rope_theta": 10000,
42
+ "sliding_window": null,
43
+ "tie_word_embeddings": true,
44
+ "transformers_version": "4.57.1",
45
+ "unsloth_version": "2025.10.12",
46
+ "use_cache": true,
47
+ "use_sliding_window": false,
48
+ "vocab_size": 151669
49
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151645
5
+ ],
6
+ "max_length": 8192,
7
+ "pad_token_id": 151654,
8
+ "transformers_version": "4.57.1"
9
+ }
last-checkpoint/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93e586d311b719c71ddfda2ce115e7c331965b1d4590a73a1588b439a86ec0b
3
+ size 1111902928
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b48fa7b21cbee2cd356ae3fff03800105f6e620aaca169794133fe190c52fe26
3
+ size 2288456139
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e831a926501c469a9775d4b96fe9f086ccb9933946219ebf4fe959ebd9224d3
3
+ size 14709
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d707a902ef2f2bc42748a130649596c5a49add3e8def53f0f98f1ae2614521ef
3
+ size 1465
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "eos_token": "<|im_end|>",
19
+ "pad_token": "<|vision_pad|>"
20
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "151643": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "151644": {
12
+ "content": "<|im_start|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "151645": {
20
+ "content": "<|im_end|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "151646": {
28
+ "content": "<|object_ref_start|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "151647": {
36
+ "content": "<|object_ref_end|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "151648": {
44
+ "content": "<|box_start|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "151649": {
52
+ "content": "<|box_end|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "151650": {
60
+ "content": "<|quad_start|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "151651": {
68
+ "content": "<|quad_end|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "151652": {
76
+ "content": "<|vision_start|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "151653": {
84
+ "content": "<|vision_end|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "151654": {
92
+ "content": "<|vision_pad|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "151655": {
100
+ "content": "<|image_pad|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "151656": {
108
+ "content": "<|video_pad|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "151657": {
116
+ "content": "<tool_call>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "151658": {
124
+ "content": "</tool_call>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "151659": {
132
+ "content": "<|fim_prefix|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "151660": {
140
+ "content": "<|fim_middle|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "151661": {
148
+ "content": "<|fim_suffix|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "151662": {
156
+ "content": "<|fim_pad|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "151663": {
164
+ "content": "<|repo_name|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "151664": {
172
+ "content": "<|file_sep|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "151665": {
180
+ "content": "<tool_response>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "151666": {
188
+ "content": "</tool_response>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "151667": {
196
+ "content": "<think>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "151668": {
204
+ "content": "</think>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ }
211
+ },
212
+ "additional_special_tokens": [
213
+ "<|im_start|>",
214
+ "<|im_end|>"
215
+ ],
216
+ "bos_token": null,
217
+ "clean_up_tokenization_spaces": false,
218
+ "eos_token": "<|im_end|>",
219
+ "extra_special_tokens": {},
220
+ "model_max_length": 1000000000000000019884624838656,
221
+ "pad_token": "<|vision_pad|>",
222
+ "tokenizer_class": "Qwen2Tokenizer",
223
+ "unk_token": null
224
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,538 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.012160364810944329,
6
+ "eval_steps": 500,
7
+ "global_step": 72,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0001688939557075601,
14
+ "grad_norm": 0.95703125,
15
+ "learning_rate": 0.0,
16
