Hugging Face's logo

jssky
/
f2c293d7-ee2f-4274-9b7e-6ff197ed2cce

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
f2c293d7-ee2f-4274-9b7e-6ff197ed2cce
File size: 3,205 Bytes 
8f90768
 
 
3c3091a
8f90768
3c3091a
8f90768
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c275204
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0ccd42a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c3091a
 
 
 
 
 
 
8f90768
 
 
 
 
 
 
 
 
 
 
 
 
 
3c3091a
8f90768
 
 
 
3c3091a
8f90768
 
 
 
 
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": 0.0009515653249595584,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.515653249595585e-05,
      "grad_norm": 0.8959489464759827,
      "learning_rate": 2e-05,
      "loss": 0.8972,
      "step": 1
    },
    {
      "epoch": 9.515653249595585e-05,
      "eval_loss": 0.9797402024269104,
      "eval_runtime": 702.7202,
      "eval_samples_per_second": 3.149,
      "eval_steps_per_second": 3.149,
      "step": 1
    },
    {
      "epoch": 0.0001903130649919117,
      "grad_norm": 0.5574295520782471,
      "learning_rate": 4e-05,
      "loss": 0.8309,
      "step": 2
    },
    {
      "epoch": 0.00028546959748786756,
      "grad_norm": 0.5667484402656555,
      "learning_rate": 6e-05,
      "loss": 0.7712,
      "step": 3
    },
    {
      "epoch": 0.00028546959748786756,
      "eval_loss": 0.9666468501091003,
      "eval_runtime": 703.082,
      "eval_samples_per_second": 3.148,
      "eval_steps_per_second": 3.148,
      "step": 3
    },
    {
      "epoch": 0.0003806261299838234,
      "grad_norm": 0.8053474426269531,
      "learning_rate": 8e-05,
      "loss": 0.7217,
      "step": 4
    },
    {
      "epoch": 0.0004757826624797792,
      "grad_norm": 0.580493152141571,
      "learning_rate": 0.0001,
      "loss": 1.161,
      "step": 5
    },
    {
      "epoch": 0.0005709391949757351,
      "grad_norm": 0.7792345285415649,
      "learning_rate": 0.00012,
      "loss": 0.9679,
      "step": 6
    },
    {
      "epoch": 0.0005709391949757351,
      "eval_loss": 0.8787497878074646,
      "eval_runtime": 702.975,
      "eval_samples_per_second": 3.148,
      "eval_steps_per_second": 3.148,
      "step": 6
    },
    {
      "epoch": 0.000666095727471691,
      "grad_norm": 0.7983985543251038,
      "learning_rate": 0.00014,
      "loss": 0.9646,
      "step": 7
    },
    {
      "epoch": 0.0007612522599676468,
      "grad_norm": 0.7791344523429871,
      "learning_rate": 0.00016,
      "loss": 1.0793,
      "step": 8
    },
    {
      "epoch": 0.0008564087924636027,
      "grad_norm": 0.9845541715621948,
      "learning_rate": 0.00018,
      "loss": 0.875,
      "step": 9
    },
    {
      "epoch": 0.0008564087924636027,
      "eval_loss": 0.7046293020248413,
      "eval_runtime": 703.0342,
      "eval_samples_per_second": 3.148,
      "eval_steps_per_second": 3.148,
      "step": 9
    },
    {
      "epoch": 0.0009515653249595584,
      "grad_norm": 0.8508020639419556,
      "learning_rate": 0.0002,
      "loss": 0.7558,
      "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": 1.27239261782016e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}