Hugging Face's logo

nathanialhunt
/
e2dbcfd2-bf17-43bf-83d3-a6b47216d74d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e2dbcfd2-bf17-43bf-83d3-a6b47216d74d
File size: 3,210 Bytes 
b316395
 
 
b35956d
b316395
b35956d
b316395
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3f049ef
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4ed1b53
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b35956d
 
 
 
 
 
 
b316395
 
 
 
 
 
 
 
 
 
 
 
 
 
b35956d
b316395
 
 
 
b35956d
b316395
 
 
 
 
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": 0.0003989706557082727,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.9897065570827266e-05,
      "grad_norm": 38.08751678466797,
      "learning_rate": 2e-05,
      "loss": 13.2355,
      "step": 1
    },
    {
      "epoch": 3.9897065570827266e-05,
      "eval_loss": 13.641461372375488,
      "eval_runtime": 461.4019,
      "eval_samples_per_second": 22.874,
      "eval_steps_per_second": 11.437,
      "step": 1
    },
    {
      "epoch": 7.979413114165453e-05,
      "grad_norm": 32.36470031738281,
      "learning_rate": 4e-05,
      "loss": 13.3156,
      "step": 2
    },
    {
      "epoch": 0.0001196911967124818,
      "grad_norm": 35.10114288330078,
      "learning_rate": 6e-05,
      "loss": 13.899,
      "step": 3
    },
    {
      "epoch": 0.0001196911967124818,
      "eval_loss": 13.088886260986328,
      "eval_runtime": 460.7602,
      "eval_samples_per_second": 22.906,
      "eval_steps_per_second": 11.453,
      "step": 3
    },
    {
      "epoch": 0.00015958826228330906,
      "grad_norm": 35.32827377319336,
      "learning_rate": 8e-05,
      "loss": 12.036,
      "step": 4
    },
    {
      "epoch": 0.00019948532785413634,
      "grad_norm": 27.98809051513672,
      "learning_rate": 0.0001,
      "loss": 13.5756,
      "step": 5
    },
    {
      "epoch": 0.0002393823934249636,
      "grad_norm": 30.70273780822754,
      "learning_rate": 0.00012,
      "loss": 9.3102,
      "step": 6
    },
    {
      "epoch": 0.0002393823934249636,
      "eval_loss": 6.75634241104126,
      "eval_runtime": 460.8268,
      "eval_samples_per_second": 22.902,
      "eval_steps_per_second": 11.451,
      "step": 6
    },
    {
      "epoch": 0.00027927945899579087,
      "grad_norm": 42.0061149597168,
      "learning_rate": 0.00014,
      "loss": 5.6204,
      "step": 7
    },
    {
      "epoch": 0.0003191765245666181,
      "grad_norm": 15.68433952331543,
      "learning_rate": 0.00016,
      "loss": 6.5446,
      "step": 8
    },
    {
      "epoch": 0.0003590735901374454,
      "grad_norm": 8.796845436096191,
      "learning_rate": 0.00018,
      "loss": 3.0595,
      "step": 9
    },
    {
      "epoch": 0.0003590735901374454,
      "eval_loss": 3.500016927719116,
      "eval_runtime": 460.7356,
      "eval_samples_per_second": 22.907,
      "eval_steps_per_second": 11.453,
      "step": 9
    },
    {
      "epoch": 0.0003989706557082727,
      "grad_norm": 12.054160118103027,
      "learning_rate": 0.0002,
      "loss": 4.0348,
      "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": 2774346372218880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}