Hugging Face's logo

vmpsergio
/
f8f011d0-3803-4b0e-ad9a-62eeeacef160

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
f8f011d0-3803-4b0e-ad9a-62eeeacef160
File size: 3,281 Bytes 
8414f71
 
 
799328a
8414f71
799328a
8414f71
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9dd2b6f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
799328a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8414f71
 
 
 
 
 
 
 
 
 
 
 
 
 
799328a
8414f71
 
 
 
799328a
8414f71
 
 
 
 
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": 0.13986013986013987,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004662004662004662,
      "eval_loss": 1.0004037618637085,
      "eval_runtime": 25.7703,
      "eval_samples_per_second": 3.531,
      "eval_steps_per_second": 1.785,
      "step": 1
    },
    {
      "epoch": 0.013986013986013986,
      "grad_norm": 0.3392694592475891,
      "learning_rate": 6e-05,
      "loss": 0.9517,
      "step": 3
    },
    {
      "epoch": 0.027972027972027972,
      "grad_norm": 0.4344029426574707,
      "learning_rate": 0.00012,
      "loss": 0.9839,
      "step": 6
    },
    {
      "epoch": 0.037296037296037296,
      "eval_loss": 0.8890663385391235,
      "eval_runtime": 24.876,
      "eval_samples_per_second": 3.658,
      "eval_steps_per_second": 1.849,
      "step": 8
    },
    {
      "epoch": 0.04195804195804196,
      "grad_norm": 0.4226091802120209,
      "learning_rate": 0.00018,
      "loss": 0.8539,
      "step": 9
    },
    {
      "epoch": 0.055944055944055944,
      "grad_norm": 0.37416017055511475,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.7767,
      "step": 12
    },
    {
      "epoch": 0.06993006993006994,
      "grad_norm": 0.3611030876636505,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.7492,
      "step": 15
    },
    {
      "epoch": 0.07459207459207459,
      "eval_loss": 0.7391844391822815,
      "eval_runtime": 24.8047,
      "eval_samples_per_second": 3.669,
      "eval_steps_per_second": 1.854,
      "step": 16
    },
    {
      "epoch": 0.08391608391608392,
      "grad_norm": 0.42007654905319214,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6869,
      "step": 18
    },
    {
      "epoch": 0.0979020979020979,
      "grad_norm": 0.27399227023124695,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.6309,
      "step": 21
    },
    {
      "epoch": 0.11188811188811189,
      "grad_norm": 0.2571362257003784,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.6143,
      "step": 24
    },
    {
      "epoch": 0.11188811188811189,
      "eval_loss": 0.7011677026748657,
      "eval_runtime": 24.8687,
      "eval_samples_per_second": 3.659,
      "eval_steps_per_second": 1.85,
      "step": 24
    },
    {
      "epoch": 0.1258741258741259,
      "grad_norm": 0.29638007283210754,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.5993,
      "step": 27
    },
    {
      "epoch": 0.13986013986013987,
      "grad_norm": 0.317417711019516,
      "learning_rate": 0.0,
      "loss": 0.7743,
      "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": 1.0373648955211776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}