Hugging Face's logo

tuanna08go
/
2ef1e1a4-26ca-421b-88f2-e27390147b1d

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
2ef1e1a4-26ca-421b-88f2-e27390147b1d
File size: 3,697 Bytes
a8c7dde
 
 
6312b1d
376c4da
6312b1d
a8c7dde
 
 
 
 
 
 
376c4da
 
 
a8c7dde
376c4da
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
faa147e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
589fa83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6312b1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a8c7dde
 
 
376c4da
a8c7dde
 
376c4da
a8c7dde
 
 
 
 
 
 
6312b1d
a8c7dde
 
 
 
6312b1d
a8c7dde
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11461318051575932,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002292263610315186,
      "eval_loss": 0.6850675344467163,
      "eval_runtime": 32.1049,
      "eval_samples_per_second": 5.731,
      "eval_steps_per_second": 2.866,
      "step": 1
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 8.41812801361084,
      "learning_rate": 5e-05,
      "loss": 2.6706,
      "step": 5
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 6.175701141357422,
      "learning_rate": 0.0001,
      "loss": 2.3579,
      "step": 10
    },
    {
      "epoch": 0.022922636103151862,
      "eval_loss": 0.5222229957580566,
      "eval_runtime": 34.3718,
      "eval_samples_per_second": 5.353,
      "eval_steps_per_second": 2.677,
      "step": 10
    },
    {
      "epoch": 0.034383954154727794,
      "grad_norm": 4.626423358917236,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.0376,
      "step": 15
    },
    {
      "epoch": 0.045845272206303724,
      "grad_norm": 4.920547008514404,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.7548,
      "step": 20
    },
    {
      "epoch": 0.045845272206303724,
      "eval_loss": 0.4074614942073822,
      "eval_runtime": 35.1925,
      "eval_samples_per_second": 5.228,
      "eval_steps_per_second": 2.614,
      "step": 20
    },
    {
      "epoch": 0.05730659025787966,
      "grad_norm": 4.158402919769287,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.5327,
      "step": 25
    },
    {
      "epoch": 0.06876790830945559,
      "grad_norm": 4.287597179412842,
      "learning_rate": 5e-05,
      "loss": 1.3894,
      "step": 30
    },
    {
      "epoch": 0.06876790830945559,
      "eval_loss": 0.37142413854599,
      "eval_runtime": 35.3436,
      "eval_samples_per_second": 5.206,
      "eval_steps_per_second": 2.603,
      "step": 30
    },
    {
      "epoch": 0.08022922636103152,
      "grad_norm": 3.6002652645111084,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.454,
      "step": 35
    },
    {
      "epoch": 0.09169054441260745,
      "grad_norm": 3.943558931350708,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.4878,
      "step": 40
    },
    {
      "epoch": 0.09169054441260745,
      "eval_loss": 0.3554995059967041,
      "eval_runtime": 35.3678,
      "eval_samples_per_second": 5.202,
      "eval_steps_per_second": 2.601,
      "step": 40
    },
    {
      "epoch": 0.10315186246418338,
      "grad_norm": 4.879668712615967,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.4834,
      "step": 45
    },
    {
      "epoch": 0.11461318051575932,
      "grad_norm": 3.6490864753723145,
      "learning_rate": 0.0,
      "loss": 1.5293,
      "step": 50
    },
    {
      "epoch": 0.11461318051575932,
      "eval_loss": 0.3512641191482544,
      "eval_runtime": 35.4018,
      "eval_samples_per_second": 5.197,
      "eval_steps_per_second": 2.599,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.75267179921408e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}