Hugging Face's logo

SystemAdmin123
/
Qwen2.5-1.5B

Safetensors
qwen2
Model card Files
xet
 Community
SystemAdmin123 commited on
Commit
862ab00
·
verified ·
1 Parent(s): f81f278

Training in progress, step 200, checkpoint

Browse files
Files changed (17) hide show
  1. last-checkpoint/added_tokens.json +24 -0
  2. last-checkpoint/config.json +31 -0
  3. last-checkpoint/generation_config.json +9 -0
  4. last-checkpoint/merges.txt +0 -0
  5. last-checkpoint/model.safetensors +3 -0
  6. last-checkpoint/optimizer.pt +3 -0
  7. last-checkpoint/rng_state_0.pth +3 -0
  8. last-checkpoint/rng_state_1.pth +3 -0
  9. last-checkpoint/rng_state_2.pth +3 -0
  10. last-checkpoint/rng_state_3.pth +3 -0
  11. last-checkpoint/scheduler.pt +3 -0
  12. last-checkpoint/special_tokens_map.json +31 -0
  13. last-checkpoint/tokenizer.json +3 -0
  14. last-checkpoint/tokenizer_config.json +210 -0
  15. last-checkpoint/trainer_state.json +189 -0
  16. last-checkpoint/training_args.bin +3 -0
  17. last-checkpoint/vocab.json +0 -0
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "unsloth/Qwen2.5-1.5B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
12
+ "max_position_embeddings": 32768,
13
+ "max_window_layers": 28,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 12,
16
+ "num_hidden_layers": 28,
17
+ "num_key_value_heads": 2,
18
+ "pad_token_id": 151654,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 1000000.0,
22
+ "sliding_window": null,
23
+ "tie_word_embeddings": true,
24
+ "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.48.1",
26
+ "unsloth_fixed": true,
27
+ "use_cache": false,
28
+ "use_mrope": false,
29
+ "use_sliding_window": false,
30
+ "vocab_size": 151665
31
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": 151643,
5
+ "max_length": 32768,
6
+ "max_new_tokens": 2048,
7
+ "pad_token_id": 151654,
8
+ "transformers_version": "4.48.1"
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 sha256:615b566772d65b23541c4b22f49a2250917350f7419552b587af9efea7f40f67
3
+ size 3086634632
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e391882f6ffdfdd4e3d8c94908cafaca5ba5efa3cb699f28b7ffd8ff415eb53c
3
+ size 3136004290
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f2762d792d815ec78151cdfb1183ff8fe6b1a4c5fcc050ac87b15dc66050802
3
+ size 15024
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc1f875219f8ac3c776408d86b647fbc8462ad7ecb23ac468a078c2c50ec46e
3
+ size 15024
last-checkpoint/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbcdba7bc63bee2e58552ca3df8d3d9521da29d066231bf49913479cc60a05a4
3
+ size 15024
last-checkpoint/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac162cf8f57eb46f3e3f12f50328cd5574b5384b6fe27493b80f0979cc8d636b
3
+ size 15024
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abcd078b1186023c3032f4652f953246e76b5f62233ca3f894e881ea9feb17b7
3
+ size 1064
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|vision_pad|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
last-checkpoint/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
3
+ size 11421896
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,210 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response: ' + message['content'] + eos_token}}{% endif %}{% endfor %}",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|endoftext|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "model_max_length": 32768,
204
+ "pad_token": "<|vision_pad|>",
205
+ "padding_side": "left",
206
+ "split_special_tokens": false,
207
+ "tokenizer_class": "Qwen2Tokenizer",
208
+ "unk_token": null,
209
+ "use_fast": true
210
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 11.11111111111111,
5
+ "eval_steps": 200,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05555555555555555,
13
+ "eval_loss": 2.2965798377990723,
14
+ "eval_runtime": 19.5242,
15
+ "eval_samples_per_second": 76.879,
16
+ "eval_steps_per_second": 1.946,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.5555555555555556,
21
+ "grad_norm": 1.171875,
22
+ "learning_rate": 0.0001,
23
+ "loss": 2.0385,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 1.1111111111111112,
