Hugging Face's logo

kooff11
/
c097e8b9-c870-4487-abcb-4ecfbb127315

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
c097e8b9-c870-4487-abcb-4ecfbb127315
File size: 3,206 Bytes 
a2b2aad
 
 
eb72304
a2b2aad
eb72304
a2b2aad
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce45ba2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
416beb7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eb72304
 
 
 
 
 
 
a2b2aad
 
 
 
 
 
 
 
 
 
 
 
 
 
eb72304
a2b2aad
 
 
 
eb72304
a2b2aad
 
 
 
 
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": 0.03656307129798903,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003656307129798903,
      "grad_norm": 0.09342558681964874,
      "learning_rate": 2e-05,
      "loss": 10.3625,
      "step": 1
    },
    {
      "epoch": 0.003656307129798903,
      "eval_loss": 10.363628387451172,
      "eval_runtime": 0.9594,
      "eval_samples_per_second": 480.517,
      "eval_steps_per_second": 60.455,
      "step": 1
    },
    {
      "epoch": 0.007312614259597806,
      "grad_norm": 0.09047584235668182,
      "learning_rate": 4e-05,
      "loss": 10.3594,
      "step": 2
    },
    {
      "epoch": 0.010968921389396709,
      "grad_norm": 0.08603765070438385,
      "learning_rate": 6e-05,
      "loss": 10.3705,
      "step": 3
    },
    {
      "epoch": 0.010968921389396709,
      "eval_loss": 10.363529205322266,
      "eval_runtime": 0.9573,
      "eval_samples_per_second": 481.543,
      "eval_steps_per_second": 60.585,
      "step": 3
    },
    {
      "epoch": 0.014625228519195612,
      "grad_norm": 0.06676133722066879,
      "learning_rate": 8e-05,
      "loss": 10.3638,
      "step": 4
    },
    {
      "epoch": 0.018281535648994516,
      "grad_norm": 0.08866722881793976,
      "learning_rate": 0.0001,
      "loss": 10.3619,
      "step": 5
    },
    {
      "epoch": 0.021937842778793418,
      "grad_norm": 0.08508071303367615,
      "learning_rate": 0.00012,
      "loss": 10.361,
      "step": 6
    },
    {
      "epoch": 0.021937842778793418,
      "eval_loss": 10.36319351196289,
      "eval_runtime": 0.9755,
      "eval_samples_per_second": 472.593,
      "eval_steps_per_second": 59.459,
      "step": 6
    },
    {
      "epoch": 0.025594149908592323,
      "grad_norm": 0.09561645984649658,
      "learning_rate": 0.00014,
      "loss": 10.3701,
      "step": 7
    },
    {
      "epoch": 0.029250457038391225,
      "grad_norm": 0.08754566311836243,
      "learning_rate": 0.00016,
      "loss": 10.3637,
      "step": 8
    },
    {
      "epoch": 0.03290676416819013,
      "grad_norm": 0.08271048218011856,
      "learning_rate": 0.00018,
      "loss": 10.3623,
      "step": 9
    },
    {
      "epoch": 0.03290676416819013,
      "eval_loss": 10.36262035369873,
      "eval_runtime": 1.0009,
      "eval_samples_per_second": 460.563,
      "eval_steps_per_second": 57.945,
      "step": 9
    },
    {
      "epoch": 0.03656307129798903,
      "grad_norm": 0.07217925786972046,
      "learning_rate": 0.0002,
      "loss": 10.3636,
      "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": 4184195727360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}