Hugging Face's logo

tuanna08go
/
6a3ceda6-4b19-4ab8-a78c-63864ff6668b

PEFT
Safetensors
phi
axolotl
Generated from Trainer
Model card Files Community
6a3ceda6-4b19-4ab8-a78c-63864ff6668b
File size: 2,249 Bytes 
d8201e6
 
 
2b77fb0
ad75744
2b77fb0
d8201e6
 
 
 
 
 
ad75744
 
 
 
d8201e6
ad75744
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2b77fb0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d8201e6
 
 
ad75744
d8201e6
 
ad75744
d8201e6
 
 
 
 
 
 
ad75744
d8201e6
 
 
 
2b77fb0
d8201e6
 
 
 
 
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": 0.00044023213779265916,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.693200529971766e-05,
      "eval_loss": 6.939432144165039,
      "eval_runtime": 384.3868,
      "eval_samples_per_second": 64.695,
      "eval_steps_per_second": 32.348,
      "step": 1
    },
    {
      "epoch": 8.46600264985883e-05,
      "grad_norm": 0.2929963171482086,
      "learning_rate": 5e-05,
      "loss": 6.9387,
      "step": 5
    },
    {
      "epoch": 0.0001693200529971766,
      "grad_norm": 0.27149704098701477,
      "learning_rate": 0.0001,
      "loss": 6.9377,
      "step": 10
    },
    {
      "epoch": 0.0001693200529971766,
      "eval_loss": 6.936197280883789,
      "eval_runtime": 402.4358,
      "eval_samples_per_second": 61.794,
      "eval_steps_per_second": 30.897,
      "step": 10
    },
    {
      "epoch": 0.0002539800794957649,
      "grad_norm": 0.28503113985061646,
      "learning_rate": 9.619397662556435e-05,
      "loss": 6.9318,
      "step": 15
    },
    {
      "epoch": 0.0003386401059943532,
      "grad_norm": 0.24860993027687073,
      "learning_rate": 8.535533905932738e-05,
      "loss": 6.9316,
      "step": 20
    },
    {
      "epoch": 0.0003386401059943532,
      "eval_loss": 6.928938388824463,
      "eval_runtime": 310.0666,
      "eval_samples_per_second": 80.202,
      "eval_steps_per_second": 40.101,
      "step": 20
    },
    {
      "epoch": 0.00042330013249294147,
      "grad_norm": 0.2915782928466797,
      "learning_rate": 6.91341716182545e-05,
      "loss": 6.9273,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 44164067328.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}