+ "loss": 1.6541,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0003377879114151202,
21
+ "grad_norm": 1.0390625,
22
+ "learning_rate": 1.1627906976744185e-05,
23
+ "loss": 1.608,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.0005066818671226803,
28
+ "grad_norm": 0.9921875,
29
+ "learning_rate": 2.325581395348837e-05,
30
+ "loss": 1.6168,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.0006755758228302404,
35
+ "grad_norm": 0.82421875,
36
+ "learning_rate": 3.4883720930232556e-05,
37
+ "loss": 1.5475,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.0008444697785378006,
42
+ "grad_norm": 0.6640625,
43
+ "learning_rate": 4.651162790697674e-05,
44
+ "loss": 1.5649,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.0010133637342453607,
49
+ "grad_norm": 0.7890625,
50
+ "learning_rate": 5.8139534883720933e-05,
51
+ "loss": 1.563,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.001182257689952921,
56
+ "grad_norm": 0.80859375,
57
+ "learning_rate": 6.976744186046511e-05,
58
+ "loss": 1.4832,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.001351151645660481,
63
+ "grad_norm": 0.79296875,
64
+ "learning_rate": 8.139534883720931e-05,
65
+ "loss": 1.7616,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.0015200456013680411,
70
+ "grad_norm": 0.6796875,
71
+ "learning_rate": 9.302325581395348e-05,
72
+ "loss": 1.6388,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.0016889395570756011,
77
+ "grad_norm": 0.5859375,
78
+ "learning_rate": 0.00010465116279069768,
79
+ "loss": 1.5912,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.0018578335127831613,
84
+ "grad_norm": 0.57421875,
85
+ "learning_rate": 0.00011627906976744187,
86
+ "loss": 1.6368,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.0020267274684907213,
91
+ "grad_norm": 0.60546875,
92
+ "learning_rate": 0.00012790697674418605,
93
+ "loss": 1.5739,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.0021956214241982816,
98
+ "grad_norm": 0.625,
99
+ "learning_rate": 0.00013953488372093022,
100
+ "loss": 1.5355,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.002364515379905842,
105
+ "grad_norm": 0.58203125,
106
+ "learning_rate": 0.00015116279069767442,
107
+ "loss": 1.5526,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.0025334093356134016,
112
+ "grad_norm": 0.5703125,
113
+ "learning_rate": 0.00016279069767441862,
114
+ "loss": 1.5748,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.002702303291320962,
119
+ "grad_norm": 0.578125,
120
+ "learning_rate": 0.0001744186046511628,
121
+ "loss": 1.54,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.002871197247028522,
126
+ "grad_norm": 0.578125,
127
+ "learning_rate": 0.00018604651162790697,
128
+ "loss": 1.5499,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.0030400912027360822,
133
+ "grad_norm": 0.60546875,
134
+ "learning_rate": 0.00019767441860465116,
135
+ "loss": 1.6157,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.003208985158443642,
140
+ "grad_norm": 0.58984375,
141
+ "learning_rate": 0.00020930232558139536,
142
+ "loss": 1.5719,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.0033778791141512022,
147
+ "grad_norm": 0.55859375,
148
+ "learning_rate": 0.00022093023255813954,
149
+ "loss": 1.6069,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.0035467730698587625,
154
+ "grad_norm": 0.60546875,
155
+ "learning_rate": 0.00023255813953488373,
156
+ "loss": 1.5841,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.0037156670255663227,
161
+ "grad_norm": 0.62109375,
162
+ "learning_rate": 0.0002441860465116279,
163
+ "loss": 1.6501,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.0038845609812738825,
168
+ "grad_norm": 0.5390625,
169
+ "learning_rate": 0.0002558139534883721,
170
+ "loss": 1.534,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.004053454936981443,
175
+ "grad_norm": 0.59375,
176
+ "learning_rate": 0.00026744186046511625,
177
+ "loss": 1.6989,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.0042223488926890025,
182
+ "grad_norm": 0.58203125,
183
+ "learning_rate": 0.00027906976744186045,
184
+ "loss": 1.6357,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.004391242848396563,
189
+ "grad_norm": 0.62890625,
190
+ "learning_rate": 0.00029069767441860465,
191
