Hugging Face's logo

fedovtt
/
cd11203b-5f42-468f-90fb-5f97b232714e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
cd11203b-5f42-468f-90fb-5f97b232714e
File size: 3,691 Bytes 
652f438
 
 
e8067d5
652f438
e8067d5
652f438
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e8067d5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
652f438
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e8067d5
652f438
 
 
 
 
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
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003719546215361726,
  "eval_steps": 2,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003719546215361726,
      "grad_norm": 28.77135467529297,
      "learning_rate": 2e-05,
      "loss": 45.9604,
      "step": 1
    },
    {
      "epoch": 0.0003719546215361726,
      "eval_loss": 11.40648078918457,
      "eval_runtime": 137.0275,
      "eval_samples_per_second": 8.261,
      "eval_steps_per_second": 4.131,
      "step": 1
    },
    {
      "epoch": 0.0007439092430723452,
      "grad_norm": 23.410951614379883,
      "learning_rate": 4e-05,
      "loss": 46.8527,
      "step": 2
    },
    {
      "epoch": 0.0007439092430723452,
      "eval_loss": 11.40257453918457,
      "eval_runtime": 137.8996,
      "eval_samples_per_second": 8.209,
      "eval_steps_per_second": 4.104,
      "step": 2
    },
    {
      "epoch": 0.0011158638646085177,
      "grad_norm": 33.30792999267578,
      "learning_rate": 6e-05,
      "loss": 44.8008,
      "step": 3
    },
    {
      "epoch": 0.0014878184861446904,
      "grad_norm": 27.510290145874023,
      "learning_rate": 8e-05,
      "loss": 48.3234,
      "step": 4
    },
    {
      "epoch": 0.0014878184861446904,
      "eval_loss": 11.253341674804688,
      "eval_runtime": 138.0011,
      "eval_samples_per_second": 8.203,
      "eval_steps_per_second": 4.101,
      "step": 4
    },
    {
      "epoch": 0.001859773107680863,
      "grad_norm": 23.642324447631836,
      "learning_rate": 0.0001,
      "loss": 42.2976,
      "step": 5
    },
    {
      "epoch": 0.0022317277292170355,
      "grad_norm": 37.700042724609375,
      "learning_rate": 9.755282581475769e-05,
      "loss": 42.5346,
      "step": 6
    },
    {
      "epoch": 0.0022317277292170355,
      "eval_loss": 10.256876945495605,
      "eval_runtime": 138.1284,
      "eval_samples_per_second": 8.195,
      "eval_steps_per_second": 4.098,
      "step": 6
    },
    {
      "epoch": 0.002603682350753208,
      "grad_norm": 46.39228057861328,
      "learning_rate": 9.045084971874738e-05,
      "loss": 39.644,
      "step": 7
    },
    {
      "epoch": 0.0029756369722893808,
      "grad_norm": 47.501041412353516,
      "learning_rate": 7.938926261462366e-05,
      "loss": 35.7466,
      "step": 8
    },
    {
      "epoch": 0.0029756369722893808,
      "eval_loss": 7.803372859954834,
      "eval_runtime": 138.0673,
      "eval_samples_per_second": 8.199,
      "eval_steps_per_second": 4.099,
      "step": 8
    },
    {
      "epoch": 0.0033475915938255534,
      "grad_norm": 45.90718460083008,
      "learning_rate": 6.545084971874738e-05,
      "loss": 31.2201,
      "step": 9
    },
    {
      "epoch": 0.003719546215361726,
      "grad_norm": 51.53364181518555,
      "learning_rate": 5e-05,
      "loss": 23.9333,
      "step": 10
    },
    {
      "epoch": 0.003719546215361726,
      "eval_loss": 5.604811191558838,
      "eval_runtime": 138.2369,
      "eval_samples_per_second": 8.189,
      "eval_steps_per_second": 4.094,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6332408345395200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}