Hugging Face's logo

dimasik87
/
c3ee1ca0-bbe7-4e45-a236-2aeceeb44d92

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
c3ee1ca0-bbe7-4e45-a236-2aeceeb44d92
File size: 3,189 Bytes 
e7e31c7
 
 
6509032
e7e31c7
6509032
e7e31c7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b669568
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c7b0294
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6509032
 
 
 
 
 
 
e7e31c7
 
 
 
 
 
 
 
 
 
 
 
 
 
6509032
e7e31c7
 
 
 
6509032
e7e31c7
 
 
 
 
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": 0.014776505356483192,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014776505356483192,
      "grad_norm": 1.2122458219528198,
      "learning_rate": 2e-05,
      "loss": 2.4179,
      "step": 1
    },
    {
      "epoch": 0.0014776505356483192,
      "eval_loss": 2.4440231323242188,
      "eval_runtime": 53.951,
      "eval_samples_per_second": 5.283,
      "eval_steps_per_second": 2.651,
      "step": 1
    },
    {
      "epoch": 0.0029553010712966383,
      "grad_norm": 0.8069053292274475,
      "learning_rate": 4e-05,
      "loss": 2.2724,
      "step": 2
    },
    {
      "epoch": 0.004432951606944958,
      "grad_norm": 1.7609020471572876,
      "learning_rate": 6e-05,
      "loss": 2.5391,
      "step": 3
    },
    {
      "epoch": 0.004432951606944958,
      "eval_loss": 2.4400010108947754,
      "eval_runtime": 54.3025,
      "eval_samples_per_second": 5.248,
      "eval_steps_per_second": 2.633,
      "step": 3
    },
    {
      "epoch": 0.005910602142593277,
      "grad_norm": 0.7547000646591187,
      "learning_rate": 8e-05,
      "loss": 2.3439,
      "step": 4
    },
    {
      "epoch": 0.007388252678241596,
      "grad_norm": 0.8642814755439758,
      "learning_rate": 0.0001,
      "loss": 2.4535,
      "step": 5
    },
    {
      "epoch": 0.008865903213889916,
      "grad_norm": 0.7741430997848511,
      "learning_rate": 0.00012,
      "loss": 2.2524,
      "step": 6
    },
    {
      "epoch": 0.008865903213889916,
      "eval_loss": 2.4153623580932617,
      "eval_runtime": 54.5172,
      "eval_samples_per_second": 5.228,
      "eval_steps_per_second": 2.623,
      "step": 6
    },
    {
      "epoch": 0.010343553749538234,
      "grad_norm": 0.8248753547668457,
      "learning_rate": 0.00014,
      "loss": 2.2024,
      "step": 7
    },
    {
      "epoch": 0.011821204285186553,
      "grad_norm": 0.8654381036758423,
      "learning_rate": 0.00016,
      "loss": 2.4941,
      "step": 8
    },
    {
      "epoch": 0.013298854820834873,
      "grad_norm": 0.7903196811676025,
      "learning_rate": 0.00018,
      "loss": 2.3585,
      "step": 9
    },
    {
      "epoch": 0.013298854820834873,
      "eval_loss": 2.3736534118652344,
      "eval_runtime": 54.3524,
      "eval_samples_per_second": 5.244,
      "eval_steps_per_second": 2.631,
      "step": 9
    },
    {
      "epoch": 0.014776505356483192,
      "grad_norm": 0.747567355632782,
      "learning_rate": 0.0002,
      "loss": 2.3932,
      "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": 2545835153817600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}