28
+ "grad_norm": 1.421875,
29
+ "learning_rate": 0.0002,
30
+ "loss": 1.9132,
31
+ "step": 20
32
+ },
33
+ {
34
+ "epoch": 1.6666666666666665,
35
+ "grad_norm": 1.421875,
36
+ "learning_rate": 0.000199658449300667,
37
+ "loss": 1.4827,
38
+ "step": 30
39
+ },
40
+ {
41
+ "epoch": 2.2222222222222223,
42
+ "grad_norm": 1.484375,
43
+ "learning_rate": 0.00019863613034027224,
44
+ "loss": 1.2376,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 2.7777777777777777,
49
+ "grad_norm": 1.1875,
50
+ "learning_rate": 0.00019694002659393305,
51
+ "loss": 0.835,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 3.3333333333333335,
56
+ "grad_norm": 1.09375,
57
+ "learning_rate": 0.00019458172417006347,
58
+ "loss": 0.5645,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 3.888888888888889,
63
+ "grad_norm": 2.53125,
64
+ "learning_rate": 0.00019157733266550575,
65
+ "loss": 0.4031,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 4.444444444444445,
70
+ "grad_norm": 0.7421875,
71
+ "learning_rate": 0.0001879473751206489,
72
+ "loss": 0.2343,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 5.0,
77
+ "grad_norm": 0.73828125,
78
+ "learning_rate": 0.00018371664782625287,
79
+ "loss": 0.1911,
80
+ "step": 90
81
+ },
82
+ {
83
+ "epoch": 5.555555555555555,
84
+ "grad_norm": 0.52734375,
85
+ "learning_rate": 0.00017891405093963938,
86
+ "loss": 0.0841,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 6.111111111111111,
91
+ "grad_norm": 0.296875,
92
+ "learning_rate": 0.00017357239106731317,
93
+ "loss": 0.0856,
94
+ "step": 110
95
+ },
96
+ {
97
+ "epoch": 6.666666666666667,
98
+ "grad_norm": 0.361328125,
99
+ "learning_rate": 0.00016772815716257412,
100
+ "loss": 0.0351,
101
+ "step": 120
102
+ },
103
+ {
104
+ "epoch": 7.222222222222222,
105
+ "grad_norm": 0.1669921875,
106
+ "learning_rate": 0.0001614212712689668,
107
+ "loss": 0.0268,
108
+ "step": 130
109
+ },
110
+ {
111
+ "epoch": 7.777777777777778,
112
+ "grad_norm": 0.171875,
113
+ "learning_rate": 0.00015469481581224272,
114
+ "loss": 0.0119,
115
+ "step": 140
116
+ },
117
+ {
118
+ "epoch": 8.333333333333334,
119
+ "grad_norm": 0.11328125,
120
+ "learning_rate": 0.00014759473930370736,
121
+ "loss": 0.0089,
122
+ "step": 150
123
+ },
124
+ {
125
+ "epoch": 8.88888888888889,
126
+ "grad_norm": 0.115234375,
127
+ "learning_rate": 0.00014016954246529696,
128
+ "loss": 0.0049,
129
+ "step": 160
130
+ },
131
+ {
132
+ "epoch": 9.444444444444445,
133
+ "grad_norm": 0.056884765625,
134
+ "learning_rate": 0.00013246994692046836,
135
+ "loss": 0.0036,
136
+ "step": 170
137
+ },
138
+ {
139
+ "epoch": 10.0,
140
+ "grad_norm": 0.037841796875,
141
+ "learning_rate": 0.00012454854871407994,
142
+ "loss": 0.0029,
143
+ "step": 180
144
+ },
145
+ {
146
+ "epoch": 10.555555555555555,
147
+ "grad_norm": 0.052978515625,
148
+ "learning_rate": 0.00011645945902807341,
149
+ "loss": 0.0027,
150
+ "step": 190
151
+ },
152
+ {
153
+ "epoch": 11.11111111111111,
154
+ "grad_norm": 0.03271484375,
155
+ "learning_rate": 0.00010825793454723325,
156
+ "loss": 0.0026,
157
+ "step": 200
158
+ },
159
+ {
160
+ "epoch": 11.11111111111111,
161
+ "eval_loss": 4.137510776519775,
162
+ "eval_runtime": 17.9093,
163
+ "eval_samples_per_second": 83.811,
164
+ "eval_steps_per_second": 2.122,
165
+ "step": 200
166
+ }
167
+ ],
168
+ "logging_steps": 10,
169
+ "max_steps": 400,
170
+ "num_input_tokens_seen": 0,
171
+ "num_train_epochs": 23,
172
+ "save_steps": 200,
173
+ "stateful_callbacks": {
174
+ "TrainerControl": {
175
+ "args": {
176
+ "should_epoch_stop": false,
177
+ "should_evaluate": false,
178
+ "should_log": false,
179
+ "should_save": true,
180
+ "should_training_stop": false
181
+ },
182
+ "attributes": {}
183
+ }
184
+ },
185
+ "total_flos": 1.2881172782645248e+17,
186
+ "train_batch_size": 10,
187
+ "trial_name": null,
188
+ "trial_params": null
189
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d53c840437a49402552cf42d45aa528cd3e540fe038280633a493abeb3e0556
3
+ size 6840
last-checkpoint/vocab.json ADDED
The diff for this file is too large to render. See raw diff