Hugging Face's logo

nadejdatarabukina
/
f9d3203c-24b3-483d-9f72-6d57884a57ea

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
f9d3203c-24b3-483d-9f72-6d57884a57ea
File size: 2,762 Bytes 
96ab349
 
 
5660fdb
96ab349
5660fdb
96ab349
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
329d3f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5660fdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96ab349
 
 
 
 
 
 
 
 
 
 
 
 
 
5660fdb
96ab349
 
 
 
5660fdb
96ab349
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010748065348237317,
  "eval_steps": 7,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004299226139294927,
      "eval_loss": NaN,
      "eval_runtime": 37.904,
      "eval_samples_per_second": 25.855,
      "eval_steps_per_second": 12.927,
      "step": 1
    },
    {
      "epoch": 0.0012897678417884782,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0025795356835769563,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0030094582975064487,
      "eval_loss": NaN,
      "eval_runtime": 36.097,
      "eval_samples_per_second": 27.149,
      "eval_steps_per_second": 13.575,
      "step": 7
    },
    {
      "epoch": 0.003869303525365434,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.005159071367153913,
      "grad_norm": NaN,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0060189165950128975,
      "eval_loss": NaN,
      "eval_runtime": 35.6499,
      "eval_samples_per_second": 27.49,
      "eval_steps_per_second": 13.745,
      "step": 14
    },
    {
      "epoch": 0.006448839208942391,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.007738607050730868,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.009028374892519347,
      "grad_norm": NaN,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.009028374892519347,
      "eval_loss": NaN,
      "eval_runtime": 35.6565,
      "eval_samples_per_second": 27.485,
      "eval_steps_per_second": 13.742,
      "step": 21
    },
    {
      "epoch": 0.010318142734307825,
      "grad_norm": NaN,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.0,
      "step": 24
    }
  ],
  "logging_steps": 3,
  "max_steps": 25,
  "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": 425104626155520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}