Hugging Face's logo

sayanbanerjee32
/
multimodal-phi3_5-mini-instruct-llava_adapter

PEFT
TensorBoard
Safetensors
Model card Files Metrics Community
multimodal-phi3_5-mini-instruct-llava_adapter
File size: 3,764 Bytes 
846d755
52042cc
 
d396859
 
 
 
846d755
 
 
52042cc
be8bb32
 
d396859
 
 
 
 
f4ec74e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5ff85c3
 
 
 
 
 
 
5d9cc9e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e6693f
 
 
 
 
 
 
2df5fd6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cf631c0
 
 
 
 
 
 
09d2529
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4938578
 
 
 
 
 
 
a213efb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52042cc
 
 
 
 
 
 
be8bb32
 
846d755
 
 
 
 
 
 
 
 
 
d396859
846d755
 
 
 
 
 
 
 
 
 
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
 
{
  "epoch": 0.12814538676607642,
  "global_step": 275,
  "max_steps": 2146,
  "logging_steps": 25,
  "eval_steps": 50,
  "save_steps": 25,
  "train_batch_size": 8,
  "num_train_epochs": 1,
  "num_input_tokens_seen": 0,
  "total_flos": 1.2757378629471437e+17,
  "log_history": [
    {
      "loss": 3.9545,
      "grad_norm": 20.241615295410156,
      "learning_rate": 5.8139534883720933e-05,
      "epoch": 0.011649580615097856,
      "step": 25
    },
    {
      "loss": 0.6469,
      "grad_norm": 0.6640440821647644,
      "learning_rate": 0.00011627906976744187,
      "epoch": 0.023299161230195712,
      "step": 50
    },
    {
      "eval_loss": 0.332077294588089,
      "eval_runtime": 1616.9669,
      "eval_samples_per_second": 0.558,
      "eval_steps_per_second": 0.14,
      "epoch": 0.023299161230195712,
      "step": 50
    },
    {
      "loss": 0.1711,
      "grad_norm": 0.0800417810678482,
      "learning_rate": 0.0001744186046511628,
      "epoch": 0.03494874184529357,
      "step": 75
    },
    {
      "loss": 0.4039,
      "grad_norm": 0.19737310707569122,
      "learning_rate": 0.00023255813953488373,
      "epoch": 0.046598322460391424,
      "step": 100
    },
    {
      "eval_loss": 0.6975870728492737,
      "eval_runtime": 1615.7283,
      "eval_samples_per_second": 0.559,
      "eval_steps_per_second": 0.14,
      "epoch": 0.046598322460391424,
      "step": 100
    },
    {
      "loss": 0.2002,
      "grad_norm": 0.0352032296359539,
      "learning_rate": 0.00029069767441860465,
      "epoch": 0.058247903075489285,
      "step": 125
    },
    {
      "loss": 0.3939,
      "grad_norm": 0.17062194645404816,
      "learning_rate": 0.0003488372093023256,
      "epoch": 0.06989748369058714,
      "step": 150
    },
    {
      "eval_loss": 0.2825596034526825,
      "eval_runtime": 1614.1197,
      "eval_samples_per_second": 0.559,
      "eval_steps_per_second": 0.14,
      "epoch": 0.06989748369058714,
      "step": 150
    },
    {
      "loss": 0.1607,
      "grad_norm": 0.08992636203765869,
      "learning_rate": 0.00040697674418604653,
      "epoch": 0.081547064305685,
      "step": 175
    },
    {
      "loss": 0.3829,
      "grad_norm": 0.960233747959137,
      "learning_rate": 0.00046511627906976747,
      "epoch": 0.09319664492078285,
      "step": 200
    },
    {
      "eval_loss": 0.2506251931190491,
      "eval_runtime": 1617.641,
      "eval_samples_per_second": 0.558,
      "eval_steps_per_second": 0.14,
      "epoch": 0.09319664492078285,
      "step": 200
    },
    {
      "loss": 0.1605,
      "grad_norm": 0.04875573888421059,
      "learning_rate": 0.0004974106680476438,
      "epoch": 0.1048462255358807,
      "step": 225
    },
    {
      "loss": 0.3913,
      "grad_norm": 0.13655845820903778,
      "learning_rate": 0.0004909373381667531,
      "epoch": 0.11649580615097857,
      "step": 250
    },
    {
      "eval_loss": 0.43965786695480347,
      "eval_runtime": 1617.1306,
      "eval_samples_per_second": 0.558,
      "eval_steps_per_second": 0.14,
      "epoch": 0.11649580615097857,
      "step": 250
    },
    {
      "loss": 0.1632,
      "grad_norm": 0.019430797547101974,
      "learning_rate": 0.0004844640082858622,
      "epoch": 0.12814538676607642,
      "step": 275
    }
  ],
  "best_metric": null,
  "best_model_checkpoint": null,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "is_hyper_param_search": false,
  "trial_name": null,
  "trial_params": null,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_training_stop": false,
        "should_epoch_stop": false,
        "should_save": true,
        "should_evaluate": false,
        "should_log": false
      },
      "attributes": {}
    }
  }
}