Hugging Face's logo

daniel40
/
b9f60105-2f1d-4dae-ae54-126f7ac6343a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
b9f60105-2f1d-4dae-ae54-126f7ac6343a
File size: 2,442 Bytes 
e2f213e
 
 
6f4ccd2
e2f213e
6f4ccd2
e2f213e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72f277f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27b4a53
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f4ccd2
 
 
 
 
 
 
 
 
 
 
 
 
 
e2f213e
 
 
 
 
 
 
 
 
 
 
 
 
 
6f4ccd2
e2f213e
 
 
 
6f4ccd2
e2f213e
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.020766275568476794,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004153255113695359,
      "eval_loss": 0.9820240139961243,
      "eval_runtime": 57.9899,
      "eval_samples_per_second": 17.486,
      "eval_steps_per_second": 8.743,
      "step": 1
    },
    {
      "epoch": 0.0041532551136953585,
      "grad_norm": 0.4132612943649292,
      "learning_rate": 0.0002,
      "loss": 0.9159,
      "step": 10
    },
    {
      "epoch": 0.005399231647803967,
      "eval_loss": 0.6973010301589966,
      "eval_runtime": 57.3907,
      "eval_samples_per_second": 17.668,
      "eval_steps_per_second": 8.834,
      "step": 13
    },
    {
      "epoch": 0.008306510227390717,
      "grad_norm": 0.31124502420425415,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.6846,
      "step": 20
    },
    {
      "epoch": 0.010798463295607933,
      "eval_loss": 0.5951049327850342,
      "eval_runtime": 57.4895,
      "eval_samples_per_second": 17.638,
      "eval_steps_per_second": 8.819,
      "step": 26
    },
    {
      "epoch": 0.012459765341086075,
      "grad_norm": 0.3194844126701355,
      "learning_rate": 0.0001,
      "loss": 0.6237,
      "step": 30
    },
    {
      "epoch": 0.0161976949434119,
      "eval_loss": 0.5683814883232117,
      "eval_runtime": 57.4235,
      "eval_samples_per_second": 17.658,
      "eval_steps_per_second": 8.829,
      "step": 39
    },
    {
      "epoch": 0.016613020454781434,
      "grad_norm": 0.2615678608417511,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.571,
      "step": 40
    },
    {
      "epoch": 0.020766275568476794,
      "grad_norm": 0.2704824209213257,
      "learning_rate": 0.0,
      "loss": 0.5732,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6478229233664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}