Delete checkpoint-8961
Browse files- checkpoint-8961/config.json +0 -41
- checkpoint-8961/generation_config.json +0 -16
- checkpoint-8961/model.safetensors +0 -3
- checkpoint-8961/optimizer.pt +0 -3
- checkpoint-8961/rng_state.pth +0 -3
- checkpoint-8961/scaler.pt +0 -3
- checkpoint-8961/scheduler.pt +0 -3
- checkpoint-8961/source.spm +0 -3
- checkpoint-8961/special_tokens_map.json +0 -23
- checkpoint-8961/target.spm +0 -3
- checkpoint-8961/tokenizer_config.json +0 -40
- checkpoint-8961/trainer_state.json +0 -1310
- checkpoint-8961/training_args.bin +0 -3
- checkpoint-8961/vocab.json +0 -0
checkpoint-8961/config.json
DELETED
@@ -1,41 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "ckartal/english-to-turkish-finetuned-model",
|
3 |
-
"activation_dropout": 0.0,
|
4 |
-
"activation_function": "swish",
|
5 |
-
"architectures": [
|
6 |
-
"MarianMTModel"
|
7 |
-
],
|
8 |
-
"attention_dropout": 0.0,
|
9 |
-
"bos_token_id": 0,
|
10 |
-
"classifier_dropout": 0.0,
|
11 |
-
"d_model": 512,
|
12 |
-
"decoder_attention_heads": 8,
|
13 |
-
"decoder_ffn_dim": 2048,
|
14 |
-
"decoder_layerdrop": 0.0,
|
15 |
-
"decoder_layers": 6,
|
16 |
-
"decoder_start_token_id": 59993,
|
17 |
-
"decoder_vocab_size": 59994,
|
18 |
-
"dropout": 0.1,
|
19 |
-
"encoder_attention_heads": 8,
|
20 |
-
"encoder_ffn_dim": 2048,
|
21 |
-
"encoder_layerdrop": 0.0,
|
22 |
-
"encoder_layers": 6,
|
23 |
-
"eos_token_id": 0,
|
24 |
-
"forced_eos_token_id": 0,
|
25 |
-
"init_std": 0.02,
|
26 |
-
"is_encoder_decoder": true,
|
27 |
-
"max_length": null,
|
28 |
-
"max_position_embeddings": 512,
|
29 |
-
"model_type": "marian",
|
30 |
-
"normalize_embedding": false,
|
31 |
-
"num_beams": null,
|
32 |
-
"num_hidden_layers": 6,
|
33 |
-
"pad_token_id": 59993,
|
34 |
-
"scale_embedding": true,
|
35 |
-
"share_encoder_decoder_embeddings": true,
|
36 |
-
"static_position_embeddings": true,
|
37 |
-
"torch_dtype": "float32",
|
38 |
-
"transformers_version": "4.49.0",
|
39 |
-
"use_cache": true,
|
40 |
-
"vocab_size": 59994
|
41 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-8961/generation_config.json
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bad_words_ids": [
|
3 |
-
[
|
4 |
-
59993
|
5 |
-
]
|
6 |
-
],
|
7 |
-
"bos_token_id": 0,
|
8 |
-
"decoder_start_token_id": 59993,
|
9 |
-
"eos_token_id": 0,
|
10 |
-
"forced_eos_token_id": 0,
|
11 |
-
"max_length": 512,
|
12 |
-
"num_beams": 6,
|
13 |
-
"pad_token_id": 59993,
|
14 |
-
"renormalize_logits": true,
|
15 |
-
"transformers_version": "4.49.0"
|
16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-8961/model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:0d68b65a2bd91fa1942bbd3a9736e0dfea53eee5b472c6c4609f74a7efc65371
|
3 |
-
size 299690728
|
|
|
|
|
|
|
|
checkpoint-8961/optimizer.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:e9504ade0945887bc18c4db219e8e77bfcdbad2a247e8fd1f93ab7936c7fdd1d
|
3 |
-
size 599054970
|
|
|
