Hugging Face's logo

VQA-DeepLearning
/
gemma_2_lora_E2b

Transformers
Safetensors
Generated from Trainer
unsloth
sft
trl
Model card Files
xet
 Community
gemma_2_lora_E2b
File size: 3,789 Bytes
20aca87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.33463469046291133,
  "eval_steps": 100,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022308979364194088,
      "grad_norm": 3.6059792041778564,
      "learning_rate": 0.00019999016517595753,
      "loss": 3.6749305725097656,
      "step": 10
    },
    {
      "epoch": 0.044617958728388175,
      "grad_norm": 1.686761498451233,
      "learning_rate": 0.00019987954562051725,
      "loss": 0.9972598075866699,
      "step": 20
    },
    {
      "epoch": 0.06692693809258227,
      "grad_norm": 1.0181570053100586,
      "learning_rate": 0.00019964614941176195,
      "loss": 0.7280679225921631,
      "step": 30
    },
    {
      "epoch": 0.08923591745677635,
      "grad_norm": 0.9052721261978149,
      "learning_rate": 0.00019929026345133122,
      "loss": 0.6308993339538574,
      "step": 40
    },
    {
      "epoch": 0.11154489682097044,
      "grad_norm": 0.8318365812301636,
      "learning_rate": 0.00019881232521105089,
      "loss": 0.6105688571929931,
      "step": 50
    },
    {
      "epoch": 0.13385387618516453,
      "grad_norm": 0.9255080223083496,
      "learning_rate": 0.00019821292219517192,
      "loss": 0.5463937282562256,
      "step": 60
    },
    {
      "epoch": 0.1561628555493586,
      "grad_norm": 0.8712772727012634,
      "learning_rate": 0.00019749279121818235,
      "loss": 0.513142728805542,
      "step": 70
    },
    {
      "epoch": 0.1784718349135527,
      "grad_norm": 0.6806803941726685,
      "learning_rate": 0.00019665281749908033,
      "loss": 0.45452089309692384,
      "step": 80
    },
    {
      "epoch": 0.2007808142777468,
      "grad_norm": 0.8569662570953369,
      "learning_rate": 0.0001956940335732209,
      "loss": 0.4099240303039551,
      "step": 90
    },
    {
      "epoch": 0.22308979364194087,
      "grad_norm": 0.5690306425094604,
      "learning_rate": 0.00019461761802307495,
      "loss": 0.4181380748748779,
      "step": 100
    },
    {
      "epoch": 0.22308979364194087,
      "eval_loss": 7.142496585845947,
      "eval_runtime": 196.0856,
      "eval_samples_per_second": 2.3,
      "eval_steps_per_second": 2.3,
      "step": 100
    },
    {
      "epoch": 0.24539877300613497,
      "grad_norm": 0.5885435938835144,
      "learning_rate": 0.00019342489402945998,
      "loss": 0.3779646873474121,
      "step": 110
    },
    {
      "epoch": 0.26770775237032907,
      "grad_norm": 0.7473471164703369,
      "learning_rate": 0.00019211732774502372,
      "loss": 0.3981457710266113,
      "step": 120
    },
    {
      "epoch": 0.29001673173452314,
      "grad_norm": 0.5102096796035767,
      "learning_rate": 0.00019069652649198005,
      "loss": 0.355985426902771,
      "step": 130
    },
    {
      "epoch": 0.3123257110987172,
      "grad_norm": 0.9202075004577637,
      "learning_rate": 0.00018916423678631272,
      "loss": 0.4652230262756348,
      "step": 140
    },
    {
      "epoch": 0.33463469046291133,
      "grad_norm": 0.47609537839889526,
      "learning_rate": 0.00018752234219087538,
      "loss": 0.31681218147277834,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 898,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2414173091470272.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}