Hugging Face's logo

cvoffer
/
8cd6e331-06d4-4075-9716-8b8cfaab1c4e

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files Community
8cd6e331-06d4-4075-9716-8b8cfaab1c4e
File size: 2,160 Bytes 
a97b448
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 1.5595622062683105,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.0007620934707641893,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.620934707641892e-05,
      "eval_loss": 1.807066559791565,
      "eval_runtime": 576.1883,
      "eval_samples_per_second": 9.589,
      "eval_steps_per_second": 4.795,
      "step": 1
    },
    {
      "epoch": 0.00022862804122925678,
      "grad_norm": 5.381506443023682,
      "learning_rate": 3e-05,
      "loss": 7.1048,
      "step": 3
    },
    {
      "epoch": 0.00038104673538209464,
      "eval_loss": 1.7532647848129272,
      "eval_runtime": 577.68,
      "eval_samples_per_second": 9.564,
      "eval_steps_per_second": 4.783,
      "step": 5
    },
    {
      "epoch": 0.00045725608245851356,
      "grad_norm": 5.005251884460449,
      "learning_rate": 4.980286753286195e-05,
      "loss": 7.1625,
      "step": 6
    },
    {
      "epoch": 0.0006858841236877703,
      "grad_norm": 3.4449706077575684,
      "learning_rate": 4.690766700109659e-05,
      "loss": 6.5864,
      "step": 9
    },
    {
      "epoch": 0.0007620934707641893,
      "eval_loss": 1.5595622062683105,
      "eval_runtime": 579.6011,
      "eval_samples_per_second": 9.532,
      "eval_steps_per_second": 4.767,
      "step": 10
    }
  ],
  "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": 1842091508367360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}