Hugging Face's logo

trenden
/
ef6eea4b-32c8-424c-b23b-b4f60e52be78

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ef6eea4b-32c8-424c-b23b-b4f60e52be78
File size: 2,983 Bytes 
65b53e6
 
 
4fa4f72
65b53e6
4fa4f72
65b53e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
212dcb3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4fa4f72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
65b53e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4fa4f72
65b53e6
 
 
 
 
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": 0.004287756074321105,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004764173415912339,
      "grad_norm": 1.7114481925964355,
      "learning_rate": 2e-05,
      "loss": 2.5354,
      "step": 1
    },
    {
      "epoch": 0.0004764173415912339,
      "eval_loss": NaN,
      "eval_runtime": 30.2525,
      "eval_samples_per_second": 29.221,
      "eval_steps_per_second": 14.61,
      "step": 1
    },
    {
      "epoch": 0.0009528346831824678,
      "grad_norm": 1.6032798290252686,
      "learning_rate": 4e-05,
      "loss": 2.5293,
      "step": 2
    },
    {
      "epoch": 0.0014292520247737017,
      "grad_norm": 1.4384857416152954,
      "learning_rate": 6e-05,
      "loss": 3.0505,
      "step": 3
    },
    {
      "epoch": 0.0014292520247737017,
      "eval_loss": NaN,
      "eval_runtime": 29.3188,
      "eval_samples_per_second": 30.151,
      "eval_steps_per_second": 15.076,
      "step": 3
    },
    {
      "epoch": 0.0019056693663649356,
      "grad_norm": 1.4929753541946411,
      "learning_rate": 8e-05,
      "loss": 2.4071,
      "step": 4
    },
    {
      "epoch": 0.0023820867079561697,
      "grad_norm": 1.3990875482559204,
      "learning_rate": 0.0001,
      "loss": 2.6898,
      "step": 5
    },
    {
      "epoch": 0.0028585040495474035,
      "grad_norm": 1.4919512271881104,
      "learning_rate": 0.00012,
      "loss": 2.7419,
      "step": 6
    },
    {
      "epoch": 0.0028585040495474035,
      "eval_loss": NaN,
      "eval_runtime": 29.4292,
      "eval_samples_per_second": 30.038,
      "eval_steps_per_second": 15.019,
      "step": 6
    },
    {
      "epoch": 0.0033349213911386373,
      "grad_norm": 1.566218614578247,
      "learning_rate": 0.00014,
      "loss": 2.5994,
      "step": 7
    },
    {
      "epoch": 0.003811338732729871,
      "grad_norm": 1.520134687423706,
      "learning_rate": 0.00016,
      "loss": 2.5051,
      "step": 8
    },
    {
      "epoch": 0.004287756074321105,
      "grad_norm": 2.302412509918213,
      "learning_rate": 0.00018,
      "loss": 2.5605,
      "step": 9
    },
    {
      "epoch": 0.004287756074321105,
      "eval_loss": NaN,
      "eval_runtime": 28.1846,
      "eval_samples_per_second": 31.365,
      "eval_steps_per_second": 15.682,
      "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": 1664636814360576.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}