Hugging Face's logo

trenden
/
82f50e97-57ee-4635-979c-e50a2900476e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
82f50e97-57ee-4635-979c-e50a2900476e
File size: 3,080 Bytes 
dc5527b
 
 
d9de5c6
dc5527b
d9de5c6
dc5527b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ec92784
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
af1cdeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d9de5c6
 
 
 
 
 
 
dc5527b
 
 
 
 
 
 
 
 
 
 
 
 
 
d9de5c6
dc5527b
 
 
 
d9de5c6
dc5527b
 
 
 
 
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": 0.0014697776961234614,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014697776961234614,
      "grad_norm": 0.10356643795967102,
      "learning_rate": 2e-05,
      "loss": 0.6371,
      "step": 1
    },
    {
      "epoch": 0.00014697776961234614,
      "eval_loss": NaN,
      "eval_runtime": 249.1633,
      "eval_samples_per_second": 11.498,
      "eval_steps_per_second": 5.751,
      "step": 1
    },
    {
      "epoch": 0.0002939555392246923,
      "grad_norm": 0.10245563089847565,
      "learning_rate": 4e-05,
      "loss": 0.6506,
      "step": 2
    },
    {
      "epoch": 0.0004409333088370384,
      "grad_norm": 0.13826023042201996,
      "learning_rate": 6e-05,
      "loss": 0.9273,
      "step": 3
    },
    {
      "epoch": 0.0004409333088370384,
      "eval_loss": NaN,
      "eval_runtime": 247.1908,
      "eval_samples_per_second": 11.59,
      "eval_steps_per_second": 5.797,
      "step": 3
    },
    {
      "epoch": 0.0005879110784493846,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.694,
      "step": 4
    },
    {
      "epoch": 0.0007348888480617307,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 1.2828,
      "step": 5
    },
    {
      "epoch": 0.0008818666176740768,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.8857,
      "step": 6
    },
    {
      "epoch": 0.0008818666176740768,
      "eval_loss": NaN,
      "eval_runtime": 247.2998,
      "eval_samples_per_second": 11.585,
      "eval_steps_per_second": 5.795,
      "step": 6
    },
    {
      "epoch": 0.0010288443872864229,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 1.2798,
      "step": 7
    },
    {
      "epoch": 0.0011758221568987691,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.5146,
      "step": 8
    },
    {
      "epoch": 0.0013227999265111152,
      "grad_norm": 0.1688116192817688,
      "learning_rate": 0.00018,
      "loss": 0.8901,
      "step": 9
    },
    {
      "epoch": 0.0013227999265111152,
      "eval_loss": NaN,
      "eval_runtime": 247.1101,
      "eval_samples_per_second": 11.594,
      "eval_steps_per_second": 5.799,
      "step": 9
    },
    {
      "epoch": 0.0014697776961234614,
      "grad_norm": 0.11648120731115341,
      "learning_rate": 0.0002,
      "loss": 0.5793,
      "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": 6346581737472000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}