Hugging Face's logo

cs552-mlp
/
phi3-lora-arc

PEFT
Safetensors
Model card Files
xet
Community
phi3-lora-arc
File size: 4,530 Bytes
a2927e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
 
{
  "best_metric": 1.3153774738311768,
  "best_model_checkpoint": "./output/checkpoints/2024-06-11_10-50-46/checkpoint-10",
  "epoch": 0.5555555555555556,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.9254094362258911,
      "learning_rate": 0.0002,
      "loss": 3.544,
      "step": 1
    },
    {
      "epoch": 0.05555555555555555,
      "eval_loss": 3.981394052505493,
      "eval_runtime": 12.6022,
      "eval_samples_per_second": 11.347,
      "eval_steps_per_second": 0.714,
      "step": 1
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 2.0063693523406982,
      "learning_rate": 0.0004,
      "loss": 3.6373,
      "step": 2
    },
    {
      "epoch": 0.1111111111111111,
      "eval_loss": 3.173820972442627,
      "eval_runtime": 12.6737,
      "eval_samples_per_second": 11.283,
      "eval_steps_per_second": 0.71,
      "step": 2
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 2.0154714584350586,
      "learning_rate": 0.000375,
      "loss": 2.7246,
      "step": 3
    },
    {
      "epoch": 0.16666666666666666,
      "eval_loss": 1.9138473272323608,
      "eval_runtime": 12.6464,
      "eval_samples_per_second": 11.308,
      "eval_steps_per_second": 0.712,
      "step": 3
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.1926450729370117,
      "learning_rate": 0.00035,
      "loss": 1.4998,
      "step": 4
    },
    {
      "epoch": 0.2222222222222222,
      "eval_loss": 1.4986788034439087,
      "eval_runtime": 12.7087,
      "eval_samples_per_second": 11.252,
      "eval_steps_per_second": 0.708,
      "step": 4
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.8283662796020508,
      "learning_rate": 0.00032500000000000004,
      "loss": 1.1373,
      "step": 5
    },
    {
      "epoch": 0.2777777777777778,
      "eval_loss": 1.3153411149978638,
      "eval_runtime": 12.7034,
      "eval_samples_per_second": 11.257,
      "eval_steps_per_second": 0.708,
      "step": 5
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.6860641241073608,
      "learning_rate": 0.00030000000000000003,
      "loss": 0.9828,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "eval_loss": 1.247497797012329,
      "eval_runtime": 12.6669,
      "eval_samples_per_second": 11.289,
      "eval_steps_per_second": 0.711,
      "step": 6
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.2969834506511688,
      "learning_rate": 0.000275,
      "loss": 0.91,
      "step": 7
    },
    {
      "epoch": 0.3888888888888889,
      "eval_loss": 1.2433477640151978,
      "eval_runtime": 12.6841,
      "eval_samples_per_second": 11.274,
      "eval_steps_per_second": 0.71,
      "step": 7
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.1941613256931305,
      "learning_rate": 0.00025,
      "loss": 0.839,
      "step": 8
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 1.2696853876113892,
      "eval_runtime": 12.7426,
      "eval_samples_per_second": 11.222,
      "eval_steps_per_second": 0.706,
      "step": 8
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.19763241708278656,
      "learning_rate": 0.00022500000000000002,
      "loss": 0.7744,
      "step": 9
    },
    {
      "epoch": 0.5,
      "eval_loss": 1.3031294345855713,
      "eval_runtime": 12.7085,
      "eval_samples_per_second": 11.252,
      "eval_steps_per_second": 0.708,
      "step": 9
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.20671840012073517,
      "learning_rate": 0.0002,
      "loss": 0.7289,
      "step": 10
    },
    {
      "epoch": 0.5555555555555556,
      "eval_loss": 1.3153774738311768,
      "eval_runtime": 12.6745,
      "eval_samples_per_second": 11.283,
      "eval_steps_per_second": 0.71,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3708922028359680.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}