Hugging Face's logo

ClarenceDan
/
a805b928-4edf-4b3c-9b7b-48c0cf20df5a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
a805b928-4edf-4b3c-9b7b-48c0cf20df5a
File size: 3,181 Bytes 
2c351ed
 
 
665467f
2c351ed
665467f
2c351ed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47b0313
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4d3d8b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
665467f
 
 
 
 
 
 
2c351ed
 
 
 
 
 
 
 
 
 
 
 
 
 
665467f
2c351ed
 
 
 
665467f
2c351ed
 
 
 
 
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": 0.01238390092879257,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001238390092879257,
      "grad_norm": 3.4508397579193115,
      "learning_rate": 2e-05,
      "loss": 1.9859,
      "step": 1
    },
    {
      "epoch": 0.001238390092879257,
      "eval_loss": 2.4396731853485107,
      "eval_runtime": 15.3414,
      "eval_samples_per_second": 22.162,
      "eval_steps_per_second": 11.081,
      "step": 1
    },
    {
      "epoch": 0.002476780185758514,
      "grad_norm": 3.828749895095825,
      "learning_rate": 4e-05,
      "loss": 1.9901,
      "step": 2
    },
    {
      "epoch": 0.0037151702786377707,
      "grad_norm": 3.8040151596069336,
      "learning_rate": 6e-05,
      "loss": 2.333,
      "step": 3
    },
    {
      "epoch": 0.0037151702786377707,
      "eval_loss": 2.3865134716033936,
      "eval_runtime": 14.9594,
      "eval_samples_per_second": 22.728,
      "eval_steps_per_second": 11.364,
      "step": 3
    },
    {
      "epoch": 0.004953560371517028,
      "grad_norm": 3.526742696762085,
      "learning_rate": 8e-05,
      "loss": 2.2862,
      "step": 4
    },
    {
      "epoch": 0.006191950464396285,
      "grad_norm": 4.159535884857178,
      "learning_rate": 0.0001,
      "loss": 2.3137,
      "step": 5
    },
    {
      "epoch": 0.007430340557275541,
      "grad_norm": 2.6144652366638184,
      "learning_rate": 0.00012,
      "loss": 2.0839,
      "step": 6
    },
    {
      "epoch": 0.007430340557275541,
      "eval_loss": 1.816732406616211,
      "eval_runtime": 14.9855,
      "eval_samples_per_second": 22.689,
      "eval_steps_per_second": 11.344,
      "step": 6
    },
    {
      "epoch": 0.0086687306501548,
      "grad_norm": 2.634336471557617,
      "learning_rate": 0.00014,
      "loss": 1.8,
      "step": 7
    },
    {
      "epoch": 0.009907120743034056,
      "grad_norm": 2.586655855178833,
      "learning_rate": 0.00016,
      "loss": 1.3643,
      "step": 8
    },
    {
      "epoch": 0.011145510835913313,
      "grad_norm": 2.1898770332336426,
      "learning_rate": 0.00018,
      "loss": 1.3185,
      "step": 9
    },
    {
      "epoch": 0.011145510835913313,
      "eval_loss": 1.5426946878433228,
      "eval_runtime": 15.028,
      "eval_samples_per_second": 22.625,
      "eval_steps_per_second": 11.312,
      "step": 9
    },
    {
      "epoch": 0.01238390092879257,
      "grad_norm": 2.10044002532959,
      "learning_rate": 0.0002,
      "loss": 2.4211,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}