Hugging Face's logo

marialvsantiago
/
14c2e710-f39f-4320-a08e-e7c253f1fce5

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files Community
14c2e710-f39f-4320-a08e-e7c253f1fce5
File size: 3,098 Bytes 
95849ea
1dd6cdb
 
 
95849ea
1dd6cdb
95849ea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1dd6cdb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95849ea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1dd6cdb
95849ea
 
 
 
 
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
112
113
114
115
116
117
118
119
120
121
122
123
124
125
 
{
  "best_metric": 1.2484335899353027,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0034278858514011482,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001713942925700574,
      "eval_loss": 1.3596421480178833,
      "eval_runtime": 583.9591,
      "eval_samples_per_second": 4.207,
      "eval_steps_per_second": 2.105,
      "step": 1
    },
    {
      "epoch": 0.0005141828777101723,
      "grad_norm": 5.756150722503662,
      "learning_rate": 6e-05,
      "loss": 5.3785,
      "step": 3
    },
    {
      "epoch": 0.0008569714628502871,
      "eval_loss": 1.350292682647705,
      "eval_runtime": 590.0216,
      "eval_samples_per_second": 4.164,
      "eval_steps_per_second": 2.083,
      "step": 5
    },
    {
      "epoch": 0.0010283657554203446,
      "grad_norm": 3711.65625,
      "learning_rate": 9.96057350657239e-05,
      "loss": 4.7408,
      "step": 6
    },
    {
      "epoch": 0.0015425486331305167,
      "grad_norm": 7608.09375,
      "learning_rate": 9.381533400219318e-05,
      "loss": 5.116,
      "step": 9
    },
    {
      "epoch": 0.0017139429257005741,
      "eval_loss": 1.3284010887145996,
      "eval_runtime": 587.3458,
      "eval_samples_per_second": 4.183,
      "eval_steps_per_second": 2.092,
      "step": 10
    },
    {
      "epoch": 0.002056731510840689,
      "grad_norm": 10.381022453308105,
      "learning_rate": 8.18711994874345e-05,
      "loss": 5.3987,
      "step": 12
    },
    {
      "epoch": 0.0025709143885508613,
      "grad_norm": 1.8296691179275513,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.907,
      "step": 15
    },
    {
      "epoch": 0.0025709143885508613,
      "eval_loss": 1.2899432182312012,
      "eval_runtime": 587.3318,
      "eval_samples_per_second": 4.183,
      "eval_steps_per_second": 2.093,
      "step": 15
    },
    {
      "epoch": 0.0030850972662610334,
      "grad_norm": 1.917513132095337,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 5.0149,
      "step": 18
    },
    {
      "epoch": 0.0034278858514011482,
      "eval_loss": 1.2484335899353027,
      "eval_runtime": 587.2531,
      "eval_samples_per_second": 4.184,
      "eval_steps_per_second": 2.093,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.361684987904e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}