Hugging Face's logo

trenden
/
e92aac83-5c27-4720-aa8d-7cb3d4d794ce

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e92aac83-5c27-4720-aa8d-7cb3d4d794ce
File size: 3,201 Bytes 
aab625e
 
 
52877f1
aab625e
52877f1
aab625e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e5f4507
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
12796ca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52877f1
 
 
 
 
 
 
aab625e
 
 
 
 
 
 
 
 
 
 
 
 
 
52877f1
aab625e
 
 
 
52877f1
aab625e
 
 
 
 
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": 0.0031181789834736516,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003118178983473651,
      "grad_norm": 0.6566165685653687,
      "learning_rate": 2e-05,
      "loss": 1.8957,
      "step": 1
    },
    {
      "epoch": 0.0003118178983473651,
      "eval_loss": 1.8035469055175781,
      "eval_runtime": 57.7332,
      "eval_samples_per_second": 23.401,
      "eval_steps_per_second": 11.709,
      "step": 1
    },
    {
      "epoch": 0.0006236357966947302,
      "grad_norm": 0.7361301183700562,
      "learning_rate": 4e-05,
      "loss": 1.8645,
      "step": 2
    },
    {
      "epoch": 0.0009354536950420954,
      "grad_norm": 0.5800981521606445,
      "learning_rate": 6e-05,
      "loss": 1.7754,
      "step": 3
    },
    {
      "epoch": 0.0009354536950420954,
      "eval_loss": 1.79875910282135,
      "eval_runtime": 55.7045,
      "eval_samples_per_second": 24.253,
      "eval_steps_per_second": 12.135,
      "step": 3
    },
    {
      "epoch": 0.0012472715933894605,
      "grad_norm": 0.6629976034164429,
      "learning_rate": 8e-05,
      "loss": 1.7424,
      "step": 4
    },
    {
      "epoch": 0.0015590894917368258,
      "grad_norm": 0.7607347965240479,
      "learning_rate": 0.0001,
      "loss": 1.7342,
      "step": 5
    },
    {
      "epoch": 0.0018709073900841909,
      "grad_norm": 0.728712260723114,
      "learning_rate": 0.00012,
      "loss": 1.6289,
      "step": 6
    },
    {
      "epoch": 0.0018709073900841909,
      "eval_loss": 1.7151895761489868,
      "eval_runtime": 55.8278,
      "eval_samples_per_second": 24.199,
      "eval_steps_per_second": 12.109,
      "step": 6
    },
    {
      "epoch": 0.002182725288431556,
      "grad_norm": 0.8463139533996582,
      "learning_rate": 0.00014,
      "loss": 1.8157,
      "step": 7
    },
    {
      "epoch": 0.002494543186778921,
      "grad_norm": 0.6177520155906677,
      "learning_rate": 0.00016,
      "loss": 1.7816,
      "step": 8
    },
    {
      "epoch": 0.002806361085126286,
      "grad_norm": 1.193546175956726,
      "learning_rate": 0.00018,
      "loss": 1.626,
      "step": 9
    },
    {
      "epoch": 0.002806361085126286,
      "eval_loss": 1.691176414489746,
      "eval_runtime": 55.8437,
      "eval_samples_per_second": 24.193,
      "eval_steps_per_second": 12.105,
      "step": 9
    },
    {
      "epoch": 0.0031181789834736516,
      "grad_norm": 1.5937474966049194,
      "learning_rate": 0.0002,
      "loss": 1.6128,
      "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": 2820585478422528.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}