Hugging Face's logo

ClarenceDan
/
50b56d67-5eb8-476b-bb9b-3f66c992fe95

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
50b56d67-5eb8-476b-bb9b-3f66c992fe95
File size: 2,931 Bytes 
92cc007
 
 
5ae078b
92cc007
5ae078b
92cc007
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
507696f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1219b59
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5ae078b
 
 
 
 
 
 
92cc007
 
 
 
 
 
 
 
 
 
 
 
 
 
5ae078b
92cc007
 
 
 
5ae078b
92cc007
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.33613445378151263,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03361344537815126,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.03361344537815126,
      "eval_loss": NaN,
      "eval_runtime": 1.4347,
      "eval_samples_per_second": 9.061,
      "eval_steps_per_second": 4.879,
      "step": 1
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.10084033613445378,
      "eval_loss": NaN,
      "eval_runtime": 0.4297,
      "eval_samples_per_second": 30.257,
      "eval_steps_per_second": 16.292,
      "step": 3
    },
    {
      "epoch": 0.13445378151260504,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.20168067226890757,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.20168067226890757,
      "eval_loss": NaN,
      "eval_runtime": 0.4283,
      "eval_samples_per_second": 30.349,
      "eval_steps_per_second": 16.342,
      "step": 6
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.2689075630252101,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.3025210084033613,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.3025210084033613,
      "eval_loss": NaN,
      "eval_runtime": 0.4279,
      "eval_samples_per_second": 30.38,
      "eval_steps_per_second": 16.358,
      "step": 9
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1768546400993280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}