|
|
|
|
|
checkpoint-8961/rng_state.pth
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:12de9ac1380ec85489c1c0ac2e8e97a71139b009320d67f140f242290f6b39b6
|
3 |
-
size 14244
|
|
|
|
|
|
|
|
checkpoint-8961/scaler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:f62134c228b9c6de37631c7eafe659790f04722a4440f8d9c2781df03f3081a3
|
3 |
-
size 988
|
|
|
|
|
|
|
|
checkpoint-8961/scheduler.pt
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:b6434206d5198b72fcdb872b88c17883c2c789d1dea784eef6faa3b3a8d9db9e
|
3 |
-
size 1064
|
|
|
|
|
|
|
|
checkpoint-8961/source.spm
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:98eb24f0995a9d5f7cb0fb628c474628b1d2284615e881e857d062c0b651ce10
|
3 |
-
size 793920
|
|
|
|
|
|
|
|
checkpoint-8961/special_tokens_map.json
DELETED
@@ -1,23 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"eos_token": {
|
3 |
-
"content": "</s>",
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"pad_token": {
|
10 |
-
"content": "<pad>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"unk_token": {
|
17 |
-
"content": "<unk>",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": false,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
}
|
23 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-8961/target.spm
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:45cc6000ed513cdca8f80739087fbcbf9933dc50c9ae36c319c9670882f72e1b
|
3 |
-
size 837876
|
|
|
|
|
|
|
|
checkpoint-8961/tokenizer_config.json
DELETED
@@ -1,40 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "</s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<unk>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"59993": {
|
20 |
-
"content": "<pad>",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
}
|
27 |
-
},
|
28 |
-
"clean_up_tokenization_spaces": true,
|
29 |
-
"eos_token": "</s>",
|
30 |
-
"extra_special_tokens": {},
|
31 |
-
"model_max_length": 512,
|
32 |
-
"pad_token": "<pad>",
|
33 |
-
"return_tensors": "pt",
|
34 |
-
"separate_vocabs": false,
|
35 |
-
"source_lang": "eng",
|
36 |
-
"sp_model_kwargs": {},
|
37 |
-
"target_lang": "tur",
|
38 |
-
"tokenizer_class": "MarianTokenizer",
|
39 |
-
"unk_token": "<unk>"
|
40 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-8961/trainer_state.json
DELETED
@@ -1,1310 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"best_metric": null,
|
3 |
-
"best_model_checkpoint": null,
|
4 |
-
"epoch": 3.0,
|
5 |
-
"eval_steps": 500,
|
6 |
-
"global_step": 8961,
|
7 |
-
"is_hyper_param_search": false,
|
8 |
-
"is_local_process_zero": true,
|
9 |
-
"is_world_process_zero": true,
|
10 |
-
"log_history": [
|
11 |
-
{
|
12 |
-
"epoch": 0.016739203213927016,
|
13 |
-
"grad_norm": 0.439177542924881,
|
14 |
-
"learning_rate": 4.987445597589555e-05,
|
15 |
-
"loss": 1.5222,
|
16 |
-
"step": 50
|
17 |
-
},
|
18 |
-
{
|
19 |
-
"epoch": 0.03347840642785403,
|
20 |
-
"grad_norm": 0.4248828887939453,
|
21 |
-
