Hugging Face's logo

dada22231
/
ee9c4f6d-84fb-4aa5-b47f-d71bef4dce71

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
ee9c4f6d-84fb-4aa5-b47f-d71bef4dce71
File size: 4,457 Bytes 
55db380
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0707070707070705,
  "eval_steps": 25,
  "global_step": 19,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16161616161616163,
      "grad_norm": 0.09301000088453293,
      "learning_rate": 9.938625865312251e-05,
      "loss": 11.9178,
      "step": 1
    },
    {
      "epoch": 0.16161616161616163,
      "eval_loss": 11.918818473815918,
      "eval_runtime": 0.1799,
      "eval_samples_per_second": 277.913,
      "eval_steps_per_second": 72.257,
      "step": 1
    },
    {
      "epoch": 0.32323232323232326,
      "grad_norm": 0.08993229269981384,
      "learning_rate": 9.756177587652856e-05,
      "loss": 11.9332,
      "step": 2
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.09598046541213989,
      "learning_rate": 9.4576318804292e-05,
      "loss": 11.9288,
      "step": 3
    },
    {
      "epoch": 0.6464646464646465,
      "grad_norm": 0.08898554742336273,
      "learning_rate": 9.051132292283771e-05,
      "loss": 11.9247,
      "step": 4
    },
    {
      "epoch": 0.8080808080808081,
      "grad_norm": 0.09454613924026489,
      "learning_rate": 8.547767072315835e-05,
      "loss": 11.9268,
      "step": 5
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.09586441516876221,
      "learning_rate": 7.961266711550922e-05,
      "loss": 11.9283,
      "step": 6
    },
    {
      "epoch": 1.1313131313131313,
      "grad_norm": 0.1707533448934555,
      "learning_rate": 7.307629410938363e-05,
      "loss": 21.6072,
      "step": 7
    },
    {
      "epoch": 1.2929292929292928,
      "grad_norm": 0.1111416220664978,
      "learning_rate": 6.604684692133597e-05,
      "loss": 11.9247,
      "step": 8
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 0.10647398978471756,
      "learning_rate": 5.8716070546254966e-05,
      "loss": 11.926,
      "step": 9
    },
    {
      "epoch": 1.6161616161616161,
      "grad_norm": 0.09251272678375244,
      "learning_rate": 5.128392945374505e-05,
      "loss": 11.9237,
      "step": 10
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.11217524856328964,
      "learning_rate": 4.395315307866405e-05,
      "loss": 11.929,
      "step": 11
    },
    {
      "epoch": 1.9393939393939394,
      "grad_norm": 0.10548664629459381,
      "learning_rate": 3.692370589061639e-05,
      "loss": 11.9278,
      "step": 12
    },
    {
      "epoch": 2.101010101010101,
      "grad_norm": 0.18034182488918304,
      "learning_rate": 3.0387332884490805e-05,
      "loss": 21.6047,
      "step": 13
    },
    {
      "epoch": 2.2626262626262625,
      "grad_norm": 0.10867207497358322,
      "learning_rate": 2.4522329276841663e-05,
      "loss": 11.9184,
      "step": 14
    },
    {
      "epoch": 2.4242424242424243,
      "grad_norm": 0.1145796999335289,
      "learning_rate": 1.9488677077162295e-05,
      "loss": 11.925,
      "step": 15
    },
    {
      "epoch": 2.5858585858585856,
      "grad_norm": 0.10127127915620804,
      "learning_rate": 1.5423681195707997e-05,
      "loss": 11.9233,
      "step": 16
    },
    {
      "epoch": 2.7474747474747474,
      "grad_norm": 0.11140892654657364,
      "learning_rate": 1.2438224123471442e-05,
      "loss": 11.9234,
      "step": 17
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 0.12017859518527985,
      "learning_rate": 1.0613741346877497e-05,
      "loss": 11.926,
      "step": 18
    },
    {
      "epoch": 3.0707070707070705,
      "grad_norm": 0.2055111676454544,
      "learning_rate": 1e-05,
      "loss": 21.6089,
      "step": 19
    }
  ],
  "logging_steps": 1,
  "max_steps": 19,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 396147818496.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}