Hugging Face's logo

trenden
/
cfef82b7-ae23-404a-978c-3f891c17f0fb

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
cfef82b7-ae23-404a-978c-3f891c17f0fb
File size: 3,058 Bytes 
f95d305
 
 
7aef58a
f95d305
7aef58a
f95d305
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3065cac
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7aef58a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f95d305
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7aef58a
f95d305
 
 
 
 
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
126
127
128
129
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00024309377342309797,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.7010419269233105e-05,
      "grad_norm": 0.8623080253601074,
      "learning_rate": 2e-05,
      "loss": 2.5139,
      "step": 1
    },
    {
      "epoch": 2.7010419269233105e-05,
      "eval_loss": 2.4878077507019043,
      "eval_runtime": 857.3558,
      "eval_samples_per_second": 18.183,
      "eval_steps_per_second": 9.092,
      "step": 1
    },
    {
      "epoch": 5.402083853846621e-05,
      "grad_norm": 1.2046571969985962,
      "learning_rate": 4e-05,
      "loss": 2.4404,
      "step": 2
    },
    {
      "epoch": 8.103125780769932e-05,
      "grad_norm": 1.2379217147827148,
      "learning_rate": 6e-05,
      "loss": 2.4415,
      "step": 3
    },
    {
      "epoch": 8.103125780769932e-05,
      "eval_loss": 2.4826765060424805,
      "eval_runtime": 850.2424,
      "eval_samples_per_second": 18.335,
      "eval_steps_per_second": 9.168,
      "step": 3
    },
    {
      "epoch": 0.00010804167707693242,
      "grad_norm": 1.1288055181503296,
      "learning_rate": 8e-05,
      "loss": 2.4938,
      "step": 4
    },
    {
      "epoch": 0.00013505209634616554,
      "grad_norm": 1.436876893043518,
      "learning_rate": 0.0001,
      "loss": 2.3032,
      "step": 5
    },
    {
      "epoch": 0.00016206251561539864,
      "grad_norm": 1.3907028436660767,
      "learning_rate": 0.00012,
      "loss": 2.3267,
      "step": 6
    },
    {
      "epoch": 0.00016206251561539864,
      "eval_loss": 2.3965697288513184,
      "eval_runtime": 849.1995,
      "eval_samples_per_second": 18.357,
      "eval_steps_per_second": 9.179,
      "step": 6
    },
    {
      "epoch": 0.00018907293488463174,
      "grad_norm": 1.208445429801941,
      "learning_rate": 0.00014,
      "loss": 2.1013,
      "step": 7
    },
    {
      "epoch": 0.00021608335415386484,
      "grad_norm": 1.384195327758789,
      "learning_rate": 0.00016,
      "loss": 2.3522,
      "step": 8
    },
    {
      "epoch": 0.00024309377342309797,
      "grad_norm": 1.4619507789611816,
      "learning_rate": 0.00018,
      "loss": 2.3595,
      "step": 9
    },
    {
      "epoch": 0.00024309377342309797,
      "eval_loss": 2.1295883655548096,
      "eval_runtime": 849.1542,
      "eval_samples_per_second": 18.358,
      "eval_steps_per_second": 9.18,
      "step": 9
    }
  ],
  "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": 3282976540459008.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}