Qin Liu
commited on
Commit
•
2e941fc
1
Parent(s):
dcb4977
Model save
Browse files- README.md +67 -0
- all_results.json +8 -0
- runs/Apr26_00-53-24_COE-CS-sv003/events.out.tfevents.1714092919.COE-CS-sv003.472150.0 +2 -2
- train_results.json +8 -0
- trainer_state.json +500 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: Undi95/Meta-Llama-3-8B-hf
|
9 |
+
model-index:
|
10 |
+
- name: llama3-poison-10p-2048
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# llama3-poison-10p-2048
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: nan
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0002
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 4
|
43 |
+
- seed: 42
|
44 |
+
- distributed_type: multi-GPU
|
45 |
+
- num_devices: 4
|
46 |
+
- gradient_accumulation_steps: 2
|
47 |
+
- total_train_batch_size: 64
|
48 |
+
- total_eval_batch_size: 16
|
49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
+
- lr_scheduler_type: cosine
|
51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
52 |
+
- num_epochs: 1
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
58 |
+
| 0.0 | 1.0 | 328 | nan |
|
59 |
+
|
60 |
+
|
61 |
+
### Framework versions
|
62 |
+
|
63 |
+
- PEFT 0.7.1
|
64 |
+
- Transformers 4.39.0.dev0
|
65 |
+
- Pytorch 2.1.2
|
66 |
+
- Datasets 2.14.6
|
67 |
+
- Tokenizers 0.15.2
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.0,
|
4 |
+
"train_runtime": 5407.763,
|
5 |
+
"train_samples": 20971,
|
6 |
+
"train_samples_per_second": 3.878,
|
7 |
+
"train_steps_per_second": 0.061
|
8 |
+
}
|
runs/Apr26_00-53-24_COE-CS-sv003/events.out.tfevents.1714092919.COE-CS-sv003.472150.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8968130c43ae61ff724acf02e89ab9fc68d970f983a60efbe4d4dddedad81a7
|
3 |
+
size 19188
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.0,
|
4 |
+
"train_runtime": 5407.763,
|
5 |
+
"train_samples": 20971,
|
6 |
+
"train_samples_per_second": 3.878,
|
7 |
+
"train_steps_per_second": 0.061
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,500 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 328,
|
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 |
+
"grad_norm": 0.0,
|
14 |
+
"learning_rate": 6.060606060606061e-06,
|
15 |
+
"loss": 0.0,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.02,
|
20 |
+
"grad_norm": 0.0,
|
21 |
+
"learning_rate": 3.0303030303030306e-05,
|
22 |
+
"loss": 0.0,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.03,
|
27 |
+
"grad_norm": 0.0,
|
28 |
+
"learning_rate": 6.060606060606061e-05,
|
29 |
+
"loss": 0.0,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.05,
|
34 |
+
"grad_norm": 0.0,
|
35 |
+
"learning_rate": 9.090909090909092e-05,
|
36 |
+
"loss": 0.0,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.06,
|
41 |
+
"grad_norm": 0.0,
|
42 |
+
"learning_rate": 0.00012121212121212122,
|
43 |
+
"loss": 0.0,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.08,
|
48 |
+
"grad_norm": 0.0,
|
49 |
+
"learning_rate": 0.00015151515151515152,
|
50 |
+
"loss": 0.0,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.09,
|
55 |
+
"grad_norm": 0.0,
|
56 |
+
"learning_rate": 0.00018181818181818183,
|
57 |
+
"loss": 0.0,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.11,
|
62 |
+
"grad_norm": 0.0,
|
63 |
+
"learning_rate": 0.0001999773186295914,
|
64 |
+
"loss": 0.0,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.12,
|
69 |
+
"grad_norm": 0.0,
|
70 |
+
"learning_rate": 0.00019972227135924052,
|
71 |
+
"loss": 0.0,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.14,
|
76 |
+
"grad_norm": 0.0,
|
77 |
+
"learning_rate": 0.00019918455047624847,
