Hugging Face's logo

havinash-ai
/
5007fede-9ccf-4240-b8fc-b7330e584e68

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
5007fede-9ccf-4240-b8fc-b7330e584e68
File size: 2,962 Bytes 
9126586
 
 
be9ce86
9126586
be9ce86
9126586
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ff8df2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
09c1b22
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
be9ce86
 
 
 
 
 
 
9126586
 
 
 
 
 
 
 
 
 
 
 
 
 
be9ce86
9126586
 
 
 
be9ce86
9126586
 
 
 
 
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": 0.22346368715083798,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0223463687150838,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 5.2067,
      "step": 1
    },
    {
      "epoch": 0.0223463687150838,
      "eval_loss": NaN,
      "eval_runtime": 1.7616,
      "eval_samples_per_second": 10.786,
      "eval_steps_per_second": 5.677,
      "step": 1
    },
    {
      "epoch": 0.0446927374301676,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 2.0659,
      "step": 2
    },
    {
      "epoch": 0.0670391061452514,
      "grad_norm": 34.9081916809082,
      "learning_rate": 6e-05,
      "loss": 5.7547,
      "step": 3
    },
    {
      "epoch": 0.0670391061452514,
      "eval_loss": NaN,
      "eval_runtime": 0.6218,
      "eval_samples_per_second": 30.558,
      "eval_steps_per_second": 16.083,
      "step": 3
    },
    {
      "epoch": 0.0893854748603352,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 3.7165,
      "step": 4
    },
    {
      "epoch": 0.11173184357541899,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.1340782122905028,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.1340782122905028,
      "eval_loss": NaN,
      "eval_runtime": 0.6099,
      "eval_samples_per_second": 31.155,
      "eval_steps_per_second": 16.397,
      "step": 6
    },
    {
      "epoch": 0.1564245810055866,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 14.8844,
      "step": 7
    },
    {
      "epoch": 0.1787709497206704,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 10.7419,
      "step": 8
    },
    {
      "epoch": 0.2011173184357542,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 4.075,
      "step": 9
    },
    {
      "epoch": 0.2011173184357542,
      "eval_loss": NaN,
      "eval_runtime": 0.6168,
      "eval_samples_per_second": 30.803,
      "eval_steps_per_second": 16.212,
      "step": 9
    },
    {
      "epoch": 0.22346368715083798,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 9.1604,
      "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": 1796486530596864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}