Commit
•
0bf0462
1
Parent(s):
77c1b43
Upload 10 files
Browse files- .gitattributes +1 -0
- added_tokens.json +4 -0
- config.json +31 -0
- hyper_params.json +1 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +11 -0
- trainer_state.json +523 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<hl>": 250101,
|
3 |
+
"<sep>": 250100
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "logoyazilim/qna_model_0000",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 1024,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 512,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "mt5",
|
19 |
+
"num_decoder_layers": 8,
|
20 |
+
"num_heads": 6,
|
21 |
+
"num_layers": 8,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_max_distance": 128,
|
24 |
+
"relative_attention_num_buckets": 32,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"tokenizer_class": "T5Tokenizer",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.22.2",
|
29 |
+
"use_cache": true,
|
30 |
+
"vocab_size": 250102
|
31 |
+
}
|
hyper_params.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"per_device_train_batch_size": 8, "per_device_eval_batch_size": 8, "gradient_accumulation_steps": 4, "learning_rate": 0.0005, "num_train_epochs": 8, "max_steps": -1}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39e4d8aba7c307a48522cef208303fab075bde4617ba957ab52178342a84228e
|
3 |
+
size 1200729797
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa317e53e3d16a2cecf7bfb32cf0e5dc9532caf47d62af4b3280beeb4abf03bf
|
3 |
+
size 16330732
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"extra_ids": 0,
|
5 |
+
"name_or_path": "ozcangundes/mt5-multitask-qa-qg-turkish",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sp_model_kwargs": {},
|
8 |
+
"special_tokens_map_file": "/root/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
|
9 |
+
"tokenizer_class": "T5Tokenizer",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,523 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.0,
|
5 |
+
"global_step": 41656,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.1,
|
12 |
+
"learning_rate": 0.0004939984636066834,
|
13 |
+
"loss": 1.91,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.19,
|
18 |
+
"learning_rate": 0.0004879969272133666,
|
19 |
+
"loss": 1.7724,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.29,
|
24 |
+
"learning_rate": 0.00048199539082004997,
|
25 |
+
"loss": 1.7095,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.38,
|
30 |
+
"learning_rate": 0.00047599385442673327,
|
31 |
+
"loss": 1.6602,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.48,
|
36 |
+
"learning_rate": 0.0004699923180334166,
|
37 |
+
"loss": 1.6298,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.58,
|
42 |
+
"learning_rate": 0.0004639907816400999,
|
43 |
+
"loss": 1.6032,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.67,
|
48 |
+
"learning_rate": 0.0004579892452467832,
|
49 |
+
"loss": 1.5764,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.77,
|
54 |
+
"learning_rate": 0.00045198770885346653,
|
55 |
+
"loss": 1.5442,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.86,
|
60 |
+
"learning_rate": 0.00044598617246014983,
|
61 |
+
"loss": 1.5179,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.96,
|
66 |
+
"learning_rate": 0.00043998463606683314,
|
67 |
+
"loss": 1.5161,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 1.06,
|
72 |
+
"learning_rate": 0.0004339830996735164,
|
73 |
+
"loss": 1.421,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.15,
|
78 |
+
"learning_rate": 0.00042798156328019974,
|
79 |
+
"loss": 1.3698,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.25,
|
84 |
+
"learning_rate": 0.00042198002688688304,
|
85 |
+
"loss": 1.389,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.34,
|
90 |
+
"learning_rate": 0.00041597849049356634,
|
91 |
+
"loss": 1.3715,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.44,
|
96 |
+
"learning_rate": 0.00040997695410024965,
|
97 |
+
"loss": 1.3656,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.54,
|
102 |
+
"learning_rate": 0.00040397541770693295,
|
103 |
+
"loss": 1.3575,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.63,
|
108 |
+
"learning_rate": 0.0003979738813136163,
|
109 |
+
"loss": 1.3539,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.73,
|
114 |
+
"learning_rate": 0.0003919723449202996,
|
115 |
+
"loss": 1.3292,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.82,
|
120 |
+
"learning_rate": 0.0003859708085269829,
|
121 |
+
"loss": 1.3215,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.92,
|
126 |
+
"learning_rate": 0.0003799692721336662,
|
127 |
+
"loss": 1.3067,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 2.02,
|
132 |
+
"learning_rate": 0.0003739677357403495,
