Hugging Face's logo

yashkumar1112000
/
llamaconvbert-model

PEFT
Model card Files Community
2
yashkumar1112000 commited on
Commit
1ecaa03
•
1 Parent(s): 003fd40

Upload 5 files

Browse files
Files changed (5) hide show
  1. README.md +3 -0
  2. optimizer.pt +3 -0
  3. rng_state.pth +3 -0
  4. scheduler.pt +3 -0
  5. trainer_state.json +156 -0
README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae0be717e2a87a3a0872e8c7a75dd0d48366bb9bc2219688952ab0b5e42203f3
3
+ size 33661637
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c90df9adb792c9f3601f79c22ee2023de722e8cd4c9b23d1609764ed637ed010
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ef30a43d20754fbeee89803ef955a46ca7e92fb8c40af3bdae2eaff291dcf94
3
+ size 627
trainer_state.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 2.080679416656494,
3
+ "best_model_checkpoint": "experiments/checkpoint-30",
4
+ "epoch": 7.529411764705882,
5
+ "global_step": 100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.75,
12
+ "learning_rate": 0.0003,
13
+ "loss": 3.069,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.75,
18
+ "eval_loss": 2.506248712539673,
19
+ "eval_runtime": 36.514,
20
+ "eval_samples_per_second": 5.477,
21
+ "eval_steps_per_second": 0.685,
22
+ "step": 10
23
+ },
24
+ {
25
+ "epoch": 1.51,
26
+ "learning_rate": 0.0002666666666666666,
27
+ "loss": 2.2982,
28
+ "step": 20
29
+ },
30
+ {
31
+ "epoch": 1.51,
32
+ "eval_loss": 2.081218957901001,
33
+ "eval_runtime": 36.5059,
34
+ "eval_samples_per_second": 5.479,
35
+ "eval_steps_per_second": 0.685,
36
+ "step": 20
37
+ },
38
+ {
39
+ "epoch": 2.26,
40
+ "learning_rate": 0.0002333333333333333,
41
+ "loss": 2.1043,
42
+ "step": 30
43
+ },
44
+ {
45
+ "epoch": 2.26,
46
+ "eval_loss": 2.080679416656494,
47
+ "eval_runtime": 36.4738,
48
+ "eval_samples_per_second": 5.483,
49
+ "eval_steps_per_second": 0.685,
50
+ "step": 30
51
+ },
52
+ {
53
+ "epoch": 3.01,
54
+ "learning_rate": 0.00019999999999999998,
55
+ "loss": 2.1125,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 3.01,
60
+ "eval_loss": 2.0814473628997803,
61
+ "eval_runtime": 36.4244,
62
+ "eval_samples_per_second": 5.491,
63
+ "eval_steps_per_second": 0.686,
64
+ "step": 40
65
+ },
66
+ {
67
+ "epoch": 3.76,
68
+ "learning_rate": 0.00016666666666666666,
69
+ "loss": 2.1094,
70
+ "step": 50
71
+ },
72
+ {
73
+ "epoch": 3.76,
74
+ "eval_loss": 2.081106662750244,
75
+ "eval_runtime": 36.5033,
76
+ "eval_samples_per_second": 5.479,
77
+ "eval_steps_per_second": 0.685,
78
+ "step": 50
79
+ },
80
+ {
81
+ "epoch": 4.52,
82
+ "learning_rate": 0.0001333333333333333,
83
+ "loss": 2.1128,
84
+ "step": 60
85
+ },
86
+ {
87
+ "epoch": 4.52,
88
+ "eval_loss": 2.0811569690704346,
89
+ "eval_runtime": 36.4577,
90
+ "eval_samples_per_second": 5.486,
91
+ "eval_steps_per_second": 0.686,
92
+ "step": 60
93
+ },
94
+ {
95
+ "epoch": 5.27,
96
+ "learning_rate": 9.999999999999999e-05,
97
+ "loss": 2.1102,
98
+ "step": 70
99
+ },
100
+ {
101
+ "epoch": 5.27,
102
+ "eval_loss": 2.0808606147766113,
103
+ "eval_runtime": 36.4061,
104
+ "eval_samples_per_second": 5.494,
105
+ "eval_steps_per_second": 0.687,
106
+ "step": 70
107
+ },
108
+ {
109
+ "epoch": 6.02,
110
+ "learning_rate": 6.666666666666666e-05,
111
+ "loss": 2.1057,
112
+ "step": 80
113
+ },
114
+ {
115
+ "epoch": 6.02,
116
+ "eval_loss": 2.081094741821289,
117
+ "eval_runtime": 36.535,
118
+ "eval_samples_per_second": 5.474,
119
+ "eval_steps_per_second": 0.684,
120
+ "step": 80
121
+ },
122
+ {
123
+ "epoch": 6.78,
124
+ "learning_rate": 3.333333333333333e-05,
125
+ "loss": 2.1069,
126
+ "step": 90
127
+ },
128
+ {
129
+ "epoch": 6.78,
130
+ "eval_loss": 2.0808064937591553,
131
+ "eval_runtime": 36.4018,
132
+ "eval_samples_per_second": 5.494,
133
+ "eval_steps_per_second": 0.687,
134
+ "step": 90
135
+ },
136
+ {
137
+ "epoch": 7.53,
138
+ "learning_rate": 0.0,
139
+ "loss": 2.1147,
140
+ "step": 100
141
+ },
142
+ {
143
+ "epoch": 7.53,
144
+ "eval_loss": 2.0808823108673096,
145
+ "eval_runtime": 36.4455,
146
+ "eval_samples_per_second": 5.488,
147
+ "eval_steps_per_second": 0.686,
148
+ "step": 100
149
+ }
150
+ ],
151
+ "max_steps": 100,
152
+ "num_train_epochs": 8,
153
+ "total_flos": 6.900128905592832e+16,
154
+ "trial_name": null,
155
+ "trial_params": null
156
+ }