Hugging Face's logo

dixedus
/
9f7c638a-7ac1-47bc-becf-4b2e346cd2e9

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
9f7c638a-7ac1-47bc-becf-4b2e346cd2e9
File size: 2,371 Bytes 
fc13558
 
 
5e6eb1c
fc13558
5e6eb1c
fc13558
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5e6eb1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fc13558
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5e6eb1c
fc13558
 
 
 
 
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": 0.47368421052631576,
  "eval_steps": 9,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02631578947368421,
      "eval_loss": 1.6184024810791016,
      "eval_runtime": 4.386,
      "eval_samples_per_second": 14.592,
      "eval_steps_per_second": 1.824,
      "step": 1
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 25.33377456665039,
      "learning_rate": 3e-05,
      "loss": 6.2534,
      "step": 3
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 19.7912540435791,
      "learning_rate": 6e-05,
      "loss": 6.0633,
      "step": 6
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 17.20012855529785,
      "learning_rate": 9e-05,
      "loss": 5.0168,
      "step": 9
    },
    {
      "epoch": 0.23684210526315788,
      "eval_loss": 1.0376337766647339,
      "eval_runtime": 4.4723,
      "eval_samples_per_second": 14.31,
      "eval_steps_per_second": 1.789,
      "step": 9
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 11.844976425170898,
      "learning_rate": 9.987820251299122e-05,
      "loss": 4.0152,
      "step": 12
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 10.39311695098877,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.859,
      "step": 15
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 9.025694847106934,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.9375,
      "step": 18
    },
    {
      "epoch": 0.47368421052631576,
      "eval_loss": 0.8340747356414795,
      "eval_runtime": 4.4933,
      "eval_samples_per_second": 14.244,
      "eval_steps_per_second": 1.78,
      "step": 18
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.531269094355763e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}