Hugging Face's logo

diagonalge
/
65b0e3b1-885f-4015-bbce-1d75548149fb

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
65b0e3b1-885f-4015-bbce-1d75548149fb
File size: 3,200 Bytes 
a730f32
 
 
9fe196e
a730f32
9fe196e
a730f32
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9fe196e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a730f32
 
 
 
 
 
 
 
 
 
 
 
 
 
9fe196e
a730f32
 
 
 
9fe196e
a730f32
 
 
 
 
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": 0.0016300582745833164,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016300582745833165,
      "grad_norm": 1.5260664224624634,
      "learning_rate": 2e-05,
      "loss": 1.4625,
      "step": 1
    },
    {
      "epoch": 0.00016300582745833165,
      "eval_loss": 1.558783769607544,
      "eval_runtime": 373.2766,
      "eval_samples_per_second": 6.92,
      "eval_steps_per_second": 3.461,
      "step": 1
    },
    {
      "epoch": 0.0003260116549166633,
      "grad_norm": 1.213285207748413,
      "learning_rate": 4e-05,
      "loss": 1.8338,
      "step": 2
    },
    {
      "epoch": 0.0004890174823749949,
      "grad_norm": 1.7155927419662476,
      "learning_rate": 6e-05,
      "loss": 1.4972,
      "step": 3
    },
    {
      "epoch": 0.0004890174823749949,
      "eval_loss": 1.555458664894104,
      "eval_runtime": 373.4863,
      "eval_samples_per_second": 6.916,
      "eval_steps_per_second": 3.459,
      "step": 3
    },
    {
      "epoch": 0.0006520233098333266,
      "grad_norm": 2.710537910461426,
      "learning_rate": 8e-05,
      "loss": 1.8002,
      "step": 4
    },
    {
      "epoch": 0.0008150291372916582,
      "grad_norm": 1.4228698015213013,
      "learning_rate": 0.0001,
      "loss": 1.256,
      "step": 5
    },
    {
      "epoch": 0.0009780349647499898,
      "grad_norm": 1.1818934679031372,
      "learning_rate": 0.00012,
      "loss": 1.7772,
      "step": 6
    },
    {
      "epoch": 0.0009780349647499898,
      "eval_loss": 1.5226942300796509,
      "eval_runtime": 374.5727,
      "eval_samples_per_second": 6.896,
      "eval_steps_per_second": 3.449,
      "step": 6
    },
    {
      "epoch": 0.0011410407922083214,
      "grad_norm": 1.2571606636047363,
      "learning_rate": 0.00014,
      "loss": 1.5778,
      "step": 7
    },
    {
      "epoch": 0.0013040466196666532,
      "grad_norm": 3.4298977851867676,
      "learning_rate": 0.00016,
      "loss": 2.0878,
      "step": 8
    },
    {
      "epoch": 0.0014670524471249848,
      "grad_norm": 0.920394241809845,
      "learning_rate": 0.00018,
      "loss": 1.583,
      "step": 9
    },
    {
      "epoch": 0.0014670524471249848,
      "eval_loss": 1.4455409049987793,
      "eval_runtime": 373.3626,
      "eval_samples_per_second": 6.918,
      "eval_steps_per_second": 3.46,
      "step": 9
    },
    {
      "epoch": 0.0016300582745833164,
      "grad_norm": 0.9525576233863831,
      "learning_rate": 0.0002,
      "loss": 1.2694,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1935445139128320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}