Hugging Face's logo

vmpsergio
/
8c05ee18-6ea1-4ba1-9315-5ff33ba91f45

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
8c05ee18-6ea1-4ba1-9315-5ff33ba91f45
File size: 2,394 Bytes 
62fd85f
 
 
717e24b
62fd85f
717e24b
62fd85f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
717e24b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62fd85f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
717e24b
62fd85f
 
 
 
 
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": 0.04810583283223091,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024052916416115455,
      "eval_loss": 2.8067831993103027,
      "eval_runtime": 3.6543,
      "eval_samples_per_second": 47.889,
      "eval_steps_per_second": 24.082,
      "step": 1
    },
    {
      "epoch": 0.0072158749248346366,
      "grad_norm": 0.44602859020233154,
      "learning_rate": 6e-05,
      "loss": 2.9609,
      "step": 3
    },
    {
      "epoch": 0.014431749849669273,
      "grad_norm": 0.6594803333282471,
      "learning_rate": 0.00012,
      "loss": 3.0153,
      "step": 6
    },
    {
      "epoch": 0.019242333132892364,
      "eval_loss": 2.7753758430480957,
      "eval_runtime": 2.4839,
      "eval_samples_per_second": 70.453,
      "eval_steps_per_second": 35.428,
      "step": 8
    },
    {
      "epoch": 0.02164762477450391,
      "grad_norm": 0.4808473289012909,
      "learning_rate": 0.00018,
      "loss": 3.1571,
      "step": 9
    },
    {
      "epoch": 0.028863499699338546,
      "grad_norm": 0.5767693519592285,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.8209,
      "step": 12
    },
    {
      "epoch": 0.03607937462417318,
      "grad_norm": 1.131788969039917,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.978,
      "step": 15
    },
    {
      "epoch": 0.03848466626578473,
      "eval_loss": 2.703683614730835,
      "eval_runtime": 2.6207,
      "eval_samples_per_second": 66.776,
      "eval_steps_per_second": 33.579,
      "step": 16
    },
    {
      "epoch": 0.04329524954900782,
      "grad_norm": 0.47926196455955505,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.8346,
      "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": 138837586083840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}