Hugging Face's logo

fedovtt
/
f9eb2fff-bae0-49b0-89c5-624fc71c75d0

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
f9eb2fff-bae0-49b0-89c5-624fc71c75d0
File size: 3,307 Bytes 
c394a31
 
 
308a8f5
c394a31
308a8f5
c394a31
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
686e49c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308a8f5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c394a31
 
 
 
 
 
 
 
 
 
 
 
 
 
308a8f5
c394a31
 
 
 
308a8f5
c394a31
 
 
 
 
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
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002956101886978371,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.853672956594571e-05,
      "eval_loss": 2.3153233528137207,
      "eval_runtime": 48.8077,
      "eval_samples_per_second": 87.548,
      "eval_steps_per_second": 43.784,
      "step": 1
    },
    {
      "epoch": 0.0002956101886978371,
      "grad_norm": 0.6262503266334534,
      "learning_rate": 6e-05,
      "loss": 1.9752,
      "step": 3
    },
    {
      "epoch": 0.0005912203773956742,
      "grad_norm": 0.6291804313659668,
      "learning_rate": 0.00012,
      "loss": 2.0395,
      "step": 6
    },
    {
      "epoch": 0.0007882938365275657,
      "eval_loss": 2.1891775131225586,
      "eval_runtime": 47.5423,
      "eval_samples_per_second": 89.878,
      "eval_steps_per_second": 44.949,
      "step": 8
    },
    {
      "epoch": 0.0008868305660935114,
      "grad_norm": 0.47909072041511536,
      "learning_rate": 0.00018,
      "loss": 1.9808,
      "step": 9
    },
    {
      "epoch": 0.0011824407547913484,
      "grad_norm": 0.39736393094062805,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.9289,
      "step": 12
    },
    {
      "epoch": 0.0014780509434891855,
      "grad_norm": 0.40689948201179504,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.9195,
      "step": 15
    },
    {
      "epoch": 0.0015765876730551313,
      "eval_loss": 2.001293659210205,
      "eval_runtime": 47.6644,
      "eval_samples_per_second": 89.648,
      "eval_steps_per_second": 44.834,
      "step": 16
    },
    {
      "epoch": 0.0017736611321870228,
      "grad_norm": 0.4287497401237488,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.7583,
      "step": 18
    },
    {
      "epoch": 0.00206927132088486,
      "grad_norm": 0.49251097440719604,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.8483,
      "step": 21
    },
    {
      "epoch": 0.002364881509582697,
      "grad_norm": 0.4831303358078003,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.8595,
      "step": 24
    },
    {
      "epoch": 0.002364881509582697,
      "eval_loss": 1.9419726133346558,
      "eval_runtime": 47.6991,
      "eval_samples_per_second": 89.582,
      "eval_steps_per_second": 44.802,
      "step": 24
    },
    {
      "epoch": 0.002660491698280534,
      "grad_norm": 0.4990459680557251,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.8028,
      "step": 27
    },
    {
      "epoch": 0.002956101886978371,
      "grad_norm": 0.35253778100013733,
      "learning_rate": 0.0,
      "loss": 1.7524,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 279410641993728.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}