|
133 |
+
"loss": 1.2928,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 2.11,
|
138 |
+
"learning_rate": 0.00036796619934703287,
|
139 |
+
"loss": 1.2058,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 2.21,
|
144 |
+
"learning_rate": 0.00036196466295371617,
|
145 |
+
"loss": 1.2242,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.3,
|
150 |
+
"learning_rate": 0.00035596312656039947,
|
151 |
+
"loss": 1.2148,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.4,
|
156 |
+
"learning_rate": 0.00034996159016708277,
|
157 |
+
"loss": 1.2109,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.5,
|
162 |
+
"learning_rate": 0.0003439600537737661,
|
163 |
+
"loss": 1.2241,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.59,
|
168 |
+
"learning_rate": 0.00033795851738044943,
|
169 |
+
"loss": 1.221,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.69,
|
174 |
+
"learning_rate": 0.00033195698098713273,
|
175 |
+
"loss": 1.2042,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.78,
|
180 |
+
"learning_rate": 0.00032595544459381603,
|
181 |
+
"loss": 1.2028,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.88,
|
186 |
+
"learning_rate": 0.00031995390820049933,
|
187 |
+
"loss": 1.2017,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.98,
|
192 |
+
"learning_rate": 0.0003139523718071827,
|
193 |
+
"loss": 1.1904,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 3.07,
|
198 |
+
"learning_rate": 0.000307950835413866,
|
199 |
+
"loss": 1.1294,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 3.17,
|
204 |
+
"learning_rate": 0.00030194929902054924,
|
205 |
+
"loss": 1.1156,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 3.26,
|
210 |
+
"learning_rate": 0.00029594776262723254,
|
211 |
+
"loss": 1.1174,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 3.36,
|
216 |
+
"learning_rate": 0.00028994622623391584,
|
217 |
+
"loss": 1.1084,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 3.46,
|
222 |
+
"learning_rate": 0.0002839446898405992,
|
223 |
+
"loss": 1.1026,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 3.55,
|
228 |
+
"learning_rate": 0.0002779431534472825,
|
229 |
+
"loss": 1.1107,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 3.65,
|
234 |
+
"learning_rate": 0.0002719416170539658,
|
235 |
+
"loss": 1.1061,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 3.74,
|
240 |
+
"learning_rate": 0.0002659400806606491,
|
241 |
+
"loss": 1.1148,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 3.84,
|
246 |
+
"learning_rate": 0.0002599385442673324,
|
247 |
+
"loss": 1.1097,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 3.94,
|
252 |
+
"learning_rate": 0.00025393700787401576,
|
253 |
+
"loss": 1.1013,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 4.03,
|
258 |
+
"learning_rate": 0.00024793547148069906,
|
259 |
+
"loss": 1.0682,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 4.13,
|
264 |
+
"learning_rate": 0.00024193393508738237,
|
265 |
+
"loss": 1.0297,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 4.23,
|
270 |
+
"learning_rate": 0.0002359323986940657,
|
271 |
+
"loss": 1.0325,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 4.32,
|
276 |
+
"learning_rate": 0.000229930862300749,
|
277 |
+
"loss": 1.0255,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 4.42,
|
282 |
+
"learning_rate": 0.00022392932590743232,
|
283 |
+
"loss": 1.0325,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 4.51,
|
288 |
+
"learning_rate": 0.00021792778951411563,
|
289 |
+
"loss": 1.0336,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 4.61,
|
294 |
+
"learning_rate": 0.00021192625312079893,
|
295 |
+
"loss": 1.0434,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 4.71,
|
300 |
+
"learning_rate": 0.00020592471672748226,
|
301 |
+
"loss": 1.0244,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 4.8,
|
306 |
+
"learning_rate": 0.00019992318033416553,
|
307 |
+
"loss": 1.0333,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 4.9,
|
312 |
+
"learning_rate": 0.00019392164394084886,
|
313 |
+
"loss": 1.033,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 4.99,
|
318 |
+
"learning_rate": 0.00018792010754753216,
|
319 |
+
"loss": 1.0327,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 5.09,
|
324 |
+
"learning_rate": 0.0001819185711542155,
|
325 |
+
"loss": 0.9682,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 5.19,
|
330 |
+
"learning_rate": 0.0001759170347608988,
|
331 |
+
"loss": 0.9799,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 5.28,
|
336 |
+
"learning_rate": 0.0001699154983675821,
|
337 |
+
"loss": 0.9725,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 5.38,
|
342 |
+
"learning_rate": 0.00016391396197426542,
|
343 |
+