+ "loss": 1.6576,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.004560136804104123,
196
+ "grad_norm": 0.5703125,
197
+ "learning_rate": 0.00030232558139534885,
198
+ "loss": 1.6448,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.004729030759811684,
203
+ "grad_norm": 0.57421875,
204
+ "learning_rate": 0.00031395348837209304,
205
+ "loss": 1.5372,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.004897924715519243,
210
+ "grad_norm": 0.63671875,
211
+ "learning_rate": 0.00032558139534883724,
212
+ "loss": 1.6233,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.005066818671226803,
217
+ "grad_norm": 0.57421875,
218
+ "learning_rate": 0.0003372093023255814,
219
+ "loss": 1.631,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.005235712626934364,
224
+ "grad_norm": 0.5625,
225
+ "learning_rate": 0.0003488372093023256,
226
+ "loss": 1.587,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.005404606582641924,
231
+ "grad_norm": 0.58203125,
232
+ "learning_rate": 0.00036046511627906973,
233
+ "loss": 1.5385,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.005573500538349484,
238
+ "grad_norm": 0.59375,
239
+ "learning_rate": 0.00037209302325581393,
240
+ "loss": 1.6433,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.005742394494057044,
245
+ "grad_norm": 0.51953125,
246
+ "learning_rate": 0.0003837209302325582,
247
+ "loss": 1.5948,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.005911288449764604,
252
+ "grad_norm": 0.56640625,
253
+ "learning_rate": 0.00039534883720930233,
254
+ "loss": 1.6416,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.0060801824054721645,
259
+ "grad_norm": 0.57421875,
260
+ "learning_rate": 0.00040697674418604653,
261
+ "loss": 1.6804,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.006249076361179724,
266
+ "grad_norm": 0.54296875,
267
+ "learning_rate": 0.0004186046511627907,
268
+ "loss": 1.6017,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.006417970316887284,
273
+ "grad_norm": 0.59765625,
274
+ "learning_rate": 0.00043023255813953487,
275
+ "loss": 1.7153,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.006586864272594845,
280
+ "grad_norm": 0.56640625,
281
+ "learning_rate": 0.00044186046511627907,
282
+ "loss": 1.6694,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.0067557582283024045,
287
+ "grad_norm": 0.55078125,
288
+ "learning_rate": 0.0004534883720930232,
289
+ "loss": 1.6596,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.006924652184009965,
294
+ "grad_norm": 0.5625,
295
+ "learning_rate": 0.00046511627906976747,
296
+ "loss": 1.6582,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.007093546139717525,
301
+ "grad_norm": 0.55859375,
302
+ "learning_rate": 0.00047674418604651167,
303
+ "loss": 1.5898,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.007262440095425085,
308
+ "grad_norm": 0.546875,
309
+ "learning_rate": 0.0004883720930232558,
310
+ "loss": 1.5138,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.007431334051132645,
315
+ "grad_norm": 0.8359375,
316
+ "learning_rate": 0.0005,
317
+ "loss": 1.5779,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.007600228006840205,
322
+ "grad_norm": 0.86328125,
323
+ "learning_rate": 0.0005116279069767442,
324
+ "loss": 1.6299,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.007769121962547765,
329
+ "grad_norm": 2.140625,
330
+ "learning_rate": 0.0005232558139534884,
331
+ "loss": 1.783,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.007938015918255326,
336
+ "grad_norm": 4.1875,
337
+ "learning_rate": 0.0005348837209302325,
338
+ "loss": 1.8094,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.008106909873962885,
343
+ "grad_norm": 1.1015625,
344
+ "learning_rate": 0.0005465116279069767,
345
+ "loss": 1.464,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.008275803829670445,
350
+ "grad_norm": 0.828125,
351
+ "learning_rate": 0.0005581395348837209,
352
+ "loss": 1.7214,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.008444697785378005,
357
+ "grad_norm": 1.3125,
358
+ "learning_rate": 0.0005697674418604651,
359
+ "loss": 1.8146,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.008613591741085566,
364
+ "grad_norm": 0.765625,
365
+ "learning_rate": 0.0005813953488372093,
366
+ "loss": 1.6926,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.008782485696793126,
