Hugging Face's logo

bbytxt
/
ada51c68-5a51-4990-9e99-7ff8d05bc6f9

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
ada51c68-5a51-4990-9e99-7ff8d05bc6f9
File size: 3,672 Bytes 
5cb9539
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.3157894736842106,
  "eval_steps": 50,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 41.065494537353516,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 7.6156,
      "step": 1
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 7.460348129272461,
      "eval_runtime": 0.3018,
      "eval_samples_per_second": 26.509,
      "eval_steps_per_second": 13.254,
      "step": 1
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 45.48214340209961,
      "learning_rate": 6.666666666666667e-06,
      "loss": 7.4887,
      "step": 2
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 39.209571838378906,
      "learning_rate": 1e-05,
      "loss": 7.4095,
      "step": 3
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 36.979095458984375,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 7.3312,
      "step": 4
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 54.07901382446289,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 9.962,
      "step": 5
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 44.620147705078125,
      "learning_rate": 2e-05,
      "loss": 6.0482,
      "step": 6
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 40.011993408203125,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 5.3659,
      "step": 7
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 28.986406326293945,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 3.4974,
      "step": 8
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 30.311237335205078,
      "learning_rate": 3e-05,
      "loss": 3.4766,
      "step": 9
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 12.783985137939453,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.3461,
      "step": 10
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 8.035650253295898,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 1.1558,
      "step": 11
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 7.6682515144348145,
      "learning_rate": 4e-05,
      "loss": 1.0517,
      "step": 12
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 4.046804428100586,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.7306,
      "step": 13
    },
    {
      "epoch": 3.1052631578947367,
      "grad_norm": 7.9675374031066895,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.111,
      "step": 14
    },
    {
      "epoch": 3.3157894736842106,
      "grad_norm": 3.6621782779693604,
      "learning_rate": 5e-05,
      "loss": 0.6098,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4082170960281600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}