"learning_rate": 4.973496261577949e-05,
|
22 |
-
"loss": 0.1842,
|
23 |
-
"step": 100
|
24 |
-
},
|
25 |
-
{
|
26 |
-
"epoch": 0.05021760964178105,
|
27 |
-
"grad_norm": 0.3019009232521057,
|
28 |
-
"learning_rate": 4.9595469255663436e-05,
|
29 |
-
"loss": 0.1471,
|
30 |
-
"step": 150
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 0.06695681285570806,
|
34 |
-
"grad_norm": 0.2518245577812195,
|
35 |
-
"learning_rate": 4.9455975895547376e-05,
|
36 |
-
"loss": 0.1306,
|
37 |
-
"step": 200
|
38 |
-
},
|
39 |
-
{
|
40 |
-
"epoch": 0.08369601606963509,
|
41 |
-
"grad_norm": 0.3660012185573578,
|
42 |
-
"learning_rate": 4.931648253543131e-05,
|
43 |
-
"loss": 0.1276,
|
44 |
-
"step": 250
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.1004352192835621,
|
48 |
-
"grad_norm": 0.32854148745536804,
|
49 |
-
"learning_rate": 4.917698917531526e-05,
|
50 |
-
"loss": 0.1048,
|
51 |
-
"step": 300
|
52 |
-
},
|
53 |
-
{
|
54 |
-
"epoch": 0.11717442249748912,
|
55 |
-
"grad_norm": 0.24879515171051025,
|
56 |
-
"learning_rate": 4.90374958151992e-05,
|
57 |
-
"loss": 0.1054,
|
58 |
-
"step": 350
|
59 |
-
},
|
60 |
-
{
|
61 |
-
"epoch": 0.13391362571141613,
|
62 |
-
"grad_norm": 0.36416563391685486,
|
63 |
-
"learning_rate": 4.889800245508314e-05,
|
64 |
-
"loss": 0.0985,
|
65 |
-
"step": 400
|
66 |
-
},
|
67 |
-
{
|
68 |
-
"epoch": 0.15065282892534315,
|
69 |
-
"grad_norm": 0.33641186356544495,
|
70 |
-
"learning_rate": 4.875850909496708e-05,
|
71 |
-
"loss": 0.1044,
|
72 |
-
"step": 450
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"epoch": 0.16739203213927017,
|
76 |
-
"grad_norm": 0.32909244298934937,
|
77 |
-
"learning_rate": 4.861901573485103e-05,
|
78 |
-
"loss": 0.1089,
|
79 |
-
"step": 500
|
80 |
-
},
|
81 |
-
{
|
82 |
-
"epoch": 0.1841312353531972,
|
83 |
-
"grad_norm": 0.36060285568237305,
|
84 |
-
"learning_rate": 4.847952237473497e-05,
|
85 |
-
"loss": 0.09,
|
86 |
-
"step": 550
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 0.2008704385671242,
|
90 |
-
"grad_norm": 0.2510785758495331,
|
91 |
-
"learning_rate": 4.83400290146189e-05,
|
92 |
-
"loss": 0.0884,
|
93 |
-
"step": 600
|
94 |
-
},
|
95 |
-
{
|
96 |
-
"epoch": 0.21760964178105122,
|
97 |
-
"grad_norm": 0.22478719055652618,
|
98 |
-
"learning_rate": 4.820053565450285e-05,
|
99 |
-
"loss": 0.0866,
|
100 |
-
"step": 650
|
101 |
-
},
|
102 |
-
{
|
103 |
-
"epoch": 0.23434884499497824,
|
104 |
-
"grad_norm": 0.37321263551712036,
|
105 |
-
"learning_rate": 4.806104229438679e-05,
|
106 |
-
"loss": 0.0884,
|
107 |
-
"step": 700
|
108 |
-
},
|
109 |
-
{
|
110 |
-
"epoch": 0.25108804820890523,
|
111 |
-
"grad_norm": 0.2660929262638092,
|
112 |
-
"learning_rate": 4.792154893427073e-05,
|
113 |
-
"loss": 0.0819,
|
114 |
-
"step": 750
|
115 |
-
},
|
116 |
-
{
|
117 |
-
"epoch": 0.26782725142283226,
|
118 |
-
"grad_norm": 0.2338525801897049,
|
119 |
-
"learning_rate": 4.778205557415467e-05,
