Hugging Face's logo

jssky
/
7f40518c-9517-4f6c-a885-d045ba26c3d6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7f40518c-9517-4f6c-a885-d045ba26c3d6
File size: 3,211 Bytes 
54a4f0b
 
 
886847b
54a4f0b
886847b
54a4f0b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ea2523
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b0cad3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
886847b
 
 
 
 
 
 
54a4f0b
 
 
 
 
 
 
 
 
 
 
 
 
 
886847b
54a4f0b
 
 
 
886847b
54a4f0b
 
 
 
 
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": 0.022197558268590455,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0022197558268590455,
      "grad_norm": 0.025404546409845352,
      "learning_rate": 2e-05,
      "loss": 10.3769,
      "step": 1
    },
    {
      "epoch": 0.0022197558268590455,
      "eval_loss": 10.37777328491211,
      "eval_runtime": 1.2457,
      "eval_samples_per_second": 152.531,
      "eval_steps_per_second": 76.265,
      "step": 1
    },
    {
      "epoch": 0.004439511653718091,
      "grad_norm": 0.02415435202419758,
      "learning_rate": 4e-05,
      "loss": 10.3758,
      "step": 2
    },
    {
      "epoch": 0.006659267480577136,
      "grad_norm": 0.027586132287979126,
      "learning_rate": 6e-05,
      "loss": 10.3763,
      "step": 3
    },
    {
      "epoch": 0.006659267480577136,
      "eval_loss": 10.377732276916504,
      "eval_runtime": 1.2364,
      "eval_samples_per_second": 153.67,
      "eval_steps_per_second": 76.835,
      "step": 3
    },
    {
      "epoch": 0.008879023307436182,
      "grad_norm": 0.025835813954472542,
      "learning_rate": 8e-05,
      "loss": 10.3749,
      "step": 4
    },
    {
      "epoch": 0.011098779134295227,
      "grad_norm": 0.0256224162876606,
      "learning_rate": 0.0001,
      "loss": 10.3748,
      "step": 5
    },
    {
      "epoch": 0.013318534961154272,
      "grad_norm": 0.018543493002653122,
      "learning_rate": 0.00012,
      "loss": 10.3791,
      "step": 6
    },
    {
      "epoch": 0.013318534961154272,
      "eval_loss": 10.377586364746094,
      "eval_runtime": 1.268,
      "eval_samples_per_second": 149.84,
      "eval_steps_per_second": 74.92,
      "step": 6
    },
    {
      "epoch": 0.01553829078801332,
      "grad_norm": 0.025994783267378807,
      "learning_rate": 0.00014,
      "loss": 10.379,
      "step": 7
    },
    {
      "epoch": 0.017758046614872364,
      "grad_norm": 0.025559840723872185,
      "learning_rate": 0.00016,
      "loss": 10.3769,
      "step": 8
    },
    {
      "epoch": 0.01997780244173141,
      "grad_norm": 0.020570356398820877,
      "learning_rate": 0.00018,
      "loss": 10.3795,
      "step": 9
    },
    {
      "epoch": 0.01997780244173141,
      "eval_loss": 10.37732982635498,
      "eval_runtime": 1.2633,
      "eval_samples_per_second": 150.402,
      "eval_steps_per_second": 75.201,
      "step": 9
    },
    {
      "epoch": 0.022197558268590455,
      "grad_norm": 0.02001837082207203,
      "learning_rate": 0.0002,
      "loss": 10.3791,
      "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": 1046048931840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}