Hugging Face's logo

Aivesa
/
6de393f4-ef2f-45d5-9093-ef6e0404bb59

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
6de393f4-ef2f-45d5-9093-ef6e0404bb59
File size: 2,968 Bytes 
e66e3a7
 
 
15d1c7c
e66e3a7
15d1c7c
e66e3a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d78f26b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1c53cc9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15d1c7c
 
 
 
 
 
 
e66e3a7
 
 
 
 
 
 
 
 
 
 
 
 
 
15d1c7c
e66e3a7
 
 
 
15d1c7c
e66e3a7
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.019782393669634024,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019782393669634025,
      "grad_norm": 1.4230250120162964,
      "learning_rate": 2e-05,
      "loss": 3.2187,
      "step": 1
    },
    {
      "epoch": 0.003956478733926805,
      "grad_norm": 1.3153244256973267,
      "learning_rate": 4e-05,
      "loss": 3.2003,
      "step": 2
    },
    {
      "epoch": 0.005934718100890208,
      "grad_norm": 1.88228178024292,
      "learning_rate": 6e-05,
      "loss": 3.3319,
      "step": 3
    },
    {
      "epoch": 0.005934718100890208,
      "eval_loss": 3.3604626655578613,
      "eval_runtime": 12.0631,
      "eval_samples_per_second": 17.657,
      "eval_steps_per_second": 8.87,
      "step": 3
    },
    {
      "epoch": 0.00791295746785361,
      "grad_norm": 1.8003789186477661,
      "learning_rate": 8e-05,
      "loss": 3.35,
      "step": 4
    },
    {
      "epoch": 0.009891196834817012,
      "grad_norm": 1.578134298324585,
      "learning_rate": 0.0001,
      "loss": 3.1165,
      "step": 5
    },
    {
      "epoch": 0.011869436201780416,
      "grad_norm": 1.6146352291107178,
      "learning_rate": 0.00012,
      "loss": 3.1276,
      "step": 6
    },
    {
      "epoch": 0.011869436201780416,
      "eval_loss": 3.161781072616577,
      "eval_runtime": 14.4687,
      "eval_samples_per_second": 14.721,
      "eval_steps_per_second": 7.395,
      "step": 6
    },
    {
      "epoch": 0.013847675568743818,
      "grad_norm": 1.8498936891555786,
      "learning_rate": 0.00014,
      "loss": 3.0711,
      "step": 7
    },
    {
      "epoch": 0.01582591493570722,
      "grad_norm": 1.8731578588485718,
      "learning_rate": 0.00016,
      "loss": 2.6369,
      "step": 8
    },
    {
      "epoch": 0.017804154302670624,
      "grad_norm": 2.1558492183685303,
      "learning_rate": 0.00018,
      "loss": 2.8718,
      "step": 9
    },
    {
      "epoch": 0.017804154302670624,
      "eval_loss": 2.8179714679718018,
      "eval_runtime": 12.1815,
      "eval_samples_per_second": 17.486,
      "eval_steps_per_second": 8.784,
      "step": 9
    },
    {
      "epoch": 0.019782393669634024,
      "grad_norm": 2.164289712905884,
      "learning_rate": 0.0002,
      "loss": 2.5339,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}