371
+ "grad_norm": 0.81640625,
372
+ "learning_rate": 0.0005930232558139536,
373
+ "loss": 1.8269,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.008951379652500686,
378
+ "grad_norm": 0.75390625,
379
+ "learning_rate": 0.0006046511627906977,
380
+ "loss": 1.7138,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.009120273608208246,
385
+ "grad_norm": 0.609375,
386
+ "learning_rate": 0.0006162790697674419,
387
+ "loss": 1.6605,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.009289167563915806,
392
+ "grad_norm": 0.6328125,
393
+ "learning_rate": 0.0006279069767441861,
394
+ "loss": 1.708,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.009458061519623367,
399
+ "grad_norm": 0.75390625,
400
+ "learning_rate": 0.0006395348837209303,
401
+ "loss": 1.7706,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.009626955475330927,
406
+ "grad_norm": 0.578125,
407
+ "learning_rate": 0.0006511627906976745,
408
+ "loss": 1.6084,
409
+ "step": 57
410
+ },
411
+ {
412
+ "epoch": 0.009795849431038487,
413
+ "grad_norm": 0.6171875,
414
+ "learning_rate": 0.0006627906976744186,
415
+ "loss": 1.7136,
416
+ "step": 58
417
+ },
418
+ {
419
+ "epoch": 0.009964743386746047,
420
+ "grad_norm": 0.61328125,
421
+ "learning_rate": 0.0006744186046511628,
422
+ "loss": 1.7147,
423
+ "step": 59
424
+ },
425
+ {
426
+ "epoch": 0.010133637342453606,
427
+ "grad_norm": 0.59765625,
428
+ "learning_rate": 0.000686046511627907,
429
+ "loss": 1.7363,
430
+ "step": 60
431
+ },
432
+ {
433
+ "epoch": 0.010302531298161168,
434
+ "grad_norm": 0.58984375,
435
+ "learning_rate": 0.0006976744186046512,
436
+ "loss": 1.7936,
437
+ "step": 61
438
+ },
439
+ {
440
+ "epoch": 0.010471425253868728,
441
+ "grad_norm": 0.609375,
442
+ "learning_rate": 0.0007093023255813954,
443
+ "loss": 1.7578,
444
+ "step": 62
445
+ },
446
+ {
447
+ "epoch": 0.010640319209576287,
448
+ "grad_norm": 0.6171875,
449
+ "learning_rate": 0.0007209302325581395,
450
+ "loss": 1.8069,
451
+ "step": 63
452
+ },
453
+ {
454
+ "epoch": 0.010809213165283847,
455
+ "grad_norm": 0.56640625,
456
+ "learning_rate": 0.0007325581395348837,
457
+ "loss": 1.7867,
458
+ "step": 64
459
+ },
460
+ {
461
+ "epoch": 0.010978107120991407,
462
+ "grad_norm": 0.63671875,
463
+ "learning_rate": 0.0007441860465116279,
464
+ "loss": 1.7881,
465
+ "step": 65
466
+ },
467
+ {
468
+ "epoch": 0.011147001076698968,
469
+ "grad_norm": 0.640625,
470
+ "learning_rate": 0.0007558139534883722,
471
+ "loss": 1.8974,
472
+ "step": 66
473
+ },
474
+ {
475
+ "epoch": 0.011315895032406528,
476
+ "grad_norm": 0.76171875,
477
+ "learning_rate": 0.0007674418604651164,
478
+ "loss": 1.7448,
479
+ "step": 67
480
+ },
481
+ {
482
+ "epoch": 0.011484788988114088,
483
+ "grad_norm": 0.703125,
484
+ "learning_rate": 0.0007790697674418606,
485
+ "loss": 1.9082,
486
+ "step": 68
487
+ },
488
+ {
489
+ "epoch": 0.011653682943821648,
490
+ "grad_norm": 0.65234375,
491
+ "learning_rate": 0.0007906976744186047,
492
+ "loss": 1.813,
493
+ "step": 69
494
+ },
495
+ {
496
+ "epoch": 0.011822576899529208,
497
+ "grad_norm": 0.625,
498
+ "learning_rate": 0.0008023255813953489,
499
+ "loss": 1.7822,
500
+ "step": 70
501
+ },
502
+ {
503
+ "epoch": 0.011991470855236767,
504
+ "grad_norm": 0.62109375,
505
+ "learning_rate": 0.0008139534883720931,
506
+ "loss": 1.9291,
507
+ "step": 71
508
+ },
509
+ {
510
+ "epoch": 0.012160364810944329,
511
+ "grad_norm": 0.58984375,
512
+ "learning_rate": 0.0008255813953488373,
513
+ "loss": 1.7611,
514
+ "step": 72
515
+ }
516
+ ],
517
+ "logging_steps": 1,
518
+ "max_steps": 7106,
519
+ "num_input_tokens_seen": 0,
520
+ "num_train_epochs": 2,
521
+ "save_steps": 72,
522
+ "stateful_callbacks": {
523
+ "TrainerControl": {
524
+ "args": {
525
+ "should_epoch_stop": false,
526
+ "should_evaluate": false,
527
+ "should_log": false,
528
+ "should_save": true,
529
+ "should_training_stop": false
530
+ },
531
+ "attributes": {}
532
+ }
533
+ },
534
+ "total_flos": 1525841909889024.0,
535
+ "train_batch_size": 2,
536
+ "trial_name": null,
537
+ "trial_params": null
538
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c17475fd5668d5bb662bc181bda6a5c4b79daa1a8b225ed4204f2de18ee52f62
3
+ size 6289
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff