Hugging Face's logo

Udith-Sandaruwan
/
Llama-3.1-8B-CP-HP-check

TensorBoard
Safetensors
llama
Model card Files Metrics Community
Udith-Sandaruwan commited on
Commit
6502585
·
verified ·
1 Parent(s): f9ec40c

Organize logs inside session_logs/

Browse files
Files changed (9) hide show
  1. session_logs/cp_finetuning_hp.log +10 -0
  2. session_logs/evaluation_results.json +180 -0
  3. session_logs/hyperparameter_results.csv +3 -0
  4. session_logs/logs/events.out.tfevents.1739332676.90b0634756a3.20917.0 +3 -0
  5. session_logs/logs/events.out.tfevents.1739333199.90b0634756a3.20917.1 +3 -0
  6. session_logs/logs/events.out.tfevents.1739335096.90b0634756a3.33581.0 +3 -0
  7. session_logs/logs/events.out.tfevents.1739335486.90b0634756a3.33581.1 +3 -0
  8. session_logs/logs/events.out.tfevents.1739335927.90b0634756a3.39823.0 +3 -0
  9. session_logs/logs/events.out.tfevents.1739336307.90b0634756a3.39823.1 +3 -0
session_logs/cp_finetuning_hp.log ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ 2025-02-12 04:51:38,115 - Logging initialized for session: 908c5f0a-aba2-42b8-9341-5223b5f944db
2
+ 2025-02-12 04:52:06,750 - Training with params:learning_rate=0.0002521627789110728, gradient_accumulation_steps=3
3
+ 2025-02-12 04:52:06,810 - Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
4
+ 2025-02-12 04:58:26,104 - Using default tokenizer.
5
+ 2025-02-12 04:58:27,088 - Evaluation Results: {'meteor_scores': {'meteor': 0.054151624548736454}, 'rouge_scores': {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0}, 'bleu_scores': {'bleu': 0.0, 'precisions': [0.13157894736842105, 0.0, 0.0, 0.0], 'brevity_penalty': 1.0, 'length_ratio': 1.4074074074074074, 'translation_length': 38, 'reference_length': 27}, 'perplexity': 10956146688.0}
6
+ 2025-02-12 04:58:27,137 - Training with params:learning_rate=0.0009522287748511998, gradient_accumulation_steps=2
7
+ 2025-02-12 04:58:27,226 - Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
8
+ 2025-02-12 05:04:42,444 - Using default tokenizer.
9
+ 2025-02-12 05:04:43,340 - Evaluation Results: {'meteor_scores': {'meteor': 0.054545454545454536}, 'rouge_scores': {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0}, 'bleu_scores': {'bleu': 0.0, 'precisions': [0.125, 0.0, 0.0, 0.0], 'brevity_penalty': 1.0, 'length_ratio': 1.4814814814814814, 'translation_length': 40, 'reference_length': 27}, 'perplexity': 10289992704.0}
10
+ 2025-02-12 05:04:43,341 - Best hyperparameters: {'gradient_accumulation_steps': 2.000081988144676, 'learning_rate': 0.0009522287748511998}
session_logs/evaluation_results.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "1": {
3
+ "learning_rate": 0.0002521627789110728,
4
+ "gradient_accumulation_steps": 3,
5
+ "eval_results": {
6
+ "meteor_scores": {
7
+ "meteor": 0.05813953488372093
8
+ },
9
+ "rouge_scores": {
10
+ "rouge1": 0.0,
11
+ "rouge2": 0.0,
12
+ "rougeL": 0.0,
13
+ "rougeLsum": 0.0
14
+ },
15
+ "bleu_scores": {
16
+ "bleu": 0.0,
17
+ "precisions": [
18
+ 0.09433962264150944,
19
+ 0.0,
20
+ 0.0,
21
+ 0.0
22
+ ],
23
+ "brevity_penalty": 1.0,
24
+ "length_ratio": 1.962962962962963,
25
+ "translation_length": 53,
26
+ "reference_length": 27
27
+ },
28
+ "perplexity": 10956146688.0
29
+ }
30
+ },
31
+ "2": {
32
+ "learning_rate": 0.0009522287748511998,
33
+ "gradient_accumulation_steps": 2,
34
+ "eval_results": {
35
+ "meteor_scores": {
36
+ "meteor": 0.05813953488372093
37
+ },
38
+ "rouge_scores": {
39
+ "rouge1": 0.0,
40
+ "rouge2": 0.0,
41
+ "rougeL": 0.0,
42
+ "rougeLsum": 0.0
43
+ },
44
+ "bleu_scores": {
45
+ "bleu": 0.0,
46
+ "precisions": [
47
+ 0.09433962264150944,
48
+ 0.0,
49
+ 0.0,
50
+ 0.0
51
+ ],
52
+ "brevity_penalty": 1.0,
53
+ "length_ratio": 1.962962962962963,
54
+ "translation_length": 53,
55
+ "reference_length": 27
56
+ },
57
+ "perplexity": 10289992704.0
58
+ }
59
+ },
60
+ "3": {
61
+ "learning_rate": 0.0002521627789110728,
62
+ "gradient_accumulation_steps": 3,
63
+ "eval_results": {
64
+ "meteor_scores": {
65
+ "meteor": 0.054151624548736454
66
+ },
67
+ "rouge_scores": {
68
+ "rouge1": 0.0,
69
+ "rouge2": 0.0,
70
+ "rougeL": 0.0,
71
+ "rougeLsum": 0.0
72
+ },
73
+ "bleu_scores": {
74
+ "bleu": 0.0,
75
+ "precisions": [
76
+ 0.13157894736842105,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0
80
