Hugging Face's logo

mveroe
/
Qwen2.5-1.5B_lightr1_3_EN_1024_1p0_0p0_1p0_sft

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
mveroe commited on
Commit
78cbb92
·
verified ·
1 Parent(s): 0cefb09

Training in progress, epoch 1, checkpoint

Browse files
Files changed (11) hide show
  1. checkpoint-21/config.json +59 -0
  2. checkpoint-21/generation_config.json +6 -0
  3. checkpoint-21/model.safetensors +3 -0
  4. checkpoint-21/optimizer.pt +3 -0
  5. checkpoint-21/rng_state_0.pth +3 -0
  6. checkpoint-21/rng_state_1.pth +3 -0
  7. checkpoint-21/rng_state_2.pth +3 -0
  8. checkpoint-21/rng_state_3.pth +3 -0
  9. checkpoint-21/scheduler.pt +3 -0
  10. checkpoint-21/trainer_state.json +181 -0
  11. checkpoint-21/training_args.bin +3 -0
checkpoint-21/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1536,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8960,
12
+ "layer_types": [
13
+ "full_attention",
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
+ ],
42
+ "max_position_embeddings": 131072,
43
+ "max_window_layers": 28,
44
+ "model_type": "qwen2",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 28,
47
+ "num_key_value_heads": 2,
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": null,
50
+ "rope_theta": 1000000.0,
51
+ "sliding_window": null,
52
+ "tie_word_embeddings": true,
53
+ "torch_dtype": "bfloat16",
54
+ "transformers_version": "4.55.2",
55
+ "use_cache": true,
56
+ "use_mrope": false,
57
+ "use_sliding_window": false,
58
+ "vocab_size": 151667
59
+ }
checkpoint-21/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.55.2"
6
+ }
checkpoint-21/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c74ad5b283dd0f658cafa4d578a3bbcb4f25dcd809c4cb9003deb2359130ac1
3
+ size 3086640776
checkpoint-21/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b13dcd75ad277f8235be9d791062a9d73b8e21ec4100c87c9f559541a131b3
3
+ size 6056331
checkpoint-21/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed69d3ae118d797e33700fb938c2b3082fd9d43cc793829f446fd120f845714b
3
+ size 15365
checkpoint-21/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86accf27064cdd503053e90476a6bd10de333d4ff0594535ad55ea13a473c91d
3
+ size 15429
checkpoint-21/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca8d714ef40be035404c1957b5a4dee84e1f43980408393f8aa710552ee6f6
3
+ size 15429
checkpoint-21/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfdebe99e40accc9c9d8f09c63136a14abda997d9b501969ec8e16e9d183179
3
+ size 15429
checkpoint-21/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44beb602faaa18f6149ebc281880bf809c7972ab1d9b2e5653a5962d3a3930c7
3
+ size 1465
checkpoint-21/trainer_state.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 21,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.04878048780487805,
14
+ "grad_norm": 126.0,
15
+ "learning_rate": 0.0,
16
+ "loss": 6.3712,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0975609756097561,
21
+ "grad_norm": 139.0,
22
+ "learning_rate": 7.142857142857143e-06,
23
+ "loss": 6.9747,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.14634146341463414,
28
+ "grad_norm": 141.0,
29
+ "learning_rate": 1.4285714285714285e-05,
30
+ "loss": 7.2169,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.1951219512195122,
35
+ "grad_norm": 135.0,
36
+ "learning_rate": 2.1428571428571428e-05,
37
+ "loss": 6.3792,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.24390243902439024,
42
+ "grad_norm": 356.0,
43
+ "learning_rate": 2.857142857142857e-05,
44
+ "loss": 5.1872,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.2926829268292683,
49
+ "grad_norm": 158.0,
50
+ "learning_rate": 3.571428571428572e-05,
51
+ "loss": 5.7681,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.34146341463414637,
56
+ "grad_norm": 149.0,
57
+ "learning_rate": 4.2857142857142856e-05,
58
+ "loss": 4.4005,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.3902439024390244,
63
+ "grad_norm": 134.0,
64
+ "learning_rate": 5e-05,
65
+ "loss": 5.056,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.43902439024390244,
70
+ "grad_norm": 94.5,
71
+ "learning_rate": 4.996067037544542e-05,
72
+ "loss": 4.2935,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.4878048780487805,
77
+ "grad_norm": 212.0,
78
+ "learning_rate": 4.984280524733107e-05,
79
+ "loss": 8.9937,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.5365853658536586,
84
+ "grad_norm": 302.0,
85
+ "learning_rate": 4.96467754629559e-05,
86
+ "loss": 4.9127,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.5853658536585366,
91
+ "grad_norm": 44.5,
92
+ "learning_rate": 4.937319780454559e-05,
93
+ "loss": 4.4251,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.6341463414634146,
98
+ "grad_norm": 39.25,
99
+ "learning_rate": 4.9022933048627496e-05,
100
+ "loss": 3.6691,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.6829268292682927,
105
+ "grad_norm": 31.25,
106
+ "learning_rate": 4.8597083257709194e-05,
107
+ "loss": 3.232,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.7317073170731707,
112
+ "grad_norm": 44.25,
113
+ "learning_rate": 4.8096988312782174e-05,
114
+ "loss": 3.1154,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.7804878048780488,
119
+ "grad_norm": 43.75,
120
+ "learning_rate": 4.752422169756048e-05,
121
+ "loss": 2.6809,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.8292682926829268,
126
+ "grad_norm": 41.0,
127
+ "learning_rate": 4.6880585547718845e-05,
128
+ "loss": 2.1384,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.8780487804878049,
133
+ "grad_norm": 50.0,
134
+ "learning_rate": 4.6168104980707107e-05,
135
+ "loss": 2.0084,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.926829268292683,
140
+ "grad_norm": 48.25,
141
+ "learning_rate": 4.538902172398151e-05,
142
+ "loss": 1.8335,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.975609756097561,
147
+ "grad_norm": 50.0,
148
+ "learning_rate": 4.454578706170075e-05,
149
+ "loss": 1.6659,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 1.0,
154
+ "grad_norm": 50.75,
155
+ "learning_rate": 4.364105412207914e-05,
156
+ "loss": 1.5889,
157
+ "step": 21
158
+ }
159
+ ],
160
+ "logging_steps": 1,
161
+ "max_steps": 63,
162
+ "num_input_tokens_seen": 0,
163
+ "num_train_epochs": 3,
164
+ "save_steps": 500,
165
+ "stateful_callbacks": {
166
+ "TrainerControl": {
167
+ "args": {
168
+ "should_epoch_stop": false,
169
+ "should_evaluate": false,
170
+ "should_log": false,
171
+ "should_save": true,
172
+ "should_training_stop": false
173
+ },
174
+ "attributes": {}
175
+ }
176
+ },
177
+ "total_flos": 1.0562561296564224e+16,
178
+ "train_batch_size": 4,
179
+ "trial_name": null,
180
+ "trial_params": null
181
+ }
checkpoint-21/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:807175855d5dd743e81254531a1a0148b2ade3b9521c50fa1999cea9a77e0a70
3
+ size 5969