Hugging Face's logo

great0001
/
e55702de-d057-4c4b-8dc7-23f9b6fec6e9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e55702de-d057-4c4b-8dc7-23f9b6fec6e9
File size: 2,234 Bytes 
51a7cca
 
 
02516e6
51a7cca
02516e6
51a7cca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
02516e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51a7cca
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
02516e6
51a7cca
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0234375,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00390625,
      "grad_norm": 0.4705980718135834,
      "learning_rate": 2e-05,
      "loss": 2.0788,
      "step": 1
    },
    {
      "epoch": 0.00390625,
      "eval_loss": 2.183541774749756,
      "eval_runtime": 3.7867,
      "eval_samples_per_second": 28.521,
      "eval_steps_per_second": 14.261,
      "step": 1
    },
    {
      "epoch": 0.0078125,
      "grad_norm": 0.46773648262023926,
      "learning_rate": 4e-05,
      "loss": 2.203,
      "step": 2
    },
    {
      "epoch": 0.01171875,
      "grad_norm": 0.4773087501525879,
      "learning_rate": 6e-05,
      "loss": 2.3165,
      "step": 3
    },
    {
      "epoch": 0.01171875,
      "eval_loss": 2.1793529987335205,
      "eval_runtime": 3.0914,
      "eval_samples_per_second": 34.935,
      "eval_steps_per_second": 17.468,
      "step": 3
    },
    {
      "epoch": 0.015625,
      "grad_norm": 0.46294865012168884,
      "learning_rate": 8e-05,
      "loss": 2.0049,
      "step": 4
    },
    {
      "epoch": 0.01953125,
      "grad_norm": 0.44666004180908203,
      "learning_rate": 0.0001,
      "loss": 1.8536,
      "step": 5
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 0.5266293287277222,
      "learning_rate": 0.00012,
      "loss": 1.9211,
      "step": 6
    },
    {
      "epoch": 0.0234375,
      "eval_loss": 2.135219097137451,
      "eval_runtime": 3.1069,
      "eval_samples_per_second": 34.761,
      "eval_steps_per_second": 17.381,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 977239881547776.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}