Hugging Face's logo

vermoney
/
bce83261-59e2-4cd8-a0cd-4b29419a167e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
bce83261-59e2-4cd8-a0cd-4b29419a167e
File size: 3,112 Bytes 
b7e899d
118fb35
 
 
b7e899d
118fb35
b7e899d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
118fb35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b7e899d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
118fb35
b7e899d
 
 
 
 
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": 2.1080482006073,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0004278967271249084,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.139483635624542e-05,
      "eval_loss": 3.7243804931640625,
      "eval_runtime": 4109.2563,
      "eval_samples_per_second": 4.789,
      "eval_steps_per_second": 2.395,
      "step": 1
    },
    {
      "epoch": 6.418450906873626e-05,
      "grad_norm": 3.968533515930176,
      "learning_rate": 6e-05,
      "loss": 3.7514,
      "step": 3
    },
    {
      "epoch": 0.0001069741817812271,
      "eval_loss": 3.2054860591888428,
      "eval_runtime": 4160.1692,
      "eval_samples_per_second": 4.731,
      "eval_steps_per_second": 2.366,
      "step": 5
    },
    {
      "epoch": 0.0001283690181374725,
      "grad_norm": 3.128091335296631,
      "learning_rate": 9.96057350657239e-05,
      "loss": 3.5579,
      "step": 6
    },
    {
      "epoch": 0.0001925535272062088,
      "grad_norm": 3.7288057804107666,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.9508,
      "step": 9
    },
    {
      "epoch": 0.0002139483635624542,
      "eval_loss": 2.416006088256836,
      "eval_runtime": 4139.1781,
      "eval_samples_per_second": 4.755,
      "eval_steps_per_second": 2.378,
      "step": 10
    },
    {
      "epoch": 0.000256738036274945,
      "grad_norm": 2.4281444549560547,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.5208,
      "step": 12
    },
    {
      "epoch": 0.0003209225453436813,
      "grad_norm": 2.5710904598236084,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.3017,
      "step": 15
    },
    {
      "epoch": 0.0003209225453436813,
      "eval_loss": 2.1858015060424805,
      "eval_runtime": 4147.3041,
      "eval_samples_per_second": 4.745,
      "eval_steps_per_second": 2.373,
      "step": 15
    },
    {
      "epoch": 0.0003851070544124176,
      "grad_norm": 2.126551866531372,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 2.24,
      "step": 18
    },
    {
      "epoch": 0.0004278967271249084,
      "eval_loss": 2.1080482006073,
      "eval_runtime": 4146.2513,
      "eval_samples_per_second": 4.747,
      "eval_steps_per_second": 2.373,
      "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": 7418872835604480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}