Hugging Face's logo

dimasik87
/
1c3701b4-7d0a-4c75-ad20-dc76160024ef

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
1c3701b4-7d0a-4c75-ad20-dc76160024ef
File size: 3,200 Bytes 
86ace5e
 
 
7c0315d
86ace5e
7c0315d
86ace5e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8e7ed29
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
259f518
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7c0315d
 
 
 
 
 
 
86ace5e
 
 
 
 
 
 
 
 
 
 
 
 
 
7c0315d
86ace5e
 
 
 
7c0315d
86ace5e
 
 
 
 
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": 0.05102040816326531,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00510204081632653,
      "grad_norm": 0.07761654257774353,
      "learning_rate": 2e-05,
      "loss": 10.3789,
      "step": 1
    },
    {
      "epoch": 0.00510204081632653,
      "eval_loss": 10.380595207214355,
      "eval_runtime": 0.3069,
      "eval_samples_per_second": 136.845,
      "eval_steps_per_second": 68.423,
      "step": 1
    },
    {
      "epoch": 0.01020408163265306,
      "grad_norm": 0.07940847426652908,
      "learning_rate": 4e-05,
      "loss": 10.3877,
      "step": 2
    },
    {
      "epoch": 0.015306122448979591,
      "grad_norm": 0.06227846071124077,
      "learning_rate": 6e-05,
      "loss": 10.3831,
      "step": 3
    },
    {
      "epoch": 0.015306122448979591,
      "eval_loss": 10.380550384521484,
      "eval_runtime": 0.3046,
      "eval_samples_per_second": 137.879,
      "eval_steps_per_second": 68.939,
      "step": 3
    },
    {
      "epoch": 0.02040816326530612,
      "grad_norm": 0.1003938615322113,
      "learning_rate": 8e-05,
      "loss": 10.3859,
      "step": 4
    },
    {
      "epoch": 0.025510204081632654,
      "grad_norm": 0.08336115628480911,
      "learning_rate": 0.0001,
      "loss": 10.3787,
      "step": 5
    },
    {
      "epoch": 0.030612244897959183,
      "grad_norm": 0.0812898501753807,
      "learning_rate": 0.00012,
      "loss": 10.3777,
      "step": 6
    },
    {
      "epoch": 0.030612244897959183,
      "eval_loss": 10.380258560180664,
      "eval_runtime": 0.3166,
      "eval_samples_per_second": 132.644,
      "eval_steps_per_second": 66.322,
      "step": 6
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 0.060700736939907074,
      "learning_rate": 0.00014,
      "loss": 10.3771,
      "step": 7
    },
    {
      "epoch": 0.04081632653061224,
      "grad_norm": 0.07724273949861526,
      "learning_rate": 0.00016,
      "loss": 10.3736,
      "step": 8
    },
    {
      "epoch": 0.04591836734693878,
      "grad_norm": 0.0864340215921402,
      "learning_rate": 0.00018,
      "loss": 10.3787,
      "step": 9
    },
    {
      "epoch": 0.04591836734693878,
      "eval_loss": 10.379778861999512,
      "eval_runtime": 0.3336,
      "eval_samples_per_second": 125.907,
      "eval_steps_per_second": 62.953,
      "step": 9
    },
    {
      "epoch": 0.05102040816326531,
      "grad_norm": 0.07752110809087753,
      "learning_rate": 0.0002,
      "loss": 10.3777,
      "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": 523024465920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}