Hugging Face's logo

ClarenceDan
/
6a0f667a-5ebc-4132-9ae4-6ec8d8d41560

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
custom_code
Model card Files
xet
Community
6a0f667a-5ebc-4132-9ae4-6ec8d8d41560
File size: 2,326 Bytes 
7b46cbe
 
 
37c8cd0
7b46cbe
37c8cd0
7b46cbe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37c8cd0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b46cbe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37c8cd0
7b46cbe
 
 
 
 
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": 0.20168067226890757,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03361344537815126,
      "grad_norm": 17.1643123626709,
      "learning_rate": 2e-05,
      "loss": 1.8096,
      "step": 1
    },
    {
      "epoch": 0.03361344537815126,
      "eval_loss": 0.4755823016166687,
      "eval_runtime": 0.6289,
      "eval_samples_per_second": 20.672,
      "eval_steps_per_second": 11.131,
      "step": 1
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 18.96877098083496,
      "learning_rate": 4e-05,
      "loss": 1.9926,
      "step": 2
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": 15.60456657409668,
      "learning_rate": 6e-05,
      "loss": 1.7178,
      "step": 3
    },
    {
      "epoch": 0.10084033613445378,
      "eval_loss": 0.32526782155036926,
      "eval_runtime": 0.629,
      "eval_samples_per_second": 20.667,
      "eval_steps_per_second": 11.128,
      "step": 3
    },
    {
      "epoch": 0.13445378151260504,
      "grad_norm": 11.628034591674805,
      "learning_rate": 8e-05,
      "loss": 1.2652,
      "step": 4
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 11.16609001159668,
      "learning_rate": 0.0001,
      "loss": 0.6447,
      "step": 5
    },
    {
      "epoch": 0.20168067226890757,
      "grad_norm": 31.83843421936035,
      "learning_rate": 0.00012,
      "loss": 0.3547,
      "step": 6
    },
    {
      "epoch": 0.20168067226890757,
      "eval_loss": 0.013815270736813545,
      "eval_runtime": 0.6335,
      "eval_samples_per_second": 20.522,
      "eval_steps_per_second": 11.05,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1051601871568896.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}