Hugging Face's logo

jssky
/
aad5141b-cfb2-47f9-8b04-66bf52b989e5

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
aad5141b-cfb2-47f9-8b04-66bf52b989e5
File size: 3,202 Bytes 
d6aeacb
 
 
053bdf9
d6aeacb
053bdf9
d6aeacb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eeac547
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95b5ff2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
053bdf9
 
 
 
 
 
 
d6aeacb
 
 
 
 
 
 
 
 
 
 
 
 
 
053bdf9
d6aeacb
 
 
 
053bdf9
d6aeacb
 
 
 
 
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": 0.0023216669568750362,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00023216669568750363,
      "grad_norm": 2.633310079574585,
      "learning_rate": 2e-05,
      "loss": 2.4602,
      "step": 1
    },
    {
      "epoch": 0.00023216669568750363,
      "eval_loss": 2.4733028411865234,
      "eval_runtime": 198.1616,
      "eval_samples_per_second": 4.577,
      "eval_steps_per_second": 4.577,
      "step": 1
    },
    {
      "epoch": 0.00046433339137500726,
      "grad_norm": 2.2018356323242188,
      "learning_rate": 4e-05,
      "loss": 2.4447,
      "step": 2
    },
    {
      "epoch": 0.0006965000870625109,
      "grad_norm": 2.590804100036621,
      "learning_rate": 6e-05,
      "loss": 2.4806,
      "step": 3
    },
    {
      "epoch": 0.0006965000870625109,
      "eval_loss": 2.3103156089782715,
      "eval_runtime": 197.5106,
      "eval_samples_per_second": 4.592,
      "eval_steps_per_second": 4.592,
      "step": 3
    },
    {
      "epoch": 0.0009286667827500145,
      "grad_norm": 3.1405253410339355,
      "learning_rate": 8e-05,
      "loss": 2.319,
      "step": 4
    },
    {
      "epoch": 0.0011608334784375181,
      "grad_norm": 2.377209424972534,
      "learning_rate": 0.0001,
      "loss": 1.6571,
      "step": 5
    },
    {
      "epoch": 0.0013930001741250218,
      "grad_norm": 3.2652180194854736,
      "learning_rate": 0.00012,
      "loss": 1.4567,
      "step": 6
    },
    {
      "epoch": 0.0013930001741250218,
      "eval_loss": 1.3078285455703735,
      "eval_runtime": 197.6739,
      "eval_samples_per_second": 4.588,
      "eval_steps_per_second": 4.588,
      "step": 6
    },
    {
      "epoch": 0.0016251668698125253,
      "grad_norm": 2.901350975036621,
      "learning_rate": 0.00014,
      "loss": 1.6501,
      "step": 7
    },
    {
      "epoch": 0.001857333565500029,
      "grad_norm": 3.143646478652954,
      "learning_rate": 0.00016,
      "loss": 1.0855,
      "step": 8
    },
    {
      "epoch": 0.0020895002611875328,
      "grad_norm": 2.208082675933838,
      "learning_rate": 0.00018,
      "loss": 0.8768,
      "step": 9
    },
    {
      "epoch": 0.0020895002611875328,
      "eval_loss": 0.6551823616027832,
      "eval_runtime": 197.4739,
      "eval_samples_per_second": 4.593,
      "eval_steps_per_second": 4.593,
      "step": 9
    },
    {
      "epoch": 0.0023216669568750362,
      "grad_norm": 1.9000203609466553,
      "learning_rate": 0.0002,
      "loss": 0.5152,
      "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": 6990386933268480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}