Hugging Face's logo

ardaspear
/
63bd93dc-ce75-4513-ac10-cade1bba594e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
63bd93dc-ce75-4513-ac10-cade1bba594e
File size: 3,587 Bytes 
c4935eb
 
 
8a466f2
c4935eb
8a466f2
c4935eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fec571e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
392bc04
 
 
 
 
 
 
 
 
 
 
 
 
 
 
08b0380
 
 
 
 
 
 
 
 
 
 
 
 
 
 
df133f8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7d56fcb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a466f2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c4935eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8a466f2
c4935eb
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7872340425531914,
  "eval_steps": 3,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0851063829787234,
      "eval_loss": 3.537301540374756,
      "eval_runtime": 0.8155,
      "eval_samples_per_second": 24.526,
      "eval_steps_per_second": 3.679,
      "step": 1
    },
    {
      "epoch": 0.2553191489361702,
      "grad_norm": 4.053133964538574,
      "learning_rate": 3e-05,
      "loss": 3.9013,
      "step": 3
    },
    {
      "epoch": 0.2553191489361702,
      "eval_loss": 3.498924732208252,
      "eval_runtime": 0.4147,
      "eval_samples_per_second": 48.228,
      "eval_steps_per_second": 7.234,
      "step": 3
    },
    {
      "epoch": 0.5106382978723404,
      "grad_norm": 3.631814479827881,
      "learning_rate": 6e-05,
      "loss": 3.5773,
      "step": 6
    },
    {
      "epoch": 0.5106382978723404,
      "eval_loss": 3.226794481277466,
      "eval_runtime": 0.4126,
      "eval_samples_per_second": 48.473,
      "eval_steps_per_second": 7.271,
      "step": 6
    },
    {
      "epoch": 0.7659574468085106,
      "grad_norm": 3.4452314376831055,
      "learning_rate": 9e-05,
      "loss": 3.432,
      "step": 9
    },
    {
      "epoch": 0.7659574468085106,
      "eval_loss": 3.062047243118286,
      "eval_runtime": 0.416,
      "eval_samples_per_second": 48.077,
      "eval_steps_per_second": 7.211,
      "step": 9
    },
    {
      "epoch": 1.0212765957446808,
      "grad_norm": 4.869143962860107,
      "learning_rate": 9.85470908713026e-05,
      "loss": 3.4585,
      "step": 12
    },
    {
      "epoch": 1.0212765957446808,
      "eval_loss": 2.945756196975708,
      "eval_runtime": 0.4153,
      "eval_samples_per_second": 48.158,
      "eval_steps_per_second": 7.224,
      "step": 12
    },
    {
      "epoch": 1.2765957446808511,
      "grad_norm": 3.5793509483337402,
      "learning_rate": 9.114919329468282e-05,
      "loss": 2.8128,
      "step": 15
    },
    {
      "epoch": 1.2765957446808511,
      "eval_loss": 2.8750696182250977,
      "eval_runtime": 0.4152,
      "eval_samples_per_second": 48.165,
      "eval_steps_per_second": 7.225,
      "step": 15
    },
    {
      "epoch": 1.5319148936170213,
      "grad_norm": 3.459306001663208,
      "learning_rate": 7.840323733655778e-05,
      "loss": 2.6305,
      "step": 18
    },
    {
      "epoch": 1.5319148936170213,
      "eval_loss": 2.800814151763916,
      "eval_runtime": 0.4153,
      "eval_samples_per_second": 48.16,
      "eval_steps_per_second": 7.224,
      "step": 18
    },
    {
      "epoch": 1.7872340425531914,
      "grad_norm": 2.895676851272583,
      "learning_rate": 6.19657832143779e-05,
      "loss": 2.6033,
      "step": 21
    },
    {
      "epoch": 1.7872340425531914,
      "eval_loss": 2.7672295570373535,
      "eval_runtime": 0.4158,
      "eval_samples_per_second": 48.098,
      "eval_steps_per_second": 7.215,
      "step": 21
    }
  ],
  "logging_steps": 3,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4204055589027840.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}