Hugging Face's logo

sergioalves
/
2ef099a5-268b-43b7-aa6e-2c0b4110a3f3

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
2ef099a5-268b-43b7-aa6e-2c0b4110a3f3
File size: 2,264 Bytes 
3257cee
 
 
075394d
3257cee
075394d
3257cee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
075394d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3257cee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
075394d
3257cee
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00023078831518760207,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1539415759380102e-05,
      "eval_loss": NaN,
      "eval_runtime": 1324.7781,
      "eval_samples_per_second": 27.543,
      "eval_steps_per_second": 13.772,
      "step": 1
    },
    {
      "epoch": 3.4618247278140306e-05,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 6.923649455628061e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 9.231532607504082e-05,
      "eval_loss": NaN,
      "eval_runtime": 1327.3751,
      "eval_samples_per_second": 27.49,
      "eval_steps_per_second": 13.745,
      "step": 8
    },
    {
      "epoch": 0.00010385474183442092,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00013847298911256122,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.00017309123639070153,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00018463065215008163,
      "eval_loss": NaN,
      "eval_runtime": 1328.9321,
      "eval_samples_per_second": 27.457,
      "eval_steps_per_second": 13.729,
      "step": 16
    },
    {
      "epoch": 0.00020770948366884183,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    }
  ],
  "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": 317835234508800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}