Hugging Face's logo

Best000
/
83daef05-987d-4758-ba83-a85c0671e787

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
83daef05-987d-4758-ba83-a85c0671e787
File size: 3,196 Bytes 
a29ed5c
 
 
4e13f5e
a29ed5c
4e13f5e
a29ed5c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e9cca06
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6bac209
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4e13f5e
 
 
 
 
 
 
a29ed5c
 
 
 
 
 
 
 
 
 
 
 
 
 
4e13f5e
a29ed5c
 
 
 
4e13f5e
a29ed5c
 
 
 
 
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": 0.00475963826749167,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00047596382674916705,
      "grad_norm": 1.8053474426269531,
      "learning_rate": 2e-05,
      "loss": 3.712,
      "step": 1
    },
    {
      "epoch": 0.00047596382674916705,
      "eval_loss": 3.891406536102295,
      "eval_runtime": 13.7664,
      "eval_samples_per_second": 64.287,
      "eval_steps_per_second": 32.18,
      "step": 1
    },
    {
      "epoch": 0.0009519276534983341,
      "grad_norm": 1.8643312454223633,
      "learning_rate": 4e-05,
      "loss": 3.972,
      "step": 2
    },
    {
      "epoch": 0.0014278914802475012,
      "grad_norm": 1.9306492805480957,
      "learning_rate": 6e-05,
      "loss": 3.9292,
      "step": 3
    },
    {
      "epoch": 0.0014278914802475012,
      "eval_loss": 3.8839597702026367,
      "eval_runtime": 12.7111,
      "eval_samples_per_second": 69.624,
      "eval_steps_per_second": 34.851,
      "step": 3
    },
    {
      "epoch": 0.0019038553069966682,
      "grad_norm": 1.9931215047836304,
      "learning_rate": 8e-05,
      "loss": 3.9517,
      "step": 4
    },
    {
      "epoch": 0.002379819133745835,
      "grad_norm": 2.122426986694336,
      "learning_rate": 0.0001,
      "loss": 3.8819,
      "step": 5
    },
    {
      "epoch": 0.0028557829604950024,
      "grad_norm": 1.9000606536865234,
      "learning_rate": 0.00012,
      "loss": 3.8583,
      "step": 6
    },
    {
      "epoch": 0.0028557829604950024,
      "eval_loss": 3.78226637840271,
      "eval_runtime": 12.7788,
      "eval_samples_per_second": 69.255,
      "eval_steps_per_second": 34.667,
      "step": 6
    },
    {
      "epoch": 0.0033317467872441696,
      "grad_norm": 1.9532514810562134,
      "learning_rate": 0.00014,
      "loss": 3.5203,
      "step": 7
    },
    {
      "epoch": 0.0038077106139933364,
      "grad_norm": 2.3859152793884277,
      "learning_rate": 0.00016,
      "loss": 3.7132,
      "step": 8
    },
    {
      "epoch": 0.004283674440742504,
      "grad_norm": 2.218242883682251,
      "learning_rate": 0.00018,
      "loss": 3.6354,
      "step": 9
    },
    {
      "epoch": 0.004283674440742504,
      "eval_loss": 3.4840054512023926,
      "eval_runtime": 12.7436,
      "eval_samples_per_second": 69.447,
      "eval_steps_per_second": 34.763,
      "step": 9
    },
    {
      "epoch": 0.00475963826749167,
      "grad_norm": 2.1710777282714844,
      "learning_rate": 0.0002,
      "loss": 3.291,
      "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": 240545515438080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}