Hugging Face's logo

vertings6
/
7964766a-2d6b-402e-8b99-33113320b90d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7964766a-2d6b-402e-8b99-33113320b90d
File size: 3,294 Bytes 
48dbaa8
 
 
96e840a
48dbaa8
96e840a
48dbaa8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76ff587
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96e840a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48dbaa8
 
 
 
 
 
 
 
 
 
 
 
 
 
96e840a
48dbaa8
 
 
 
96e840a
48dbaa8
 
 
 
 
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": 0.0006418450906873626,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.139483635624542e-05,
      "eval_loss": 3.725355863571167,
      "eval_runtime": 2541.9047,
      "eval_samples_per_second": 7.743,
      "eval_steps_per_second": 3.872,
      "step": 1
    },
    {
      "epoch": 6.418450906873626e-05,
      "grad_norm": 3.953409194946289,
      "learning_rate": 3e-05,
      "loss": 3.7594,
      "step": 3
    },
    {
      "epoch": 0.0001283690181374725,
      "grad_norm": 3.3203933238983154,
      "learning_rate": 6e-05,
      "loss": 3.7394,
      "step": 6
    },
    {
      "epoch": 0.00017115869084996337,
      "eval_loss": 2.99819016456604,
      "eval_runtime": 2550.9541,
      "eval_samples_per_second": 7.715,
      "eval_steps_per_second": 3.858,
      "step": 8
    },
    {
      "epoch": 0.0001925535272062088,
      "grad_norm": 2.904099702835083,
      "learning_rate": 9e-05,
      "loss": 3.2948,
      "step": 9
    },
    {
      "epoch": 0.000256738036274945,
      "grad_norm": 3.060228109359741,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.7908,
      "step": 12
    },
    {
      "epoch": 0.0003209225453436813,
      "grad_norm": 3.075441837310791,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.3934,
      "step": 15
    },
    {
      "epoch": 0.00034231738169992673,
      "eval_loss": 2.2090160846710205,
      "eval_runtime": 2548.8684,
      "eval_samples_per_second": 7.721,
      "eval_steps_per_second": 3.861,
      "step": 16
    },
    {
      "epoch": 0.0003851070544124176,
      "grad_norm": 2.209512710571289,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.286,
      "step": 18
    },
    {
      "epoch": 0.0004492915634811538,
      "grad_norm": 2.8848774433135986,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.1907,
      "step": 21
    },
    {
      "epoch": 0.00051347607254989,
      "grad_norm": 2.1118345260620117,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.0544,
      "step": 24
    },
    {
      "epoch": 0.00051347607254989,
      "eval_loss": 2.096832275390625,
      "eval_runtime": 2546.8778,
      "eval_samples_per_second": 7.728,
      "eval_steps_per_second": 3.864,
      "step": 24
    },
    {
      "epoch": 0.0005776605816186263,
      "grad_norm": 2.1737489700317383,
      "learning_rate": 5.449673790581611e-06,
      "loss": 2.0826,
      "step": 27
    },
    {
      "epoch": 0.0006418450906873626,
      "grad_norm": 2.259516954421997,
      "learning_rate": 0.0,
      "loss": 1.9007,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.112830925340672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}