Hugging Face's logo

VERSIL91
/
993bcbc6-6ee9-428a-9677-00cc99cbaba9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
993bcbc6-6ee9-428a-9677-00cc99cbaba9
File size: 2,680 Bytes 
59be11b
 
 
ff2e90c
59be11b
ff2e90c
59be11b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0f6ee5c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cbdb983
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff2e90c
 
 
 
 
 
 
59be11b
 
 
 
 
 
 
 
 
 
 
 
 
 
ff2e90c
59be11b
 
 
 
ff2e90c
59be11b
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1428571428571428,
  "eval_steps": 2,
  "global_step": 7,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 1.509329080581665,
      "learning_rate": 1e-05,
      "loss": 1.4429,
      "step": 1
    },
    {
      "epoch": 0.16326530612244897,
      "eval_loss": 2.717928171157837,
      "eval_runtime": 95.8731,
      "eval_samples_per_second": 0.115,
      "eval_steps_per_second": 0.063,
      "step": 1
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 1.883664846420288,
      "learning_rate": 2e-05,
      "loss": 1.5643,
      "step": 2
    },
    {
      "epoch": 0.32653061224489793,
      "eval_loss": 2.6112759113311768,
      "eval_runtime": 0.2845,
      "eval_samples_per_second": 38.663,
      "eval_steps_per_second": 21.089,
      "step": 2
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 1.697153091430664,
      "learning_rate": 3e-05,
      "loss": 1.3637,
      "step": 3
    },
    {
      "epoch": 0.6530612244897959,
      "grad_norm": 1.6881253719329834,
      "learning_rate": 4e-05,
      "loss": 1.2991,
      "step": 4
    },
    {
      "epoch": 0.6530612244897959,
      "eval_loss": 2.5000574588775635,
      "eval_runtime": 0.2857,
      "eval_samples_per_second": 38.508,
      "eval_steps_per_second": 21.004,
      "step": 4
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 1.609917402267456,
      "learning_rate": 5e-05,
      "loss": 1.1747,
      "step": 5
    },
    {
      "epoch": 0.9795918367346939,
      "grad_norm": 1.8385484218597412,
      "learning_rate": 6e-05,
      "loss": 1.1581,
      "step": 6
    },
    {
      "epoch": 0.9795918367346939,
      "eval_loss": 2.186253309249878,
      "eval_runtime": 0.2832,
      "eval_samples_per_second": 38.836,
      "eval_steps_per_second": 21.183,
      "step": 6
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 6.098566055297852,
      "learning_rate": 7e-05,
      "loss": 2.4494,
      "step": 7
    }
  ],
  "logging_steps": 1,
  "max_steps": 7,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4655099758510080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}