|
120 |
-
"loss": 0.0845,
|
121 |
-
"step": 800
|
122 |
-
},
|
123 |
-
{
|
124 |
-
"epoch": 0.2845664546367593,
|
125 |
-
"grad_norm": 0.308557391166687,
|
126 |
-
"learning_rate": 4.764256221403862e-05,
|
127 |
-
"loss": 0.0815,
|
128 |
-
"step": 850
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 0.3013056578506863,
|
132 |
-
"grad_norm": 0.27098262310028076,
|
133 |
-
"learning_rate": 4.750306885392255e-05,
|
134 |
-
"loss": 0.0833,
|
135 |
-
"step": 900
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"epoch": 0.3180448610646133,
|
139 |
-
"grad_norm": 0.23054952919483185,
|
140 |
-
"learning_rate": 4.736357549380649e-05,
|
141 |
-
"loss": 0.0806,
|
142 |
-
"step": 950
|
143 |
-
},
|
144 |
-
{
|
145 |
-
"epoch": 0.33478406427854035,
|
146 |
-
"grad_norm": 0.21355900168418884,
|
147 |
-
"learning_rate": 4.722408213369044e-05,
|
148 |
-
"loss": 0.073,
|
149 |
-
"step": 1000
|
150 |
-
},
|
151 |
-
{
|
152 |
-
"epoch": 0.3515232674924674,
|
153 |
-
"grad_norm": 0.20395708084106445,
|
154 |
-
"learning_rate": 4.708458877357438e-05,
|
155 |
-
"loss": 0.0775,
|
156 |
-
"step": 1050
|
157 |
-
},
|
158 |
-
{
|
159 |
-
"epoch": 0.3682624707063944,
|
160 |
-
"grad_norm": 0.21063613891601562,
|
161 |
-
"learning_rate": 4.694509541345832e-05,
|
162 |
-
"loss": 0.0789,
|
163 |
-
"step": 1100
|
164 |
-
},
|
165 |
-
{
|
166 |
-
"epoch": 0.3850016739203214,
|
167 |
-
"grad_norm": 0.20589284598827362,
|
168 |
-
"learning_rate": 4.680560205334226e-05,
|
169 |
-
"loss": 0.0809,
|
170 |
-
"step": 1150
|
171 |
-
},
|
172 |
-
{
|
173 |
-
"epoch": 0.4017408771342484,
|
174 |
-
"grad_norm": 0.27975228428840637,
|
175 |
-
"learning_rate": 4.666610869322621e-05,
|
176 |
-
"loss": 0.078,
|
177 |
-
"step": 1200
|
178 |
-
},
|
179 |
-
{
|
180 |
-
"epoch": 0.4184800803481754,
|
181 |
-
"grad_norm": 0.2529745399951935,
|
182 |
-
"learning_rate": 4.6526615333110144e-05,
|
183 |
-
"loss": 0.0704,
|
184 |
-
"step": 1250
|
185 |
-
},
|
186 |
-
{
|
187 |
-
"epoch": 0.43521928356210243,
|
188 |
-
"grad_norm": 0.2205154448747635,
|
189 |
-
"learning_rate": 4.6387121972994084e-05,
|
190 |
-
"loss": 0.0733,
|
191 |
-
"step": 1300
|
192 |
-
},
|
193 |
-
{
|
194 |
-
"epoch": 0.45195848677602946,
|
195 |
-
"grad_norm": 0.2254629135131836,
|
196 |
-
"learning_rate": 4.624762861287803e-05,
|
197 |
-
"loss": 0.0751,
|
198 |
-
"step": 1350
|
199 |
-
},
|
200 |
-
{
|
201 |
-
"epoch": 0.4686976899899565,
|
202 |
-
"grad_norm": 0.17614957690238953,
|
203 |
-
"learning_rate": 4.610813525276197e-05,
|
204 |
-
"loss": 0.0747,
|
205 |
-
"step": 1400
|
206 |
-
},
|
207 |
-
{
|
208 |
-
"epoch": 0.4854368932038835,
|
209 |
-
"grad_norm": 0.15940478444099426,
|
210 |
-
"learning_rate": 4.596864189264591e-05,
|
211 |
-
"loss": 0.0698,
|
212 |
-
"step": 1450
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 0.5021760964178105,
|
216 |
-
"grad_norm": 0.1869521141052246,
|
217 |
-
