Hugging Face's logo

filipesantoscv11
/
7bb66c70-c6d0-4860-beaf-8beb46ece2ba

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
7bb66c70-c6d0-4860-beaf-8beb46ece2ba
File size: 2,656 Bytes 
b0b408b
 
 
7494cd4
b0b408b
7494cd4
b0b408b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7494cd4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b0b408b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7494cd4
b0b408b
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002178708570494839,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010893542852474196,
      "eval_loss": NaN,
      "eval_runtime": 237.3388,
      "eval_samples_per_second": 16.289,
      "eval_steps_per_second": 8.144,
      "step": 1
    },
    {
      "epoch": 0.0003268062855742259,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005446771426237097,
      "eval_loss": NaN,
      "eval_runtime": 237.3222,
      "eval_samples_per_second": 16.29,
      "eval_steps_per_second": 8.145,
      "step": 5
    },
    {
      "epoch": 0.0006536125711484518,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0009804188567226777,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0010893542852474195,
      "eval_loss": NaN,
      "eval_runtime": 237.3799,
      "eval_samples_per_second": 16.286,
      "eval_steps_per_second": 8.143,
      "step": 10
    },
    {
      "epoch": 0.0013072251422969036,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0016340314278711294,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0016340314278711294,
      "eval_loss": NaN,
      "eval_runtime": 237.3995,
      "eval_samples_per_second": 16.285,
      "eval_steps_per_second": 8.142,
      "step": 15
    },
    {
      "epoch": 0.0019608377134453553,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.002178708570494839,
      "eval_loss": NaN,
      "eval_runtime": 237.3389,
      "eval_samples_per_second": 16.289,
      "eval_steps_per_second": 8.144,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7220940609945600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}