Hugging Face's logo

lesso
/
e2db0468-9254-4f62-8ed2-c1edf69735b5

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
e2db0468-9254-4f62-8ed2-c1edf69735b5
File size: 2,726 Bytes 
ff7b2b0
93cb097
 
dad086f
ff7b2b0
dad086f
ff7b2b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c374efc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ffe53a1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93cb097
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff7b2b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dad086f
ff7b2b0
 
 
 
dad086f
ff7b2b0
 
 
 
 
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
 
{
  "best_metric": 0.46152710914611816,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.37540453074433655,
  "eval_steps": 50,
  "global_step": 203,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018492834026814608,
      "eval_loss": 0.6752422451972961,
      "eval_runtime": 47.1784,
      "eval_samples_per_second": 9.665,
      "eval_steps_per_second": 0.318,
      "step": 1
    },
    {
      "epoch": 0.09246417013407304,
      "grad_norm": 2.9781739711761475,
      "learning_rate": 0.000208,
      "loss": 1.948,
      "step": 50
    },
    {
      "epoch": 0.09246417013407304,
      "eval_loss": 0.4734339118003845,
      "eval_runtime": 47.5435,
      "eval_samples_per_second": 9.591,
      "eval_steps_per_second": 0.316,
      "step": 50
    },
    {
      "epoch": 0.18492834026814609,
      "grad_norm": 2.779236078262329,
      "learning_rate": 0.000208,
      "loss": 1.8153,
      "step": 100
    },
    {
      "epoch": 0.18492834026814609,
      "eval_loss": 0.46913212537765503,
      "eval_runtime": 47.566,
      "eval_samples_per_second": 9.587,
      "eval_steps_per_second": 0.315,
      "step": 100
    },
    {
      "epoch": 0.27739251040221913,
      "grad_norm": 2.7492291927337646,
      "learning_rate": 0.000208,
      "loss": 1.7946,
      "step": 150
    },
    {
      "epoch": 0.27739251040221913,
      "eval_loss": 0.4658304452896118,
      "eval_runtime": 47.5243,
      "eval_samples_per_second": 9.595,
      "eval_steps_per_second": 0.316,
      "step": 150
    },
    {
      "epoch": 0.36985668053629217,
      "grad_norm": 2.738309621810913,
      "learning_rate": 0.000208,
      "loss": 1.8198,
      "step": 200
    },
    {
      "epoch": 0.36985668053629217,
      "eval_loss": 0.46152710914611816,
      "eval_runtime": 47.55,
      "eval_samples_per_second": 9.59,
      "eval_steps_per_second": 0.315,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 203,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4524629791224627e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}