Hugging Face's logo

youssefkhalil320
/
llm2vec-Qwen2-0.5B

PEFT
Safetensors
Model card Files Community
youssefkhalil320 commited on
Commit
59ebeaa
·
verified ·
1 Parent(s): c44c1be

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +15 -0
  2. eval_results.json +10 -0
  3. train_results.json +8 -0
  4. trainer_state.json +134 -0
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.02,
3
+ "eval_accuracy": 0.3776317811587521,
4
+ "eval_loss": 3.4153313636779785,
5
+ "eval_runtime": 420.8675,
6
+ "eval_samples": 510,
7
+ "eval_samples_per_second": 1.212,
8
+ "eval_steps_per_second": 0.304,
9
+ "perplexity": 30.427030169904086,
10
+ "train_loss": 3.5216834716796876,
11
+ "train_runtime": 13589.9527,
12
+ "train_samples": 241770,
13
+ "train_samples_per_second": 17.79,
14
+ "train_steps_per_second": 4.448
15
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.02,
3
+ "eval_accuracy": 0.3776317811587521,
4
+ "eval_loss": 3.4153313636779785,
5
+ "eval_runtime": 420.8675,
6
+ "eval_samples": 510,
7
+ "eval_samples_per_second": 1.212,
8
+ "eval_steps_per_second": 0.304,
9
+ "perplexity": 30.427030169904086
10
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.02,
3
+ "train_loss": 3.5216834716796876,
4
+ "train_runtime": 13589.9527,
5
+ "train_samples": 241770,
6
+ "train_samples_per_second": 17.79,
7
+ "train_steps_per_second": 4.448
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.016544513012259485,
5
+ "eval_steps": 100,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "eval_accuracy": 0.3502469255350053,
14
+ "eval_loss": 3.632826328277588,
15
+ "eval_runtime": 398.6921,
16
+ "eval_samples_per_second": 1.279,
17
+ "eval_steps_per_second": 0.321,
18
+ "step": 100
19
+ },
20
+ {
21
+ "epoch": 0.0,
22
+ "eval_accuracy": 0.3616211331782439,
23
+ "eval_loss": 3.540499210357666,
24
+ "eval_runtime": 408.0902,
25
+ "eval_samples_per_second": 1.25,
26
+ "eval_steps_per_second": 0.314,
27
+ "step": 200
28
+ },
29
+ {
30
+ "epoch": 0.0,
31
+ "eval_accuracy": 0.3631109076341994,
32
+ "eval_loss": 3.538304090499878,
33
+ "eval_runtime": 413.5149,
34
+ "eval_samples_per_second": 1.233,
35
+ "eval_steps_per_second": 0.31,
36
+ "step": 300
37
+ },
38
+ {
39
+ "epoch": 0.01,
40
+ "eval_accuracy": 0.3691925896000462,
41
+ "eval_loss": 3.498488187789917,
42
+ "eval_runtime": 416.6621,
43
+ "eval_samples_per_second": 1.224,
44
+ "eval_steps_per_second": 0.307,
45
+ "step": 400
46
+ },
47
+ {
48
+ "epoch": 0.01,
49
+ "grad_norm": 3.8307032585144043,
50
+ "learning_rate": 4.958638717469351e-05,
51
+ "loss": 3.5814,
52
+ "step": 500
53
+ },
54
+ {
55
+ "epoch": 0.01,
56
+ "eval_accuracy": 0.3655637771728712,
57
+ "eval_loss": 3.510744333267212,
58
+ "eval_runtime": 417.8436,
59
+ "eval_samples_per_second": 1.221,
60
+ "eval_steps_per_second": 0.306,
61
+ "step": 500
62
+ },
63
+ {
64
+ "epoch": 0.01,
65
+ "eval_accuracy": 0.37279766365016237,
66
+ "eval_loss": 3.448606014251709,
67
+ "eval_runtime": 418.2361,
68
+ "eval_samples_per_second": 1.219,
69
+ "eval_steps_per_second": 0.306,
70
+ "step": 600
71
+ },
72
+ {
73
+ "epoch": 0.01,
74
+ "eval_accuracy": 0.37432385775117966,
75
+ "eval_loss": 3.437483072280884,
76
+ "eval_runtime": 424.8484,
77
+ "eval_samples_per_second": 1.2,
78
+ "eval_steps_per_second": 0.301,
79
+ "step": 700
80
+ },
81
+ {
82
+ "epoch": 0.01,
83
+ "eval_accuracy": 0.37553490882454993,
84
+ "eval_loss": 3.4409470558166504,
85
+ "eval_runtime": 426.0459,
86
+ "eval_samples_per_second": 1.197,
87
+ "eval_steps_per_second": 0.3,
88
+ "step": 800
89
+ },
90
+ {
91
+ "epoch": 0.01,
92
+ "eval_accuracy": 0.37346273380746275,
93
+ "eval_loss": 3.4459047317504883,
94
+ "eval_runtime": 426.9882,
95
+ "eval_samples_per_second": 1.194,
96
+ "eval_steps_per_second": 0.3,
97
+ "step": 900
98
+ },
99
+ {
100
+ "epoch": 0.02,
101
+ "grad_norm": 3.9651877880096436,
102
+ "learning_rate": 4.917277434938703e-05,
103
+ "loss": 3.462,
104
+ "step": 1000
105
+ },
106
+ {
107
+ "epoch": 0.02,
108
+ "eval_accuracy": 0.37652163895395724,
109
+ "eval_loss": 3.4321560859680176,
110
+ "eval_runtime": 427.9304,
111
+ "eval_samples_per_second": 1.192,
112
+ "eval_steps_per_second": 0.299,
113
+ "step": 1000
114
+ },
115
+ {
116
+ "epoch": 0.02,
117
+ "step": 1000,
118
+ "total_flos": 4505964380160000.0,
119
+ "train_loss": 3.5216834716796876,
120
+ "train_runtime": 13589.9527,
121
+ "train_samples_per_second": 17.79,
122
+ "train_steps_per_second": 4.448
123
+ }
124
+ ],
125
+ "logging_steps": 500,
126
+ "max_steps": 60443,
127
+ "num_input_tokens_seen": 0,
128
+ "num_train_epochs": 1,
129
+ "save_steps": 200,
130
+ "total_flos": 4505964380160000.0,
131
+ "train_batch_size": 4,
132
+ "trial_name": null,
133
+ "trial_params": null
134
+ }