Hugging Face's logo

adammandic87
/
b558bc9c-9ec0-498e-8f55-6831ae6151b2

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
b558bc9c-9ec0-498e-8f55-6831ae6151b2
File size: 3,202 Bytes 
e7fdc9c
 
 
b59ee9f
e7fdc9c
b59ee9f
e7fdc9c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72eeb00
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
05de45d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b59ee9f
 
 
 
 
 
 
e7fdc9c
 
 
 
 
 
 
 
 
 
 
 
 
 
b59ee9f
e7fdc9c
 
 
 
b59ee9f
e7fdc9c
 
 
 
 
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": 0.001554001554001554,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001554001554001554,
      "grad_norm": 2.598501443862915,
      "learning_rate": 2e-05,
      "loss": 5.5903,
      "step": 1
    },
    {
      "epoch": 0.0001554001554001554,
      "eval_loss": 5.979092121124268,
      "eval_runtime": 119.1828,
      "eval_samples_per_second": 22.738,
      "eval_steps_per_second": 11.369,
      "step": 1
    },
    {
      "epoch": 0.0003108003108003108,
      "grad_norm": 1.9009497165679932,
      "learning_rate": 4e-05,
      "loss": 4.2089,
      "step": 2
    },
    {
      "epoch": 0.0004662004662004662,
      "grad_norm": 2.9781405925750732,
      "learning_rate": 6e-05,
      "loss": 5.9268,
      "step": 3
    },
    {
      "epoch": 0.0004662004662004662,
      "eval_loss": 5.970939636230469,
      "eval_runtime": 117.8699,
      "eval_samples_per_second": 22.991,
      "eval_steps_per_second": 11.496,
      "step": 3
    },
    {
      "epoch": 0.0006216006216006216,
      "grad_norm": 2.6014654636383057,
      "learning_rate": 8e-05,
      "loss": 6.3323,
      "step": 4
    },
    {
      "epoch": 0.000777000777000777,
      "grad_norm": 2.1102042198181152,
      "learning_rate": 0.0001,
      "loss": 4.3612,
      "step": 5
    },
    {
      "epoch": 0.0009324009324009324,
      "grad_norm": 3.557586431503296,
      "learning_rate": 0.00012,
      "loss": 5.8431,
      "step": 6
    },
    {
      "epoch": 0.0009324009324009324,
      "eval_loss": 5.798998832702637,
      "eval_runtime": 117.8935,
      "eval_samples_per_second": 22.987,
      "eval_steps_per_second": 11.493,
      "step": 6
    },
    {
      "epoch": 0.0010878010878010878,
      "grad_norm": 2.7650983333587646,
      "learning_rate": 0.00014,
      "loss": 4.7111,
      "step": 7
    },
    {
      "epoch": 0.0012432012432012432,
      "grad_norm": 3.379702091217041,
      "learning_rate": 0.00016,
      "loss": 5.5954,
      "step": 8
    },
    {
      "epoch": 0.0013986013986013986,
      "grad_norm": 3.5403878688812256,
      "learning_rate": 0.00018,
      "loss": 4.7313,
      "step": 9
    },
    {
      "epoch": 0.0013986013986013986,
      "eval_loss": 5.086339950561523,
      "eval_runtime": 117.9242,
      "eval_samples_per_second": 22.981,
      "eval_steps_per_second": 11.49,
      "step": 9
    },
    {
      "epoch": 0.001554001554001554,
      "grad_norm": 3.722743034362793,
      "learning_rate": 0.0002,
      "loss": 4.751,
      "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": 2728107266015232.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}