Hugging Face's logo

tuantmdev
/
0056c078-b3a1-424e-81e4-6de80f79d4d8

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
0056c078-b3a1-424e-81e4-6de80f79d4d8
File size: 4,648 Bytes 
70d2fa5
a581787
 
 
70d2fa5
a581787
70d2fa5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e5726c5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8e31108
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a8477e0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
becd8ac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
447ea82
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1ac461d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a581787
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70d2fa5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a581787
70d2fa5
 
 
 
a581787
70d2fa5
 
 
 
 
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
185
 
{
  "best_metric": 0.4624326527118683,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.031939634091566936,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.984908522891735e-05,
      "eval_loss": 2.0086100101470947,
      "eval_runtime": 702.0595,
      "eval_samples_per_second": 15.023,
      "eval_steps_per_second": 7.512,
      "step": 1
    },
    {
      "epoch": 0.003193963409156694,
      "grad_norm": 60.47791290283203,
      "learning_rate": 5e-05,
      "loss": 8.1173,
      "step": 40
    },
    {
      "epoch": 0.003992454261445867,
      "eval_loss": 0.7402405142784119,
      "eval_runtime": 703.0805,
      "eval_samples_per_second": 15.001,
      "eval_steps_per_second": 7.501,
      "step": 50
    },
    {
      "epoch": 0.006387926818313388,
      "grad_norm": 37.602317810058594,
      "learning_rate": 0.0001,
      "loss": 5.2458,
      "step": 80
    },
    {
      "epoch": 0.007984908522891734,
      "eval_loss": 0.645350456237793,
      "eval_runtime": 703.8766,
      "eval_samples_per_second": 14.984,
      "eval_steps_per_second": 7.493,
      "step": 100
    },
    {
      "epoch": 0.009581890227470082,
      "grad_norm": 35.46270751953125,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.8448,
      "step": 120
    },
    {
      "epoch": 0.011977362784337602,
      "eval_loss": 0.6013292670249939,
      "eval_runtime": 703.7908,
      "eval_samples_per_second": 14.986,
      "eval_steps_per_second": 7.494,
      "step": 150
    },
    {
      "epoch": 0.012775853636626776,
      "grad_norm": 19.138328552246094,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.5843,
      "step": 160
    },
    {
      "epoch": 0.015969817045783468,
      "grad_norm": 44.18806838989258,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.4517,
      "step": 200
    },
    {
      "epoch": 0.015969817045783468,
      "eval_loss": 0.5775735974311829,
      "eval_runtime": 704.1932,
      "eval_samples_per_second": 14.977,
      "eval_steps_per_second": 7.489,
      "step": 200
    },
    {
      "epoch": 0.019163780454940164,
      "grad_norm": 28.21241569519043,
      "learning_rate": 5e-05,
      "loss": 4.1189,
      "step": 240
    },
    {
      "epoch": 0.019962271307229336,
      "eval_loss": 0.520143449306488,
      "eval_runtime": 704.7521,
      "eval_samples_per_second": 14.966,
      "eval_steps_per_second": 7.483,
      "step": 250
    },
    {
      "epoch": 0.022357743864096856,
      "grad_norm": 24.794347763061523,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.9716,
      "step": 280
    },
    {
      "epoch": 0.023954725568675204,
      "eval_loss": 0.4819493889808655,
      "eval_runtime": 704.0197,
      "eval_samples_per_second": 14.981,
      "eval_steps_per_second": 7.491,
      "step": 300
    },
    {
      "epoch": 0.02555170727325355,
      "grad_norm": 17.22718048095703,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.8944,
      "step": 320
    },
    {
      "epoch": 0.02794717983012107,
      "eval_loss": 0.4660003185272217,
      "eval_runtime": 703.3672,
      "eval_samples_per_second": 14.995,
      "eval_steps_per_second": 7.498,
      "step": 350
    },
    {
      "epoch": 0.028745670682410244,
      "grad_norm": 17.49160385131836,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.8966,
      "step": 360
    },
    {
      "epoch": 0.031939634091566936,
      "grad_norm": 32.967838287353516,
      "learning_rate": 0.0,
      "loss": 3.5671,
      "step": 400
    },
    {
      "epoch": 0.031939634091566936,
      "eval_loss": 0.4624326527118683,
      "eval_runtime": 702.7683,
      "eval_samples_per_second": 15.008,
      "eval_steps_per_second": 7.505,
      "step": 400
    }
  ],
  "logging_steps": 40,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 1.4149473674880614e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}