Hugging Face's logo

vertings6
/
3b93eff0-5fb7-47bf-acde-797e3082cb42

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
3b93eff0-5fb7-47bf-acde-797e3082cb42
File size: 3,106 Bytes 
0872dce
85ed8c5
 
 
0872dce
85ed8c5
0872dce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85ed8c5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0872dce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85ed8c5
0872dce
 
 
 
 
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
 
{
  "best_metric": 2.0634360313415527,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.07640878701050621,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038204393505253103,
      "eval_loss": 2.355255603790283,
      "eval_runtime": 86.6983,
      "eval_samples_per_second": 2.549,
      "eval_steps_per_second": 0.646,
      "step": 1
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 0.22021570801734924,
      "learning_rate": 0.00012,
      "loss": 2.3681,
      "step": 3
    },
    {
      "epoch": 0.019102196752626553,
      "eval_loss": 2.2745025157928467,
      "eval_runtime": 87.0605,
      "eval_samples_per_second": 2.538,
      "eval_steps_per_second": 0.643,
      "step": 5
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 0.3847930133342743,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.2964,
      "step": 6
    },
    {
      "epoch": 0.034383954154727794,
      "grad_norm": 0.19991150498390198,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.2225,
      "step": 9
    },
    {
      "epoch": 0.038204393505253106,
      "eval_loss": 2.1533548831939697,
      "eval_runtime": 86.9934,
      "eval_samples_per_second": 2.54,
      "eval_steps_per_second": 0.644,
      "step": 10
    },
    {
      "epoch": 0.045845272206303724,
      "grad_norm": 0.16003547608852386,
      "learning_rate": 0.000163742398974869,
      "loss": 2.1493,
      "step": 12
    },
    {
      "epoch": 0.05730659025787966,
      "grad_norm": 0.17825794219970703,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.1093,
      "step": 15
    },
    {
      "epoch": 0.05730659025787966,
      "eval_loss": 2.093752861022949,
      "eval_runtime": 86.9783,
      "eval_samples_per_second": 2.541,
      "eval_steps_per_second": 0.644,
      "step": 15
    },
    {
      "epoch": 0.06876790830945559,
      "grad_norm": 0.15024003386497498,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.1147,
      "step": 18
    },
    {
      "epoch": 0.07640878701050621,
      "eval_loss": 2.0634360313415527,
      "eval_runtime": 86.9622,
      "eval_samples_per_second": 2.541,
      "eval_steps_per_second": 0.644,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.0782317576192e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}