|
78 |
+
"loss": 0.0,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.15,
|
83 |
+
"grad_norm": 0.0,
|
84 |
+
"learning_rate": 0.00019836568020887964,
|
85 |
+
"loss": 0.0,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.17,
|
90 |
+
"grad_norm": 0.0,
|
91 |
+
"learning_rate": 0.00019726798173387415,
|
92 |
+
"loss": 0.0,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.18,
|
97 |
+
"grad_norm": 0.0,
|
98 |
+
"learning_rate": 0.00019589456659682057,
|
99 |
+
"loss": 0.0,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.2,
|
104 |
+
"grad_norm": 0.0,
|
105 |
+
"learning_rate": 0.00019424932789214157,
|
106 |
+
"loss": 0.0,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.21,
|
111 |
+
"grad_norm": 0.0,
|
112 |
+
"learning_rate": 0.00019233692922769496,
|
113 |
+
"loss": 0.0,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.23,
|
118 |
+
"grad_norm": 0.0,
|
119 |
+
"learning_rate": 0.00019016279150527044,
|
120 |
+
"loss": 0.0,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.24,
|
125 |
+
"grad_norm": 0.0,
|
126 |
+
"learning_rate": 0.00018773307755445465,
|
127 |
+
"loss": 0.0,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.26,
|
132 |
+
"grad_norm": 0.0,
|
133 |
+
"learning_rate": 0.0001850546746634211,
|
134 |
+
"loss": 0.0,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.27,
|
139 |
+
"grad_norm": 0.0,
|
140 |
+
"learning_rate": 0.00018213517505616338,
|
141 |
+
"loss": 0.0,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.29,
|
146 |
+
"grad_norm": 0.0,
|
147 |
+
"learning_rate": 0.0001789828543715116,
|
148 |
+
"loss": 0.0,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.3,
|
153 |
+
"grad_norm": 0.0,
|
154 |
+
"learning_rate": 0.00017560664820493498,
|
155 |
+
"loss": 0.0,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.32,
|
160 |
+
"grad_norm": 0.0,
|
161 |
+
"learning_rate": 0.0001720161267796256,
|
162 |
+
"loss": 0.0,
|
163 |
+
"step": 105
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.34,
|
167 |
+
"grad_norm": 0.0,
|
168 |
+
"learning_rate": 0.00016822146781866098,
|
169 |
+
"loss": 0.0,
|
170 |
+
"step": 110
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.35,
|
174 |
+
"grad_norm": 0.0,
|
175 |
+
"learning_rate": 0.00016423342769514228,
|
176 |
+
"loss": 0.0,
|
177 |
+
"step": 115
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.37,
|
181 |
+
"grad_norm": 0.0,
|
182 |
+
"learning_rate": 0.0001600633109420861,
|
183 |
+
"loss": 0.0,
|
184 |
+
"step": 120
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.38,
|
188 |
+
"grad_norm": 0.0,
|
189 |
+
"learning_rate": 0.00015572293820849753,
|
190 |
+
"loss": 0.0,
|
191 |
+
"step": 125
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.4,
|
195 |
+
"grad_norm": 0.0,
|
196 |
+
"learning_rate": 0.0001512246127524561,
|
197 |
+
"loss": 0.0,
|
198 |
+
"step": 130
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.41,
|
202 |
+
"grad_norm": 0.0,
|
203 |
+
"learning_rate": 0.00014658108556619417,
|
204 |
+
"loss": 0.0,
|
205 |
+
"step": 135
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.43,
|
209 |
+
"grad_norm": 0.0,
|
210 |
+
"learning_rate": 0.00014180551923202405,
|
211 |
+
"loss": 0.0,
|
212 |
+
"step": 140
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.44,
|
216 |
+
"grad_norm": 0.0,
|
217 |
+
"learning_rate": 0.00013691145061156844,
|
218 |
+
"loss": 0.0,
|
219 |
+
"step": 145
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.46,
|
223 |
+
"grad_norm": 0.0,
|
224 |
+
"learning_rate": 0.00013191275247405527,
|
225 |
+
"loss": 0.0,
|
226 |
+
"step": 150
