Hugging Face's logo

kokovova
/
40d67707-4edc-4585-b8da-3e5f220cbdee

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
1
40d67707-4edc-4585-b8da-3e5f220cbdee
File size: 3,279 Bytes 
b2c5892
 
 
956c67e
b2c5892
956c67e
b2c5892
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43504e4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
956c67e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b2c5892
 
 
 
 
 
 
 
 
 
 
 
 
 
956c67e
b2c5892
 
 
 
956c67e
b2c5892
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04432951606944958,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014776505356483192,
      "eval_loss": 2.284550189971924,
      "eval_runtime": 8.0244,
      "eval_samples_per_second": 35.517,
      "eval_steps_per_second": 17.821,
      "step": 1
    },
    {
      "epoch": 0.004432951606944958,
      "grad_norm": 1.086187481880188,
      "learning_rate": 6e-05,
      "loss": 2.246,
      "step": 3
    },
    {
      "epoch": 0.008865903213889916,
      "grad_norm": 0.9703373908996582,
      "learning_rate": 0.00012,
      "loss": 2.3058,
      "step": 6
    },
    {
      "epoch": 0.011821204285186553,
      "eval_loss": 2.1647727489471436,
      "eval_runtime": 6.9073,
      "eval_samples_per_second": 41.261,
      "eval_steps_per_second": 20.703,
      "step": 8
    },
    {
      "epoch": 0.013298854820834873,
      "grad_norm": 1.1059170961380005,
      "learning_rate": 0.00018,
      "loss": 2.2392,
      "step": 9
    },
    {
      "epoch": 0.01773180642777983,
      "grad_norm": 0.8991310596466064,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.0468,
      "step": 12
    },
    {
      "epoch": 0.02216475803472479,
      "grad_norm": 1.0070017576217651,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.9515,
      "step": 15
    },
    {
      "epoch": 0.023642408570373107,
      "eval_loss": 1.9984503984451294,
      "eval_runtime": 6.9326,
      "eval_samples_per_second": 41.11,
      "eval_steps_per_second": 20.627,
      "step": 16
    },
    {
      "epoch": 0.026597709641669746,
      "grad_norm": 1.078281044960022,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.9955,
      "step": 18
    },
    {
      "epoch": 0.031030661248614703,
      "grad_norm": 1.1806660890579224,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.0976,
      "step": 21
    },
    {
      "epoch": 0.03546361285555966,
      "grad_norm": 0.9979068040847778,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.9791,
      "step": 24
    },
    {
      "epoch": 0.03546361285555966,
      "eval_loss": 1.9604854583740234,
      "eval_runtime": 6.975,
      "eval_samples_per_second": 40.86,
      "eval_steps_per_second": 20.502,
      "step": 24
    },
    {
      "epoch": 0.03989656446250462,
      "grad_norm": 0.8984552621841431,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.9597,
      "step": 27
    },
    {
      "epoch": 0.04432951606944958,
      "grad_norm": 1.0433257818222046,
      "learning_rate": 0.0,
      "loss": 1.9852,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1959403255234560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}