Hugging Face's logo

joboffer
/
d827ca30-b98d-4026-aaff-71c94869a653

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
d827ca30-b98d-4026-aaff-71c94869a653
File size: 3,093 Bytes 
4909bd8
3ecd400
 
 
4909bd8
3ecd400
4909bd8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ecd400
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4909bd8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ecd400
4909bd8
 
 
 
 
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": 1.0417708158493042,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.040160642570281124,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002008032128514056,
      "eval_loss": 1.3232147693634033,
      "eval_runtime": 72.9359,
      "eval_samples_per_second": 2.879,
      "eval_steps_per_second": 1.44,
      "step": 1
    },
    {
      "epoch": 0.006024096385542169,
      "grad_norm": 1.1903401613235474,
      "learning_rate": 6e-05,
      "loss": 5.3337,
      "step": 3
    },
    {
      "epoch": 0.010040160642570281,
      "eval_loss": 1.29500150680542,
      "eval_runtime": 73.686,
      "eval_samples_per_second": 2.85,
      "eval_steps_per_second": 1.425,
      "step": 5
    },
    {
      "epoch": 0.012048192771084338,
      "grad_norm": 3.233403444290161,
      "learning_rate": 9.96057350657239e-05,
      "loss": 5.3897,
      "step": 6
    },
    {
      "epoch": 0.018072289156626505,
      "grad_norm": 1.7138043642044067,
      "learning_rate": 9.381533400219318e-05,
      "loss": 4.3576,
      "step": 9
    },
    {
      "epoch": 0.020080321285140562,
      "eval_loss": 1.1749109029769897,
      "eval_runtime": 73.6686,
      "eval_samples_per_second": 2.851,
      "eval_steps_per_second": 1.425,
      "step": 10
    },
    {
      "epoch": 0.024096385542168676,
      "grad_norm": 1.7703816890716553,
      "learning_rate": 8.18711994874345e-05,
      "loss": 4.5346,
      "step": 12
    },
    {
      "epoch": 0.030120481927710843,
      "grad_norm": 8.211416244506836,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.7168,
      "step": 15
    },
    {
      "epoch": 0.030120481927710843,
      "eval_loss": 1.092099905014038,
      "eval_runtime": 73.6836,
      "eval_samples_per_second": 2.85,
      "eval_steps_per_second": 1.425,
      "step": 15
    },
    {
      "epoch": 0.03614457831325301,
      "grad_norm": 1.9411234855651855,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 4.1431,
      "step": 18
    },
    {
      "epoch": 0.040160642570281124,
      "eval_loss": 1.0417708158493042,
      "eval_runtime": 73.76,
      "eval_samples_per_second": 2.847,
      "eval_steps_per_second": 1.424,
      "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": 2.57085482729472e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}