Hugging Face's logo

sergioalves
/
0c12ba50-1288-403c-b3f8-d9a452c7f0ce

PEFT
Safetensors
dbrx
axolotl
Generated from Trainer
Model card Files Community
0c12ba50-1288-403c-b3f8-d9a452c7f0ce
File size: 2,350 Bytes 
efed9b8
 
 
fa16115
efed9b8
fa16115
efed9b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa16115
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
efed9b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fa16115
efed9b8
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.023330417031204434,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011665208515602217,
      "eval_loss": 11.5,
      "eval_runtime": 3.5729,
      "eval_samples_per_second": 101.04,
      "eval_steps_per_second": 50.66,
      "step": 1
    },
    {
      "epoch": 0.003499562554680665,
      "grad_norm": 6.78294018143788e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.00699912510936133,
      "grad_norm": 7.048947009025142e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.009332166812481774,
      "eval_loss": 11.5,
      "eval_runtime": 3.5169,
      "eval_samples_per_second": 102.646,
      "eval_steps_per_second": 51.465,
      "step": 8
    },
    {
      "epoch": 0.010498687664041995,
      "grad_norm": 9.457429405301809e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.01399825021872266,
      "grad_norm": 0.00011205866030650213,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.017497812773403325,
      "grad_norm": 9.639419295126572e-05,
      "learning_rate": 8.535533905932738e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.018664333624963548,
      "eval_loss": 11.5,
      "eval_runtime": 3.5697,
      "eval_samples_per_second": 101.129,
      "eval_steps_per_second": 50.705,
      "step": 16
    },
    {
      "epoch": 0.02099737532808399,
      "grad_norm": 6.34350799373351e-05,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 18
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 797921771520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}