Hugging Face's logo

dsakerkwq
/
c504561c-9cd9-4a50-8f9c-b0b80246538c

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
c504561c-9cd9-4a50-8f9c-b0b80246538c
File size: 3,202 Bytes 
250a4f2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2903225806451615,
  "eval_steps": 25,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 2.5122365951538086,
      "learning_rate": 9.846666218300807e-05,
      "loss": 4.2481,
      "step": 1
    },
    {
      "epoch": 0.25806451612903225,
      "eval_loss": 4.566070556640625,
      "eval_runtime": 2.4808,
      "eval_samples_per_second": 20.155,
      "eval_steps_per_second": 5.24,
      "step": 1
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 2.683114528656006,
      "learning_rate": 9.397114317029975e-05,
      "loss": 4.2015,
      "step": 2
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 3.2781496047973633,
      "learning_rate": 8.681980515339464e-05,
      "loss": 3.7456,
      "step": 3
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 3.645509719848633,
      "learning_rate": 7.75e-05,
      "loss": 4.3088,
      "step": 4
    },
    {
      "epoch": 1.3548387096774195,
      "grad_norm": 2.247633218765259,
      "learning_rate": 6.664685702961344e-05,
      "loss": 2.6704,
      "step": 5
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 1.8294740915298462,
      "learning_rate": 5.500000000000001e-05,
      "loss": 2.6275,
      "step": 6
    },
    {
      "epoch": 1.870967741935484,
      "grad_norm": 2.493924379348755,
      "learning_rate": 4.3353142970386564e-05,
      "loss": 3.2239,
      "step": 7
    },
    {
      "epoch": 2.193548387096774,
      "grad_norm": 1.8082947731018066,
      "learning_rate": 3.250000000000001e-05,
      "loss": 2.8087,
      "step": 8
    },
    {
      "epoch": 2.4516129032258065,
      "grad_norm": 1.3744213581085205,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 2.3614,
      "step": 9
    },
    {
      "epoch": 2.709677419354839,
      "grad_norm": 1.3035913705825806,
      "learning_rate": 1.602885682970026e-05,
      "loss": 2.5687,
      "step": 10
    },
    {
      "epoch": 3.032258064516129,
      "grad_norm": 1.7011222839355469,
      "learning_rate": 1.1533337816991932e-05,
      "loss": 3.0748,
      "step": 11
    },
    {
      "epoch": 3.2903225806451615,
      "grad_norm": 1.2215309143066406,
      "learning_rate": 1e-05,
      "loss": 2.109,
      "step": 12
    }
  ],
  "logging_steps": 1,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1.3497738745557811e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}