Hugging Face's logo

gavrilstep
/
9b12302c-6c3a-4537-b436-cb2a6f269c24

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
9b12302c-6c3a-4537-b436-cb2a6f269c24
File size: 3,359 Bytes 
3b588c8
 
 
4e4adf7
3b588c8
4e4adf7
3b588c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c637c79
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4e4adf7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3b588c8
 
 
 
 
 
 
 
 
 
 
 
 
 
4e4adf7
3b588c8
 
 
 
4e4adf7
3b588c8
 
 
 
 
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": 0.009284332688588007,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003094777562862669,
      "eval_loss": 10.374013900756836,
      "eval_runtime": 14.2343,
      "eval_samples_per_second": 430.158,
      "eval_steps_per_second": 143.386,
      "step": 1
    },
    {
      "epoch": 0.0009284332688588008,
      "grad_norm": 0.03615349903702736,
      "learning_rate": 8.999999999999999e-05,
      "loss": 10.3744,
      "step": 3
    },
    {
      "epoch": 0.0018568665377176016,
      "grad_norm": 0.04060865938663483,
      "learning_rate": 0.00017999999999999998,
      "loss": 10.3731,
      "step": 6
    },
    {
      "epoch": 0.0024758220502901353,
      "eval_loss": 10.372960090637207,
      "eval_runtime": 14.2469,
      "eval_samples_per_second": 429.779,
      "eval_steps_per_second": 143.26,
      "step": 8
    },
    {
      "epoch": 0.0027852998065764022,
      "grad_norm": 0.04149027168750763,
      "learning_rate": 0.00027,
      "loss": 10.3733,
      "step": 9
    },
    {
      "epoch": 0.003713733075435203,
      "grad_norm": 0.042886920273303986,
      "learning_rate": 0.00029265847744427303,
      "loss": 10.3725,
      "step": 12
    },
    {
      "epoch": 0.0046421663442940036,
      "grad_norm": 0.04727409780025482,
      "learning_rate": 0.00025606601717798207,
      "loss": 10.3698,
      "step": 15
    },
    {
      "epoch": 0.0049516441005802705,
      "eval_loss": 10.369811058044434,
      "eval_runtime": 14.2492,
      "eval_samples_per_second": 429.709,
      "eval_steps_per_second": 143.236,
      "step": 16
    },
    {
      "epoch": 0.0055705996131528044,
      "grad_norm": 0.04473396763205528,
      "learning_rate": 0.0001963525491562421,
      "loss": 10.3694,
      "step": 18
    },
    {
      "epoch": 0.006499032882011605,
      "grad_norm": 0.06059557572007179,
      "learning_rate": 0.00012653483024396533,
      "loss": 10.3673,
      "step": 21
    },
    {
      "epoch": 0.007427466150870406,
      "grad_norm": 0.05967845022678375,
      "learning_rate": 6.183221215612904e-05,
      "loss": 10.3669,
      "step": 24
    },
    {
      "epoch": 0.007427466150870406,
      "eval_loss": 10.367446899414062,
      "eval_runtime": 14.2805,
      "eval_samples_per_second": 428.767,
      "eval_steps_per_second": 142.922,
      "step": 24
    },
    {
      "epoch": 0.008355899419729206,
      "grad_norm": 0.06560368090867996,
      "learning_rate": 1.634902137174483e-05,
      "loss": 10.368,
      "step": 27
    },
    {
      "epoch": 0.009284332688588007,
      "grad_norm": 0.06149117276072502,
      "learning_rate": 0.0,
      "loss": 10.3674,
      "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": 3530415144960.0,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}