Hugging Face's logo

kostiantynk1205
/
a9957f3b-22c9-4b98-b0bc-bb87823dbcf3

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
a9957f3b-22c9-4b98-b0bc-bb87823dbcf3
File size: 2,964 Bytes 
dfcd3f2
 
 
d35c7d5
dfcd3f2
d35c7d5
dfcd3f2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f937cbe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70ed0fd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d35c7d5
 
 
 
 
 
 
dfcd3f2
 
 
 
 
 
 
 
 
 
 
 
 
 
d35c7d5
dfcd3f2
 
 
 
d35c7d5
dfcd3f2
 
 
 
 
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": 0.003321983223984719,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033219832239847187,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.00033219832239847187,
      "eval_loss": NaN,
      "eval_runtime": 127.9865,
      "eval_samples_per_second": 9.907,
      "eval_steps_per_second": 4.954,
      "step": 1
    },
    {
      "epoch": 0.0006643966447969437,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0009965949671954157,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0009965949671954157,
      "eval_loss": NaN,
      "eval_runtime": 127.3094,
      "eval_samples_per_second": 9.96,
      "eval_steps_per_second": 4.98,
      "step": 3
    },
    {
      "epoch": 0.0013287932895938875,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0016609916119923595,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0019931899343908314,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0019931899343908314,
      "eval_loss": NaN,
      "eval_runtime": 127.4114,
      "eval_samples_per_second": 9.952,
      "eval_steps_per_second": 4.976,
      "step": 6
    },
    {
      "epoch": 0.002325388256789303,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.002657586579187775,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.002989784901586247,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 1.5199,
      "step": 9
    },
    {
      "epoch": 0.002989784901586247,
      "eval_loss": NaN,
      "eval_runtime": 127.4964,
      "eval_samples_per_second": 9.945,
      "eval_steps_per_second": 4.973,
      "step": 9
    },
    {
      "epoch": 0.003321983223984719,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6893996794183680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}