Hugging Face's logo

dimasik2987
/
92e67268-b5ed-4f1e-84ab-efb0da174c25

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
92e67268-b5ed-4f1e-84ab-efb0da174c25
File size: 3,269 Bytes 
f4d01e1
 
 
6eb59aa
f4d01e1
6eb59aa
f4d01e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0784b05
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6eb59aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f4d01e1
 
 
 
 
 
 
 
 
 
 
 
 
 
6eb59aa
f4d01e1
 
 
 
6eb59aa
f4d01e1
 
 
 
 
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": 0.10810810810810811,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036036036036036037,
      "eval_loss": 2.2794220447540283,
      "eval_runtime": 26.7462,
      "eval_samples_per_second": 4.374,
      "eval_steps_per_second": 2.206,
      "step": 1
    },
    {
      "epoch": 0.010810810810810811,
      "grad_norm": 2.174393892288208,
      "learning_rate": 6e-05,
      "loss": 8.4487,
      "step": 3
    },
    {
      "epoch": 0.021621621621621623,
      "grad_norm": 2.042609214782715,
      "learning_rate": 0.00012,
      "loss": 7.9254,
      "step": 6
    },
    {
      "epoch": 0.02882882882882883,
      "eval_loss": 2.1537671089172363,
      "eval_runtime": 27.2912,
      "eval_samples_per_second": 4.287,
      "eval_steps_per_second": 2.162,
      "step": 8
    },
    {
      "epoch": 0.032432432432432434,
      "grad_norm": 2.866565465927124,
      "learning_rate": 0.00018,
      "loss": 9.3699,
      "step": 9
    },
    {
      "epoch": 0.043243243243243246,
      "grad_norm": 6.563762664794922,
      "learning_rate": 0.00019510565162951537,
      "loss": 8.6299,
      "step": 12
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 3.654428720474243,
      "learning_rate": 0.00017071067811865476,
      "loss": 7.1947,
      "step": 15
    },
    {
      "epoch": 0.05765765765765766,
      "eval_loss": 1.9088410139083862,
      "eval_runtime": 27.3814,
      "eval_samples_per_second": 4.273,
      "eval_steps_per_second": 2.155,
      "step": 16
    },
    {
      "epoch": 0.06486486486486487,
      "grad_norm": 4.6610107421875,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.7044,
      "step": 18
    },
    {
      "epoch": 0.07567567567567568,
      "grad_norm": 9.290574073791504,
      "learning_rate": 8.435655349597689e-05,
      "loss": 6.7934,
      "step": 21
    },
    {
      "epoch": 0.08648648648648649,
      "grad_norm": 5.527563571929932,
      "learning_rate": 4.12214747707527e-05,
      "loss": 7.2144,
      "step": 24
    },
    {
      "epoch": 0.08648648648648649,
      "eval_loss": 1.7844364643096924,
      "eval_runtime": 27.3944,
      "eval_samples_per_second": 4.271,
      "eval_steps_per_second": 2.154,
      "step": 24
    },
    {
      "epoch": 0.0972972972972973,
      "grad_norm": 3.0254547595977783,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 7.2205,
      "step": 27
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 6.862932205200195,
      "learning_rate": 0.0,
      "loss": 7.2248,
      "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": 1.90434898870272e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}