Hugging Face's logo

ClarenceDan
/
252364f9-fc70-4227-b6e0-27b41db2bed4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
252364f9-fc70-4227-b6e0-27b41db2bed4
File size: 2,983 Bytes 
c9afdf1
 
 
7582833
c9afdf1
7582833
c9afdf1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8f70a01
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0ac14b4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7582833
 
 
 
 
 
 
c9afdf1
 
 
 
 
 
 
 
 
 
 
 
 
 
7582833
c9afdf1
 
 
 
7582833
c9afdf1
 
 
 
 
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": 0.0016304569355561896,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016304569355561895,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.2121,
      "step": 1
    },
    {
      "epoch": 0.00016304569355561895,
      "eval_loss": NaN,
      "eval_runtime": 41.549,
      "eval_samples_per_second": 62.168,
      "eval_steps_per_second": 31.096,
      "step": 1
    },
    {
      "epoch": 0.0003260913871112379,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0004891370806668569,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0004891370806668569,
      "eval_loss": NaN,
      "eval_runtime": 40.5147,
      "eval_samples_per_second": 63.755,
      "eval_steps_per_second": 31.89,
      "step": 3
    },
    {
      "epoch": 0.0006521827742224758,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0008152284677780948,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0009782741613337139,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.2186,
      "step": 6
    },
    {
      "epoch": 0.0009782741613337139,
      "eval_loss": NaN,
      "eval_runtime": 40.3666,
      "eval_samples_per_second": 63.988,
      "eval_steps_per_second": 32.007,
      "step": 6
    },
    {
      "epoch": 0.0011413198548893327,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.211,
      "step": 7
    },
    {
      "epoch": 0.0013043655484449516,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0014674112420005707,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 2.347,
      "step": 9
    },
    {
      "epoch": 0.0014674112420005707,
      "eval_loss": NaN,
      "eval_runtime": 40.0558,
      "eval_samples_per_second": 64.485,
      "eval_steps_per_second": 32.255,
      "step": 9
    },
    {
      "epoch": 0.0016304569355561896,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.6112,
      "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": 384872824700928.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}