Hugging Face's logo

great0001
/
a2ab05cb-2e99-44fa-bd39-93794b0428e0

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
a2ab05cb-2e99-44fa-bd39-93794b0428e0
File size: 3,041 Bytes 
127812a
 
 
91ee8e7
127812a
91ee8e7
127812a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ae8039
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91ee8e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
127812a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91ee8e7
127812a
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014719110311554502,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016354567012838336,
      "grad_norm": 0.853318452835083,
      "learning_rate": 2e-05,
      "loss": 4.1796,
      "step": 1
    },
    {
      "epoch": 0.00016354567012838336,
      "eval_loss": 3.870612859725952,
      "eval_runtime": 117.9532,
      "eval_samples_per_second": 21.831,
      "eval_steps_per_second": 10.92,
      "step": 1
    },
    {
      "epoch": 0.0003270913402567667,
      "grad_norm": 0.7066583633422852,
      "learning_rate": 4e-05,
      "loss": 3.2798,
      "step": 2
    },
    {
      "epoch": 0.00049063701038515,
      "grad_norm": 0.5949627161026001,
      "learning_rate": 6e-05,
      "loss": 2.8722,
      "step": 3
    },
    {
      "epoch": 0.00049063701038515,
      "eval_loss": 3.8621253967285156,
      "eval_runtime": 116.8527,
      "eval_samples_per_second": 22.036,
      "eval_steps_per_second": 11.022,
      "step": 3
    },
    {
      "epoch": 0.0006541826805135334,
      "grad_norm": 1.0430587530136108,
      "learning_rate": 8e-05,
      "loss": 3.5746,
      "step": 4
    },
    {
      "epoch": 0.0008177283506419167,
      "grad_norm": 0.8327656984329224,
      "learning_rate": 0.0001,
      "loss": 3.6405,
      "step": 5
    },
    {
      "epoch": 0.0009812740207703,
      "grad_norm": 1.4123550653457642,
      "learning_rate": 0.00012,
      "loss": 3.7486,
      "step": 6
    },
    {
      "epoch": 0.0009812740207703,
      "eval_loss": 3.747291326522827,
      "eval_runtime": 116.9365,
      "eval_samples_per_second": 22.02,
      "eval_steps_per_second": 11.015,
      "step": 6
    },
    {
      "epoch": 0.0011448196908986834,
      "grad_norm": 1.0004723072052002,
      "learning_rate": 0.00014,
      "loss": 3.2888,
      "step": 7
    },
    {
      "epoch": 0.0013083653610270669,
      "grad_norm": 1.0540218353271484,
      "learning_rate": 0.00016,
      "loss": 3.4393,
      "step": 8
    },
    {
      "epoch": 0.0014719110311554502,
      "grad_norm": 0.7315677404403687,
      "learning_rate": 0.00018,
      "loss": 2.3771,
      "step": 9
    },
    {
      "epoch": 0.0014719110311554502,
      "eval_loss": 3.418764352798462,
      "eval_runtime": 116.9534,
      "eval_samples_per_second": 22.017,
      "eval_steps_per_second": 11.013,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2849583755427840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}