Hugging Face's logo

kostiantynk
/
a8d8bb99-de0d-4671-aef9-20896a3e4883

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
a8d8bb99-de0d-4671-aef9-20896a3e4883
File size: 3,194 Bytes 
cfd5022
 
 
0036543
cfd5022
0036543
cfd5022
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ee0b70
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80b5031
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0036543
 
 
 
 
 
 
cfd5022
 
 
 
 
 
 
 
 
 
 
 
 
 
0036543
cfd5022
 
 
 
0036543
cfd5022
 
 
 
 
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": 0.004715868898844612,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004715868898844612,
      "grad_norm": 1.3327773809432983,
      "learning_rate": 2e-05,
      "loss": 2.2718,
      "step": 1
    },
    {
      "epoch": 0.0004715868898844612,
      "eval_loss": 1.7843847274780273,
      "eval_runtime": 17.041,
      "eval_samples_per_second": 52.403,
      "eval_steps_per_second": 26.231,
      "step": 1
    },
    {
      "epoch": 0.0009431737797689225,
      "grad_norm": 1.477419137954712,
      "learning_rate": 4e-05,
      "loss": 1.8746,
      "step": 2
    },
    {
      "epoch": 0.0014147606696533837,
      "grad_norm": 1.2436550855636597,
      "learning_rate": 6e-05,
      "loss": 1.7272,
      "step": 3
    },
    {
      "epoch": 0.0014147606696533837,
      "eval_loss": 1.7788474559783936,
      "eval_runtime": 15.7606,
      "eval_samples_per_second": 56.66,
      "eval_steps_per_second": 28.362,
      "step": 3
    },
    {
      "epoch": 0.001886347559537845,
      "grad_norm": 1.1900620460510254,
      "learning_rate": 8e-05,
      "loss": 1.63,
      "step": 4
    },
    {
      "epoch": 0.002357934449422306,
      "grad_norm": 0.9931256175041199,
      "learning_rate": 0.0001,
      "loss": 1.2157,
      "step": 5
    },
    {
      "epoch": 0.0028295213393067674,
      "grad_norm": 1.1468905210494995,
      "learning_rate": 0.00012,
      "loss": 1.5953,
      "step": 6
    },
    {
      "epoch": 0.0028295213393067674,
      "eval_loss": 1.71695077419281,
      "eval_runtime": 16.058,
      "eval_samples_per_second": 55.611,
      "eval_steps_per_second": 27.837,
      "step": 6
    },
    {
      "epoch": 0.0033011082291912286,
      "grad_norm": 1.1601518392562866,
      "learning_rate": 0.00014,
      "loss": 1.6881,
      "step": 7
    },
    {
      "epoch": 0.00377269511907569,
      "grad_norm": 1.0804229974746704,
      "learning_rate": 0.00016,
      "loss": 1.7769,
      "step": 8
    },
    {
      "epoch": 0.004244282008960151,
      "grad_norm": 1.4835208654403687,
      "learning_rate": 0.00018,
      "loss": 1.9097,
      "step": 9
    },
    {
      "epoch": 0.004244282008960151,
      "eval_loss": 1.6258902549743652,
      "eval_runtime": 15.9442,
      "eval_samples_per_second": 56.008,
      "eval_steps_per_second": 28.035,
      "step": 9
    },
    {
      "epoch": 0.004715868898844612,
      "grad_norm": 1.0217928886413574,
      "learning_rate": 0.0002,
      "loss": 1.4921,
      "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": 100167934279680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}