Hugging Face's logo

ardaspear
/
5807bbc0-18e4-48a5-aa6e-ba928564ad68

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
5807bbc0-18e4-48a5-aa6e-ba928564ad68
File size: 3,834 Bytes 
488f5f0
 
 
876ac1d
488f5f0
876ac1d
488f5f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d956887
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f449f2c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
876ac1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
488f5f0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
876ac1d
488f5f0
 
 
 
 
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
153
154
155
156
157
158
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1350844277673546,
  "eval_steps": 9,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00375234521575985,
      "eval_loss": 10.385416984558105,
      "eval_runtime": 16.6568,
      "eval_samples_per_second": 13.508,
      "eval_steps_per_second": 3.422,
      "step": 1
    },
    {
      "epoch": 0.01125703564727955,
      "grad_norm": 9.703173637390137,
      "learning_rate": 3e-05,
      "loss": 10.4586,
      "step": 3
    },
    {
      "epoch": 0.0225140712945591,
      "grad_norm": 8.736605644226074,
      "learning_rate": 6e-05,
      "loss": 9.0406,
      "step": 6
    },
    {
      "epoch": 0.03377110694183865,
      "grad_norm": 9.648565292358398,
      "learning_rate": 9e-05,
      "loss": 5.2104,
      "step": 9
    },
    {
      "epoch": 0.03377110694183865,
      "eval_loss": 1.994680404663086,
      "eval_runtime": 16.3241,
      "eval_samples_per_second": 13.783,
      "eval_steps_per_second": 3.492,
      "step": 9
    },
    {
      "epoch": 0.0450281425891182,
      "grad_norm": 5.035146713256836,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.5712,
      "step": 12
    },
    {
      "epoch": 0.05628517823639775,
      "grad_norm": 6.059263706207275,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6058,
      "step": 15
    },
    {
      "epoch": 0.0675422138836773,
      "grad_norm": 2.648972511291504,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.3104,
      "step": 18
    },
    {
      "epoch": 0.0675422138836773,
      "eval_loss": 0.18601766228675842,
      "eval_runtime": 16.4012,
      "eval_samples_per_second": 13.719,
      "eval_steps_per_second": 3.475,
      "step": 18
    },
    {
      "epoch": 0.07879924953095685,
      "grad_norm": 7.399054050445557,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.2436,
      "step": 21
    },
    {
      "epoch": 0.0900562851782364,
      "grad_norm": 3.5452539920806885,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.246,
      "step": 24
    },
    {
      "epoch": 0.10131332082551595,
      "grad_norm": 3.253471851348877,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.1533,
      "step": 27
    },
    {
      "epoch": 0.10131332082551595,
      "eval_loss": 0.11802710592746735,
      "eval_runtime": 16.4414,
      "eval_samples_per_second": 13.685,
      "eval_steps_per_second": 3.467,
      "step": 27
    },
    {
      "epoch": 0.1125703564727955,
      "grad_norm": 0.3799557685852051,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.045,
      "step": 30
    },
    {
      "epoch": 0.12382739212007504,
      "grad_norm": 0.9986750483512878,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0625,
      "step": 33
    },
    {
      "epoch": 0.1350844277673546,
      "grad_norm": 0.397352010011673,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0679,
      "step": 36
    },
    {
      "epoch": 0.1350844277673546,
      "eval_loss": 0.05288050323724747,
      "eval_runtime": 16.4545,
      "eval_samples_per_second": 13.674,
      "eval_steps_per_second": 3.464,
      "step": 36
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.559399633616896e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}