Hugging Face's logo

tuanna08go
/
5b24d025-60f3-4555-9341-76f2c94dab21

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files Community
5b24d025-60f3-4555-9341-76f2c94dab21
File size: 3,773 Bytes 
714d6b7
 
 
92a3635
ec68ac3
92a3635
714d6b7
 
 
 
 
 
 
ec68ac3
 
 
714d6b7
ec68ac3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cb187d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3aa9e49
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92a3635
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
714d6b7
 
 
ec68ac3
714d6b7
 
ec68ac3
714d6b7
 
 
 
 
 
 
92a3635
714d6b7
 
 
 
92a3635
714d6b7
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0026217473946385265,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.2434947892770535e-05,
      "eval_loss": 12.45307445526123,
      "eval_runtime": 110.2136,
      "eval_samples_per_second": 72.859,
      "eval_steps_per_second": 36.429,
      "step": 1
    },
    {
      "epoch": 0.00026217473946385267,
      "grad_norm": 0.002715166425332427,
      "learning_rate": 5e-05,
      "loss": 12.4518,
      "step": 5
    },
    {
      "epoch": 0.0005243494789277053,
      "grad_norm": 0.004838508553802967,
      "learning_rate": 0.0001,
      "loss": 12.4532,
      "step": 10
    },
    {
      "epoch": 0.0005243494789277053,
      "eval_loss": 12.453064918518066,
      "eval_runtime": 110.4922,
      "eval_samples_per_second": 72.675,
      "eval_steps_per_second": 36.337,
      "step": 10
    },
    {
      "epoch": 0.000786524218391558,
      "grad_norm": 0.004974856972694397,
      "learning_rate": 9.619397662556435e-05,
      "loss": 12.4545,
      "step": 15
    },
    {
      "epoch": 0.0010486989578554107,
      "grad_norm": 0.004730704706162214,
      "learning_rate": 8.535533905932738e-05,
      "loss": 12.456,
      "step": 20
    },
    {
      "epoch": 0.0010486989578554107,
      "eval_loss": 12.453044891357422,
      "eval_runtime": 110.6233,
      "eval_samples_per_second": 72.589,
      "eval_steps_per_second": 36.294,
      "step": 20
    },
    {
      "epoch": 0.0013108736973192633,
      "grad_norm": 0.005735255312174559,
      "learning_rate": 6.91341716182545e-05,
      "loss": 12.4515,
      "step": 25
    },
    {
      "epoch": 0.001573048436783116,
      "grad_norm": 0.008840982802212238,
      "learning_rate": 5e-05,
      "loss": 12.4552,
      "step": 30
    },
    {
      "epoch": 0.001573048436783116,
      "eval_loss": 12.453033447265625,
      "eval_runtime": 110.6772,
      "eval_samples_per_second": 72.553,
      "eval_steps_per_second": 36.277,
      "step": 30
    },
    {
      "epoch": 0.0018352231762469686,
      "grad_norm": 0.007563808001577854,
      "learning_rate": 3.086582838174551e-05,
      "loss": 12.4549,
      "step": 35
    },
    {
      "epoch": 0.0020973979157108214,
      "grad_norm": 0.0029871268197894096,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 12.4555,
      "step": 40
    },
    {
      "epoch": 0.0020973979157108214,
      "eval_loss": 12.453027725219727,
      "eval_runtime": 110.644,
      "eval_samples_per_second": 72.575,
      "eval_steps_per_second": 36.288,
      "step": 40
    },
    {
      "epoch": 0.002359572655174674,
      "grad_norm": 0.005952336825430393,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 12.4553,
      "step": 45
    },
    {
      "epoch": 0.0026217473946385265,
      "grad_norm": 0.0046081626787781715,
      "learning_rate": 0.0,
      "loss": 12.4562,
      "step": 50
    },
    {
      "epoch": 0.0026217473946385265,
      "eval_loss": 12.453025817871094,
      "eval_runtime": 110.6277,
      "eval_samples_per_second": 72.586,
      "eval_steps_per_second": 36.293,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5421858816.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}