Hugging Face's logo

trenden
/
57d0411d-0630-4b65-85eb-9d576e6ed587

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
57d0411d-0630-4b65-85eb-9d576e6ed587
File size: 2,946 Bytes 
420f21a
 
 
0ad28a0
420f21a
0ad28a0
420f21a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
837178b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d08834
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0ad28a0
 
 
 
 
 
 
420f21a
 
 
 
 
 
 
 
 
 
 
 
 
 
0ad28a0
420f21a
 
 
 
0ad28a0
420f21a
 
 
 
 
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": 0.10526315789473684,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010526315789473684,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.010526315789473684,
      "eval_loss": NaN,
      "eval_runtime": 3.0083,
      "eval_samples_per_second": 13.297,
      "eval_steps_per_second": 6.648,
      "step": 1
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.031578947368421054,
      "eval_loss": NaN,
      "eval_runtime": 1.6307,
      "eval_samples_per_second": 24.53,
      "eval_steps_per_second": 12.265,
      "step": 3
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 5.0537,
      "step": 4
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 5.077,
      "step": 6
    },
    {
      "epoch": 0.06315789473684211,
      "eval_loss": NaN,
      "eval_runtime": 1.6265,
      "eval_samples_per_second": 24.592,
      "eval_steps_per_second": 12.296,
      "step": 6
    },
    {
      "epoch": 0.07368421052631578,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.09473684210526316,
      "eval_loss": NaN,
      "eval_runtime": 1.6561,
      "eval_samples_per_second": 24.154,
      "eval_steps_per_second": 12.077,
      "step": 9
    },
    {
      "epoch": 0.10526315789473684,
      "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": 2095034388185088.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}