"loss": 0.9675,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 5.47,
|
348 |
+
"learning_rate": 0.00015791242558094873,
|
349 |
+
"loss": 0.9746,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 5.57,
|
354 |
+
"learning_rate": 0.00015191088918763205,
|
355 |
+
"loss": 0.9726,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 5.67,
|
360 |
+
"learning_rate": 0.00014590935279431536,
|
361 |
+
"loss": 0.9804,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 5.76,
|
366 |
+
"learning_rate": 0.00013990781640099868,
|
367 |
+
"loss": 0.9677,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 5.86,
|
372 |
+
"learning_rate": 0.00013390628000768196,
|
373 |
+
"loss": 0.9757,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 5.95,
|
378 |
+
"learning_rate": 0.00012790474361436526,
|
379 |
+
"loss": 0.9504,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 6.05,
|
384 |
+
"learning_rate": 0.00012190320722104859,
|
385 |
+
"loss": 0.9511,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 6.15,
|
390 |
+
"learning_rate": 0.00011590167082773189,
|
391 |
+
"loss": 0.9176,
|
392 |
+
"step": 32000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 6.24,
|
396 |
+
"learning_rate": 0.00010990013443441521,
|
397 |
+
"loss": 0.9248,
|
398 |
+
"step": 32500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 6.34,
|
402 |
+
"learning_rate": 0.00010389859804109852,
|
403 |
+
"loss": 0.9145,
|
404 |
+
"step": 33000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 6.43,
|
408 |
+
"learning_rate": 9.789706164778184e-05,
|
409 |
+
"loss": 0.9163,
|
410 |
+
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 6.53,
|
414 |
+
"learning_rate": 9.189552525446515e-05,
|
415 |
+
"loss": 0.9233,
|
416 |
+
"step": 34000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 6.63,
|
420 |
+
"learning_rate": 8.589398886114845e-05,
|
421 |
+
"loss": 0.9315,
|
422 |
+
"step": 34500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 6.72,
|
426 |
+
"learning_rate": 7.989245246783177e-05,
|
427 |
+
"loss": 0.9184,
|
428 |
+
"step": 35000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 6.82,
|
432 |
+
"learning_rate": 7.389091607451507e-05,
|
433 |
+
"loss": 0.9263,
|
434 |
+
"step": 35500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 6.91,
|
438 |
+
"learning_rate": 6.788937968119839e-05,
|
439 |
+
"loss": 0.9189,
|
440 |
+
"step": 36000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 7.01,
|
444 |
+
"learning_rate": 6.18878432878817e-05,
|
445 |
+
"loss": 0.912,
|
446 |
+
"step": 36500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 7.11,
|
450 |
+
"learning_rate": 5.588630689456501e-05,
|
451 |
+
"loss": 0.89,
|
452 |
+
"step": 37000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 7.2,
|
456 |
+
"learning_rate": 4.9884770501248326e-05,
|
457 |
+
"loss": 0.8878,
|
458 |
+
"step": 37500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 7.3,
|
462 |
+
"learning_rate": 4.388323410793163e-05,
|
463 |
+
"loss": 0.8822,
|
464 |
+
"step": 38000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 7.39,
|
468 |
+
"learning_rate": 3.7881697714614944e-05,
|
469 |
+
"loss": 0.8887,
|
470 |
+
"step": 38500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 7.49,
|
474 |
+
"learning_rate": 3.188016132129825e-05,
|
475 |
+
"loss": 0.8717,
|
476 |
+
"step": 39000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 7.59,
|
480 |
+
"learning_rate": 2.5878624927981564e-05,
|
481 |
+
"loss": 0.8945,
|
482 |
+
"step": 39500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 7.68,
|
486 |
+
"learning_rate": 1.9877088534664873e-05,
|
487 |
+
"loss": 0.8851,
|
488 |
+
"step": 40000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 7.78,
|
492 |
+
"learning_rate": 1.3875552141348186e-05,
|
493 |
+
"loss": 0.8871,
|
494 |
+
"step": 40500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 7.87,
|
498 |
+
"learning_rate": 7.874015748031496e-06,
|
499 |
+
"loss": 0.8934,
|
500 |
+
"step": 41000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 7.97,
|
504 |
+
"learning_rate": 1.872479354714807e-06,
|
505 |
+
"loss": 0.8863,
|
506 |
+
"step": 41500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 8.0,
|
510 |
+
"step": 41656,
|
511 |
+
"total_flos": 4.8424619578097664e+17,
|
512 |
+
"train_loss": 1.139437837565909,
|
513 |
+
"train_runtime": 38132.6596,
|
514 |
+
"train_samples_per_second": 34.957,
|
515 |
+
"train_steps_per_second": 1.092
|
516 |
+
}
|
517 |
+
],
|
518 |
+
"max_steps": 41656,
|
519 |
+
"num_train_epochs": 8,
|
520 |
+
"total_flos": 4.8424619578097664e+17,
|
521 |
+
"trial_name": null,
|
522 |
+
"trial_params": null
|
523 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8f54b2682867ea79c0a36c35cf42f6502cd6244c0cb634f536739498550f160
|
3 |
+
size 3375
|