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.47,
|
230 |
+
"grad_norm": 0.0,
|
231 |
+
"learning_rate": 0.0001268235941724463,
|
232 |
+
"loss": 0.0,
|
233 |
+
"step": 155
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.49,
|
237 |
+
"grad_norm": 0.0,
|
238 |
+
"learning_rate": 0.00012165840147886656,
|
239 |
+
"loss": 0.0,
|
240 |
+
"step": 160
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.5,
|
244 |
+
"grad_norm": 0.0,
|
245 |
+
"learning_rate": 0.00011643181569318595,
|
246 |
+
"loss": 0.0,
|
247 |
+
"step": 165
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.52,
|
251 |
+
"grad_norm": 0.0,
|
252 |
+
"learning_rate": 0.00011115865214066414,
|
253 |
+
"loss": 0.0,
|
254 |
+
"step": 170
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.53,
|
258 |
+
"grad_norm": 0.0,
|
259 |
+
"learning_rate": 0.00010585385817630137,
|
260 |
+
"loss": 0.0,
|
261 |
+
"step": 175
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.55,
|
265 |
+
"grad_norm": 0.0,
|
266 |
+
"learning_rate": 0.00010053247081493685,
|
267 |
+
"loss": 0.0,
|
268 |
+
"step": 180
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.56,
|
272 |
+
"grad_norm": 0.0,
|
273 |
+
"learning_rate": 9.520957410719632e-05,
|
274 |
+
"loss": 0.0,
|
275 |
+
"step": 185
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.58,
|
279 |
+
"grad_norm": 0.0,
|
280 |
+
"learning_rate": 8.990025638211179e-05,
|
281 |
+
"loss": 0.0,
|
282 |
+
"step": 190
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.59,
|
286 |
+
"grad_norm": 0.0,
|
287 |
+
"learning_rate": 8.461956747761374e-05,
|
288 |
+
"loss": 0.0,
|
289 |
+
"step": 195
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.61,
|
293 |
+
"grad_norm": 0.0,
|
294 |
+
"learning_rate": 7.938247608013021e-05,
|
295 |
+
"loss": 0.0,
|
296 |
+
"step": 200
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.62,
|
300 |
+
"grad_norm": 0.0,
|
301 |
+
"learning_rate": 7.420382729421883e-05,
|
302 |
+
"loss": 0.0,
|
303 |
+
"step": 205
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.64,
|
307 |
+
"grad_norm": 0.0,
|
308 |
+
"learning_rate": 6.909830056250527e-05,
|
309 |
+
"loss": 0.0,
|
310 |
+
"step": 210
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.66,
|
314 |
+
"grad_norm": 0.0,
|
315 |
+
"learning_rate": 6.408036805520801e-05,
|
316 |
+
"loss": 0.0,
|
317 |
+
"step": 215
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.67,
|
321 |
+
"grad_norm": 0.0,
|
322 |
+
"learning_rate": 5.916425364719975e-05,
|
323 |
+
"loss": 0.0,
|
324 |
+
"step": 220
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.69,
|
328 |
+
"grad_norm": 0.0,
|
329 |
+
"learning_rate": 5.436389259888841e-05,
|
330 |
+
"loss": 0.0,
|
331 |
+
"step": 225
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.7,
|
335 |
+
"grad_norm": 0.0,
|
336 |
+
"learning_rate": 4.969289205520778e-05,
|
337 |
+
"loss": 0.0,
|
338 |
+
"step": 230
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.72,
|
342 |
+
"grad_norm": 0.0,
|
343 |
+
"learning_rate": 4.516449247468666e-05,
|
344 |
+
"loss": 0.0,
|
345 |
+
"step": 235
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.73,
|
349 |
+
"grad_norm": 0.0,
|
350 |
+
"learning_rate": 4.0791530097930676e-05,
|
351 |
+
"loss": 0.0,
|
352 |
+
"step": 240
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.75,
|
356 |
+
"grad_norm": 0.0,
|
357 |
+
"learning_rate": 3.658640056190378e-05,
|
358 |
+
"loss": 0.0,
|
359 |
+
"step": 245
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.76,
|
363 |
+
"grad_norm": 0.0,
|
364 |
+
"learning_rate": 3.256102376314824e-05,
|
365 |
+
