Hugging Face's logo

tuanna08go
/
48b075d3-1d5c-4bb5-955f-d82665432ab7

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
48b075d3-1d5c-4bb5-955f-d82665432ab7
File size: 3,736 Bytes 
18743d4
 
 
cbab22d
3ee1b5d
cbab22d
18743d4
 
 
 
 
 
 
3ee1b5d
 
 
18743d4
3ee1b5d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3487f28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a53ee0c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cbab22d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18743d4
 
 
3ee1b5d
18743d4
 
3ee1b5d
18743d4
 
 
 
 
 
 
cbab22d
18743d4
 
 
 
cbab22d
18743d4
 
 
 
 
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": 0.0014116019564803116,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8232039129606233e-05,
      "eval_loss": 1.372756004333496,
      "eval_runtime": 1295.716,
      "eval_samples_per_second": 11.511,
      "eval_steps_per_second": 5.756,
      "step": 1
    },
    {
      "epoch": 0.00014116019564803118,
      "grad_norm": 9.01905632019043,
      "learning_rate": 5e-05,
      "loss": 5.2824,
      "step": 5
    },
    {
      "epoch": 0.00028232039129606236,
      "grad_norm": 6.25973653793335,
      "learning_rate": 0.0001,
      "loss": 4.8007,
      "step": 10
    },
    {
      "epoch": 0.00028232039129606236,
      "eval_loss": 1.1299453973770142,
      "eval_runtime": 1315.7538,
      "eval_samples_per_second": 11.336,
      "eval_steps_per_second": 5.668,
      "step": 10
    },
    {
      "epoch": 0.0004234805869440935,
      "grad_norm": 6.059873104095459,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.3526,
      "step": 15
    },
    {
      "epoch": 0.0005646407825921247,
      "grad_norm": 6.142041206359863,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.131,
      "step": 20
    },
    {
      "epoch": 0.0005646407825921247,
      "eval_loss": 0.9743238091468811,
      "eval_runtime": 1313.8488,
      "eval_samples_per_second": 11.352,
      "eval_steps_per_second": 5.676,
      "step": 20
    },
    {
      "epoch": 0.0007058009782401558,
      "grad_norm": 6.113480567932129,
      "learning_rate": 6.91341716182545e-05,
      "loss": 4.1495,
      "step": 25
    },
    {
      "epoch": 0.000846961173888187,
      "grad_norm": 5.63142728805542,
      "learning_rate": 5e-05,
      "loss": 3.5645,
      "step": 30
    },
    {
      "epoch": 0.000846961173888187,
      "eval_loss": 0.9139702916145325,
      "eval_runtime": 1315.7943,
      "eval_samples_per_second": 11.335,
      "eval_steps_per_second": 5.668,
      "step": 30
    },
    {
      "epoch": 0.0009881213695362183,
      "grad_norm": 5.424609184265137,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.5494,
      "step": 35
    },
    {
      "epoch": 0.0011292815651842494,
      "grad_norm": 5.923633098602295,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.5106,
      "step": 40
    },
    {
      "epoch": 0.0011292815651842494,
      "eval_loss": 0.8934321403503418,
      "eval_runtime": 1315.4296,
      "eval_samples_per_second": 11.339,
      "eval_steps_per_second": 5.67,
      "step": 40
    },
    {
      "epoch": 0.0012704417608322806,
      "grad_norm": 6.608625411987305,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.7016,
      "step": 45
    },
    {
      "epoch": 0.0014116019564803116,
      "grad_norm": 5.440760135650635,
      "learning_rate": 0.0,
      "loss": 3.3832,
      "step": 50
    },
    {
      "epoch": 0.0014116019564803116,
      "eval_loss": 0.8904063701629639,
      "eval_runtime": 1315.2003,
      "eval_samples_per_second": 11.34,
      "eval_steps_per_second": 5.671,
      "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": 8763348929740800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}