Hugging Face's logo

aixk
/
miniai

Transformers
Safetensors
Model card Files
xet
 Community
aixk commited on
Commit
4c3bee5
·
verified ·
1 Parent(s): 866e561

Upload checkpoint-1000

Browse files
Files changed (11) hide show
  1. checkpoint-1000/chat_template.jinja +4 -0
  2. checkpoint-1000/config.json +63 -0
  3. checkpoint-1000/generation_config.json +7 -0
  4. checkpoint-1000/model.safetensors +3 -0
  5. checkpoint-1000/optimizer.pt +3 -0
  6. checkpoint-1000/rng_state.pth +3 -0
  7. checkpoint-1000/scheduler.pt +3 -0
  8. checkpoint-1000/tokenizer.json +3 -0
  9. checkpoint-1000/tokenizer_config.json +18 -0
  10. checkpoint-1000/trainer_state.json +174 -0
  11. checkpoint-1000/training_args.bin +3 -0
checkpoint-1000/chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{ '<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ ' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
checkpoint-1000/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": null,
7
+ "dtype": "float32",
8
+ "eos_token_id": null,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 640,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 1536,
13
+ "layer_types": [
14
+ "full_attention",
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
+ "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
+ ],
45
+ "max_position_embeddings": 2048,
46
+ "max_window_layers": 28,
47
+ "model_type": "qwen2",
48
+ "num_attention_heads": 10,
49
+ "num_hidden_layers": 30,
50
+ "num_key_value_heads": 2,
51
+ "pad_token_id": null,
52
+ "rms_norm_eps": 1e-06,
53
+ "rope_parameters": {
54
+ "rope_theta": 100000.0,
55
+ "rope_type": "default"
56
+ },
57
+ "sliding_window": null,
58
+ "tie_word_embeddings": true,
59
+ "transformers_version": "5.0.0",
60
+ "use_cache": false,
61
+ "use_sliding_window": false,
62
+ "vocab_size": 151665
63
+ }
checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "output_attentions": false,
4
+ "output_hidden_states": false,
5
+ "transformers_version": "5.0.0",
6
+ "use_cache": true
7
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949c68f8f18584ed26005ae66e9a31f70eb34d0465503b4b9d7b4c9d8d48fd27
3
+ size 860425256
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587d56499783c6a16988e309ee9e6f8f06dfcee6171f42bb863ce5c2a4490cc0
3
+ size 1721079713
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
3
+ size 14645
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ddd8b81bd93f65a8c6496f3c34318ddf6a7c382d096483dbcc1d427fddd695
3
+ size 1465
checkpoint-1000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
3
+ size 11421892
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>"
11
+ ],
12
+ "is_local": false,
13
+ "model_max_length": 131072,
14
+ "pad_token": "<|endoftext|>",
15
+ "split_special_tokens": false,
16
+ "tokenizer_class": "Qwen2Tokenizer",
17
+ "unk_token": null
18
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.00157153124012575,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 7.85765620062875e-05,
14
+ "grad_norm": 3.4856550693511963,
15
+ "learning_rate": 9.800000000000001e-06,
16
+ "loss": 11.309625244140625,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.000157153124012575,
21
+ "grad_norm": 3.3093955516815186,
22
+ "learning_rate": 1.9800000000000004e-05,
23
+ "loss": 9.846463012695313,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.0002357296860188625,
28
+ "grad_norm": 3.2158353328704834,
29
+ "learning_rate": 2.98e-05,
30
+ "loss": 8.753692626953125,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.00031430624802515,
35
+ "grad_norm": 1.8870658874511719,
36
+ "learning_rate": 3.9800000000000005e-05,
37
+ "loss": 7.157894287109375,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.0003928828100314375,
42
+ "grad_norm": 1.709052562713623,
43
+ "learning_rate": 4.9800000000000004e-05,
44
+ "loss": 5.5407257080078125,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.000471459372037725,
49
+ "grad_norm": 2.6122117042541504,
50
+ "learning_rate": 5.9800000000000003e-05,
51
+ "loss": 4.60130126953125,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.0005500359340440125,
56
+ "grad_norm": 2.101297378540039,
57
+ "learning_rate": 6.98e-05,
58
+ "loss": 4.0536062622070315,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.0006286124960503,
63
+ "grad_norm": 3.6969990730285645,
64
+ "learning_rate": 7.98e-05,
65
+ "loss": 3.595623779296875,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.0007071890580565875,
70
+ "grad_norm": 1.2866711616516113,
71
+ "learning_rate": 8.98e-05,
72
+ "loss": 3.5386227416992186,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.000785765620062875,
77
+ "grad_norm": 1.563516616821289,
78
+ "learning_rate": 9.98e-05,
79
+ "loss": 3.341569519042969,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.0008643421820691625,
84
+ "grad_norm": 1.6755658388137817,
85
+ "learning_rate": 0.00010980000000000001,
86
+ "loss": 3.142231140136719,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.00094291874407545,
91
+ "grad_norm": 1.294084072113037,
92
+ "learning_rate": 0.0001198,
93
+ "loss": 3.1897616577148438,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.0010214953060817375,
98
+ "grad_norm": 1.468405842781067,
99
+ "learning_rate": 0.0001298,
100
+ "loss": 3.0959951782226565,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.001100071868088025,
105
+ "grad_norm": 1.301240086555481,
106
+ "learning_rate": 0.0001398,
107
+ "loss": 2.91419921875,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.0011786484300943124,
112
+ "grad_norm": 1.40414297580719,
113
+ "learning_rate": 0.0001498,
114
+ "loss": 2.933033447265625,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.0012572249921006,
119
+ "grad_norm": 1.468867540359497,
120
+ "learning_rate": 0.0001598,
121
+ "loss": 2.8924459838867187,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.0013358015541068875,
126
+ "grad_norm": 1.293474555015564,
127
+ "learning_rate": 0.0001698,
128
+ "loss": 2.845906982421875,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.001414378116113175,
133
+ "grad_norm": 1.3119351863861084,
134
+ "learning_rate": 0.0001798,
135
+ "loss": 2.829622497558594,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.0014929546781194626,
140
+ "grad_norm": 1.3707680702209473,
141
+ "learning_rate": 0.0001898,
142
+ "loss": 2.864462890625,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.00157153124012575,
147
+ "grad_norm": 1.312740683555603,
148
+ "learning_rate": 0.0001998,
149
+ "loss": 2.6262371826171873,
150
+ "step": 1000
151
+ }
152
+ ],
153
+ "logging_steps": 50,
154
+ "max_steps": 1272646,
155
+ "num_input_tokens_seen": 0,
156
+ "num_train_epochs": 2,
157
+ "save_steps": 1000,
158
+ "stateful_callbacks": {
159
+ "TrainerControl": {
160
+ "args": {
161
+ "should_epoch_stop": false,
162
+ "should_evaluate": false,
163
+ "should_log": false,
164
+ "should_save": true,
165
+ "should_training_stop": false
166
+ },
167
+ "attributes": {}
168
+ }
169
+ },
170
+ "total_flos": 1138722852791040.0,
171
+ "train_batch_size": 1,
172
+ "trial_name": null,
173
+ "trial_params": null
174
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b61c8be48c27ca9fac3df24a8b94cabce7b9b3ee2c05fa8888748079d0ff377f
3
+ size 5137