"loss": 0.0,
|
366 |
+
"step": 250
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.78,
|
370 |
+
"grad_norm": 0.0,
|
371 |
+
"learning_rate": 2.872681006954315e-05,
|
372 |
+
"loss": 0.0,
|
373 |
+
"step": 255
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.79,
|
377 |
+
"grad_norm": 0.0,
|
378 |
+
"learning_rate": 2.5094627976376927e-05,
|
379 |
+
"loss": 0.0,
|
380 |
+
"step": 260
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.81,
|
384 |
+
"grad_norm": 0.0,
|
385 |
+
"learning_rate": 2.167477329841633e-05,
|
386 |
+
"loss": 0.0,
|
387 |
+
"step": 265
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.82,
|
391 |
+
"grad_norm": 0.0,
|
392 |
+
"learning_rate": 1.8476939985301256e-05,
|
393 |
+
"loss": 0.0,
|
394 |
+
"step": 270
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.84,
|
398 |
+
"grad_norm": 0.0,
|
399 |
+
"learning_rate": 1.5510192642991073e-05,
|
400 |
+
"loss": 0.0,
|
401 |
+
"step": 275
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.85,
|
405 |
+
"grad_norm": 0.0,
|
406 |
+
"learning_rate": 1.2782940839154111e-05,
|
407 |
+
"loss": 0.0,
|
408 |
+
"step": 280
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.87,
|
412 |
+
"grad_norm": 0.0,
|
413 |
+
"learning_rate": 1.0302915265334723e-05,
|
414 |
+
"loss": 0.0,
|
415 |
+
"step": 285
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.88,
|
419 |
+
"grad_norm": 0.0,
|
420 |
+
"learning_rate": 8.077145823467924e-06,
|
421 |
+
"loss": 0.0,
|
422 |
+
"step": 290
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.9,
|
426 |
+
"grad_norm": 0.0,
|
427 |
+
"learning_rate": 6.111941698858681e-06,
|
428 |
+
"loss": 0.0,
|
429 |
+
"step": 295
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.91,
|
433 |
+
"grad_norm": 0.0,
|
434 |
+
"learning_rate": 4.412873476110702e-06,
|
435 |
+
"loss": 0.0,
|
436 |
+
"step": 300
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.93,
|
440 |
+
"grad_norm": 0.0,
|
441 |
+
"learning_rate": 2.984757348699152e-06,
|
442 |
+
"loss": 0.0,
|
443 |
+
"step": 305
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.95,
|
447 |
+
"grad_norm": 0.0,
|
448 |
+
"learning_rate": 1.8316414669469539e-06,
|
449 |
+
"loss": 0.0,
|
450 |
+
"step": 310
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.96,
|
454 |
+
"grad_norm": 0.0,
|
455 |
+
"learning_rate": 9.567944631029169e-07,
|
456 |
+
"loss": 0.0,
|
457 |
+
"step": 315
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.98,
|
461 |
+
"grad_norm": 0.0,
|
462 |
+
"learning_rate": 3.6269618604847233e-07,
|
463 |
+
"loss": 0.0,
|
464 |
+
"step": 320
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.99,
|
468 |
+
"grad_norm": 0.0,
|
469 |
+
"learning_rate": 5.103067189662358e-08,
|
470 |
+
"loss": 0.0,
|
471 |
+
"step": 325
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.0,
|
475 |
+
"eval_loss": NaN,
|
476 |
+
"eval_runtime": 207.504,
|
477 |
+
"eval_samples_per_second": 11.132,
|
478 |
+
"eval_steps_per_second": 0.699,
|
479 |
+
"step": 328
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.0,
|
483 |
+
"step": 328,
|
484 |
+
"total_flos": 3727285442576384.0,
|
485 |
+
"train_loss": 0.0,
|
486 |
+
"train_runtime": 5407.763,
|
487 |
+
"train_samples_per_second": 3.878,
|
488 |
+
"train_steps_per_second": 0.061
|
489 |
+
}
|
490 |
+
],
|
491 |
+
"logging_steps": 5,
|
492 |
+
"max_steps": 328,
|
493 |
+
"num_input_tokens_seen": 0,
|
494 |
+
"num_train_epochs": 1,
|
495 |
+
"save_steps": 100,
|
496 |
+
"total_flos": 3727285442576384.0,
|
497 |
+
"train_batch_size": 8,
|
498 |
+
"trial_name": null,
|
499 |
+
"trial_params": null
|
500 |
+
}
|