Hugging Face's logo

dimasik87
/
23eaf7d9-c6d2-4c3e-956c-acb89fa92a4c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
23eaf7d9-c6d2-4c3e-956c-acb89fa92a4c
File size: 3,200 Bytes 
5dee131
 
 
987500c
5dee131
987500c
5dee131
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2ac6ff9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93fdfe4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
987500c
 
 
 
 
 
 
5dee131
 
 
 
 
 
 
 
 
 
 
 
 
 
987500c
5dee131
 
 
 
987500c
5dee131
 
 
 
 
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
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007343491830365339,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007343491830365339,
      "grad_norm": 0.7374667525291443,
      "learning_rate": 2e-05,
      "loss": 0.6968,
      "step": 1
    },
    {
      "epoch": 0.0007343491830365339,
      "eval_loss": 0.6995853185653687,
      "eval_runtime": 172.0393,
      "eval_samples_per_second": 6.667,
      "eval_steps_per_second": 1.668,
      "step": 1
    },
    {
      "epoch": 0.0014686983660730677,
      "grad_norm": 0.7952613234519958,
      "learning_rate": 4e-05,
      "loss": 0.6825,
      "step": 2
    },
    {
      "epoch": 0.0022030475491096016,
      "grad_norm": 0.7004721164703369,
      "learning_rate": 6e-05,
      "loss": 0.6528,
      "step": 3
    },
    {
      "epoch": 0.0022030475491096016,
      "eval_loss": 0.6738851070404053,
      "eval_runtime": 171.1769,
      "eval_samples_per_second": 6.701,
      "eval_steps_per_second": 1.677,
      "step": 3
    },
    {
      "epoch": 0.0029373967321461355,
      "grad_norm": 0.6414063572883606,
      "learning_rate": 8e-05,
      "loss": 0.5886,
      "step": 4
    },
    {
      "epoch": 0.0036717459151826694,
      "grad_norm": 0.6509028673171997,
      "learning_rate": 0.0001,
      "loss": 0.5753,
      "step": 5
    },
    {
      "epoch": 0.004406095098219203,
      "grad_norm": 0.73858243227005,
      "learning_rate": 0.00012,
      "loss": 0.5315,
      "step": 6
    },
    {
      "epoch": 0.004406095098219203,
      "eval_loss": 0.4672764241695404,
      "eval_runtime": 171.3975,
      "eval_samples_per_second": 6.692,
      "eval_steps_per_second": 1.674,
      "step": 6
    },
    {
      "epoch": 0.005140444281255737,
      "grad_norm": 0.5061175227165222,
      "learning_rate": 0.00014,
      "loss": 0.4653,
      "step": 7
    },
    {
      "epoch": 0.005874793464292271,
      "grad_norm": 0.7058733105659485,
      "learning_rate": 0.00016,
      "loss": 0.4515,
      "step": 8
    },
    {
      "epoch": 0.006609142647328804,
      "grad_norm": 0.6450387835502625,
      "learning_rate": 0.00018,
      "loss": 0.3974,
      "step": 9
    },
    {
      "epoch": 0.006609142647328804,
      "eval_loss": 0.3535566031932831,
      "eval_runtime": 171.1504,
      "eval_samples_per_second": 6.702,
      "eval_steps_per_second": 1.677,
      "step": 9
    },
    {
      "epoch": 0.007343491830365339,
      "grad_norm": 0.7145763635635376,
      "learning_rate": 0.0002,
      "loss": 0.3324,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.317076820033536e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}