Hugging Face's logo

dimasik87
/
0216996a-2229-48a5-87d5-f074c6af64d8

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
0216996a-2229-48a5-87d5-f074c6af64d8
File size: 3,650 Bytes 
b275c69
 
 
45631b3
b275c69
45631b3
b275c69
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8629934
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98e25eb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5cb4419
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45631b3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b275c69
 
 
 
 
 
 
 
 
 
 
 
 
 
45631b3
b275c69
 
 
 
45631b3
b275c69
 
 
 
 
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": 0.0003260913871112379,
  "eval_steps": 2,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.260913871112379e-05,
      "grad_norm": 2.9804935455322266,
      "learning_rate": 2e-05,
      "loss": 3.2729,
      "step": 1
    },
    {
      "epoch": 3.260913871112379e-05,
      "eval_loss": 2.8746273517608643,
      "eval_runtime": 399.3712,
      "eval_samples_per_second": 16.168,
      "eval_steps_per_second": 16.168,
      "step": 1
    },
    {
      "epoch": 6.521827742224758e-05,
      "grad_norm": 2.4193668365478516,
      "learning_rate": 4e-05,
      "loss": 2.602,
      "step": 2
    },
    {
      "epoch": 6.521827742224758e-05,
      "eval_loss": 2.8728725910186768,
      "eval_runtime": 400.1947,
      "eval_samples_per_second": 16.135,
      "eval_steps_per_second": 16.135,
      "step": 2
    },
    {
      "epoch": 9.782741613337138e-05,
      "grad_norm": 3.057901620864868,
      "learning_rate": 6e-05,
      "loss": 2.8494,
      "step": 3
    },
    {
      "epoch": 0.00013043655484449516,
      "grad_norm": 2.7539632320404053,
      "learning_rate": 8e-05,
      "loss": 3.3534,
      "step": 4
    },
    {
      "epoch": 0.00013043655484449516,
      "eval_loss": 2.842006206512451,
      "eval_runtime": 400.6337,
      "eval_samples_per_second": 16.117,
      "eval_steps_per_second": 16.117,
      "step": 4
    },
    {
      "epoch": 0.00016304569355561895,
      "grad_norm": 3.022265672683716,
      "learning_rate": 0.0001,
      "loss": 2.176,
      "step": 5
    },
    {
      "epoch": 0.00019565483226674277,
      "grad_norm": 2.7493996620178223,
      "learning_rate": 0.00012,
      "loss": 2.2505,
      "step": 6
    },
    {
      "epoch": 0.00019565483226674277,
      "eval_loss": 2.7171995639801025,
      "eval_runtime": 401.3245,
      "eval_samples_per_second": 16.089,
      "eval_steps_per_second": 16.089,
      "step": 6
    },
    {
      "epoch": 0.00022826397097786656,
      "grad_norm": 3.325737953186035,
      "learning_rate": 0.00014,
      "loss": 2.9736,
      "step": 7
    },
    {
      "epoch": 0.0002608731096889903,
      "grad_norm": 2.959261894226074,
      "learning_rate": 0.00016,
      "loss": 2.8115,
      "step": 8
    },
    {
      "epoch": 0.0002608731096889903,
      "eval_loss": 2.495354413986206,
      "eval_runtime": 400.9211,
      "eval_samples_per_second": 16.105,
      "eval_steps_per_second": 16.105,
      "step": 8
    },
    {
      "epoch": 0.00029348224840011414,
      "grad_norm": 3.5420632362365723,
      "learning_rate": 0.00018,
      "loss": 2.6092,
      "step": 9
    },
    {
      "epoch": 0.0003260913871112379,
      "grad_norm": 3.2168703079223633,
      "learning_rate": 0.0002,
      "loss": 2.1234,
      "step": 10
    },
    {
      "epoch": 0.0003260913871112379,
      "eval_loss": 2.3552844524383545,
      "eval_runtime": 400.4535,
      "eval_samples_per_second": 16.124,
      "eval_steps_per_second": 16.124,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 967722569564160.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}