Hugging Face's logo

duyphu
/
1818ba1a-8418-467f-80bd-d9c0d35c0b89

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
1818ba1a-8418-467f-80bd-d9c0d35c0b89
File size: 3,502 Bytes 
3b6147c
 
 
8ad622a
b842a2d
8ad622a
3b6147c
 
 
 
 
 
 
b842a2d
 
 
3b6147c
b842a2d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6528514
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13fdcbe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8ad622a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3b6147c
 
 
b842a2d
3b6147c
 
b842a2d
3b6147c
 
 
 
 
 
 
8ad622a
3b6147c
 
 
 
8ad622a
3b6147c
 
 
 
 
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": 0.0007661250162801566,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5322500325603132e-05,
      "eval_loss": NaN,
      "eval_runtime": 1265.0534,
      "eval_samples_per_second": 21.722,
      "eval_steps_per_second": 10.861,
      "step": 1
    },
    {
      "epoch": 7.661250162801566e-05,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 29.8212,
      "step": 5
    },
    {
      "epoch": 0.00015322500325603132,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00015322500325603132,
      "eval_loss": NaN,
      "eval_runtime": 1265.6774,
      "eval_samples_per_second": 21.712,
      "eval_steps_per_second": 10.856,
      "step": 10
    },
    {
      "epoch": 0.00022983750488404697,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00030645000651206264,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.00030645000651206264,
      "eval_loss": NaN,
      "eval_runtime": 1269.5948,
      "eval_samples_per_second": 21.645,
      "eval_steps_per_second": 10.822,
      "step": 20
    },
    {
      "epoch": 0.0003830625081400783,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 8.4151,
      "step": 25
    },
    {
      "epoch": 0.00045967500976809393,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.00045967500976809393,
      "eval_loss": NaN,
      "eval_runtime": 1268.5609,
      "eval_samples_per_second": 21.662,
      "eval_steps_per_second": 10.831,
      "step": 30
    },
    {
      "epoch": 0.0005362875113961096,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0006129000130241253,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0006129000130241253,
      "eval_loss": NaN,
      "eval_runtime": 1265.8644,
      "eval_samples_per_second": 21.708,
      "eval_steps_per_second": 10.854,
      "step": 40
    },
    {
      "epoch": 0.000689512514652141,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0007661250162801566,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0007661250162801566,
      "eval_loss": NaN,
      "eval_runtime": 1266.8065,
      "eval_samples_per_second": 21.692,
      "eval_steps_per_second": 10.846,
      "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": 5281565890314240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}