+ ],
81
+ "brevity_penalty": 1.0,
82
+ "length_ratio": 1.4074074074074074,
83
+ "translation_length": 38,
84
+ "reference_length": 27
85
+ },
86
+ "perplexity": 10956146688.0
87
+ }
88
+ },
89
+ "4": {
90
+ "learning_rate": 0.0009522287748511998,
91
+ "gradient_accumulation_steps": 2,
92
+ "eval_results": {
93
+ "meteor_scores": {
94
+ "meteor": 0.054545454545454536
95
+ },
96
+ "rouge_scores": {
97
+ "rouge1": 0.0,
98
+ "rouge2": 0.0,
99
+ "rougeL": 0.0,
100
+ "rougeLsum": 0.0
101
+ },
102
+ "bleu_scores": {
103
+ "bleu": 0.0,
104
+ "precisions": [
105
+ 0.125,
106
+ 0.0,
107
+ 0.0,
108
+ 0.0
109
+ ],
110
+ "brevity_penalty": 1.0,
111
+ "length_ratio": 1.4814814814814814,
112
+ "translation_length": 40,
113
+ "reference_length": 27
114
+ },
115
+ "perplexity": 10289992704.0
116
+ }
117
+ },
118
+ "5": {
119
+ "learning_rate": 0.0002521627789110728,
120
+ "gradient_accumulation_steps": 3,
121
+ "eval_results": {
122
+ "meteor_scores": {
123
+ "meteor": 0.054151624548736454
124
+ },
125
+ "rouge_scores": {
126
+ "rouge1": 0.0,
127
+ "rouge2": 0.0,
128
+ "rougeL": 0.0,
129
+ "rougeLsum": 0.0
130
+ },
131
+ "bleu_scores": {
132
+ "bleu": 0.0,
133
+ "precisions": [
134
+ 0.13157894736842105,
135
+ 0.0,
136
+ 0.0,
137
+ 0.0
138
+ ],
139
+ "brevity_penalty": 1.0,
140
+ "length_ratio": 1.4074074074074074,
141
+ "translation_length": 38,
142
+ "reference_length": 27
143
+ },
144
+ "perplexity": 10956146688.0
145
+ }
146
+ },
147
+ "6": {
148
+ "learning_rate": 0.0009522287748511998,
149
+ "gradient_accumulation_steps": 2,
150
+ "eval_results": {
151
+ "meteor_scores": {
152
+ "meteor": 0.054545454545454536
153
+ },
154
+ "rouge_scores": {
155
+ "rouge1": 0.0,
156
+ "rouge2": 0.0,
157
+ "rougeL": 0.0,
158
+ "rougeLsum": 0.0
159
+ },
160
+ "bleu_scores": {
161
+ "bleu": 0.0,
162
+ "precisions": [
163
+ 0.125,
164
+ 0.0,
165
+ 0.0,
166
+ 0.0
167
+ ],
168
+ "brevity_penalty": 1.0,
169
+ "length_ratio": 1.4814814814814814,
170
+ "translation_length": 40,
171
+ "reference_length": 27
172
+ },
173
+ "perplexity": 10289992704.0
174
+ }
175
+ },
176
+ "best_param": {
177
+ "learning_rate": 0.0009522287748511998,
178
+ "gradient_accumulation_steps": 2
179
+ }
180
+ }
session_logs/hyperparameter_results.csv ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ learning_rate,gradient_accumulation_steps,eval_results
2
+ 0.0002521627789110728,3,"{'meteor_scores': {'meteor': 0.054151624548736454}, 'rouge_scores': {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0}, 'bleu_scores': {'bleu': 0.0, 'precisions': [0.13157894736842105, 0.0, 0.0, 0.0], 'brevity_penalty': 1.0, 'length_ratio': 1.4074074074074074, 'translation_length': 38, 'reference_length': 27}, 'perplexity': 10956146688.0}"
3
+ 0.0009522287748511998,2,"{'meteor_scores': {'meteor': 0.054545454545454536}, 'rouge_scores': {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0}, 'bleu_scores': {'bleu': 0.0, 'precisions': [0.125, 0.0, 0.0, 0.0], 'brevity_penalty': 1.0, 'length_ratio': 1.4814814814814814, 'translation_length': 40, 'reference_length': 27}, 'perplexity': 10289992704.0}"
session_logs/logs/events.out.tfevents.1739332676.90b0634756a3.20917.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4ffe9ce9f0a9d812c45931e1183bae42dfb367b2b852c583275821a764890e
3
+ size 9810
session_logs/logs/events.out.tfevents.1739333199.90b0634756a3.20917.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2fb2bdb262baa5d6db1ea188a165398b0896e78759d7ab779f64b1f4614f5c
3
+ size 9769
session_logs/logs/events.out.tfevents.1739335096.90b0634756a3.33581.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e350970a4150ddf9ee5c366a8367fae09a07666a1d4e4f6800bb3dcd14e47c4d
3
+ size 10342
session_logs/logs/events.out.tfevents.1739335486.90b0634756a3.33581.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c32a3870450163c08553e70fa581c5b6f729accfe84498a9f8d24f2c1608fe5a
3
+ size 10301
session_logs/logs/events.out.tfevents.1739335927.90b0634756a3.39823.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df6e29ee3b23a4c91497cc0c6459dc3dd8c3a086dcca28ea19fa6f5361b71522
3
+ size 10342
session_logs/logs/events.out.tfevents.1739336307.90b0634756a3.39823.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc71fb91e9f7b4879a4209f885d6824e602c4bedba4bc289f40b3b66cfd6c65
3
+ size 10301