Hugging Face's logo

Best000
/
f09fa775-07fe-4b66-b7f2-b9282dcf5d03

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
f09fa775-07fe-4b66-b7f2-b9282dcf5d03
File size: 2,029 Bytes 
f2984a1
 
 
9a921ab
f2984a1
9a921ab
f2984a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
af4585b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9a921ab
 
 
 
 
 
 
f2984a1
 
 
 
 
 
 
 
 
 
 
 
 
 
9a921ab
f2984a1
 
 
 
9a921ab
f2984a1
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1578947368421053,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21052631578947367,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 8.8987,
      "step": 1
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": NaN,
      "eval_runtime": 0.6923,
      "eval_samples_per_second": 2.889,
      "eval_steps_per_second": 1.445,
      "step": 1
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.42105263157894735,
      "eval_loss": NaN,
      "eval_runtime": 0.0869,
      "eval_samples_per_second": 23.027,
      "eval_steps_per_second": 11.513,
      "step": 2
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.8421052631578947,
      "eval_loss": NaN,
      "eval_runtime": 0.0876,
      "eval_samples_per_second": 22.819,
      "eval_steps_per_second": 11.41,
      "step": 4
    },
    {
      "epoch": 1.1578947368421053,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 918533198315520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}