"learning_rate": 4.5829148532529854e-05,
|
218 |
-
"loss": 0.0721,
|
219 |
-
"step": 1500
|
220 |
-
},
|
221 |
-
{
|
222 |
-
"epoch": 0.5189152996317375,
|
223 |
-
"grad_norm": 0.36063650250434875,
|
224 |
-
"learning_rate": 4.5689655172413794e-05,
|
225 |
-
"loss": 0.0706,
|
226 |
-
"step": 1550
|
227 |
-
},
|
228 |
-
{
|
229 |
-
"epoch": 0.5356545028456645,
|
230 |
-
"grad_norm": 0.16967014968395233,
|
231 |
-
"learning_rate": 4.5550161812297735e-05,
|
232 |
-
"loss": 0.0759,
|
233 |
-
"step": 1600
|
234 |
-
},
|
235 |
-
{
|
236 |
-
"epoch": 0.5523937060595916,
|
237 |
-
"grad_norm": 0.29293423891067505,
|
238 |
-
"learning_rate": 4.5410668452181676e-05,
|
239 |
-
"loss": 0.0711,
|
240 |
-
"step": 1650
|
241 |
-
},
|
242 |
-
{
|
243 |
-
"epoch": 0.5691329092735186,
|
244 |
-
"grad_norm": 0.3034748136997223,
|
245 |
-
"learning_rate": 4.527117509206562e-05,
|
246 |
-
"loss": 0.067,
|
247 |
-
"step": 1700
|
248 |
-
},
|
249 |
-
{
|
250 |
-
"epoch": 0.5858721124874456,
|
251 |
-
"grad_norm": 0.1974593997001648,
|
252 |
-
"learning_rate": 4.513168173194956e-05,
|
253 |
-
"loss": 0.0701,
|
254 |
-
"step": 1750
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 0.6026113157013726,
|
258 |
-
"grad_norm": 0.18101799488067627,
|
259 |
-
"learning_rate": 4.4992188371833505e-05,
|
260 |
-
"loss": 0.0717,
|
261 |
-
"step": 1800
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"epoch": 0.6193505189152997,
|
265 |
-
"grad_norm": 0.14422941207885742,
|
266 |
-
"learning_rate": 4.4852695011717445e-05,
|
267 |
-
"loss": 0.0686,
|
268 |
-
"step": 1850
|
269 |
-
},
|
270 |
-
{
|
271 |
-
"epoch": 0.6360897221292267,
|
272 |
-
"grad_norm": 0.28663551807403564,
|
273 |
-
"learning_rate": 4.4713201651601386e-05,
|
274 |
-
"loss": 0.0646,
|
275 |
-
"step": 1900
|
276 |
-
},
|
277 |
-
{
|
278 |
-
"epoch": 0.6528289253431536,
|
279 |
-
"grad_norm": 0.23879379034042358,
|
280 |
-
"learning_rate": 4.4573708291485327e-05,
|
281 |
-
"loss": 0.0684,
|
282 |
-
"step": 1950
|
283 |
-
},
|
284 |
-
{
|
285 |
-
"epoch": 0.6695681285570807,
|
286 |
-
"grad_norm": 0.21389362215995789,
|
287 |
-
"learning_rate": 4.443421493136927e-05,
|
288 |
-
"loss": 0.066,
|
289 |
-
"step": 2000
|
290 |
-
},
|
291 |
-
{
|
292 |
-
"epoch": 0.6863073317710077,
|
293 |
-
"grad_norm": 0.26841893792152405,
|
294 |
-
"learning_rate": 4.4294721571253215e-05,
|
295 |
-
"loss": 0.0717,
|
296 |
-
"step": 2050
|
297 |
-
},
|
298 |
-
{
|
299 |
-
"epoch": 0.7030465349849347,
|
300 |
-
"grad_norm": 0.240205317735672,
|
301 |
-
"learning_rate": 4.415522821113715e-05,
|
302 |
-
"loss": 0.0697,
|
303 |
-
"step": 2100
|
304 |
-
},
|
305 |
-
{
|
306 |
-
"epoch": 0.7197857381988617,
|
307 |
-
"grad_norm": 0.28098127245903015,
|
308 |
-
"learning_rate": 4.4015734851021096e-05,
|
309 |
-
"loss": 0.0713,
|
310 |
-
"step": 2150
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"epoch": 0.7365249414127888,
|
314 |
-
"grad_norm": 0.23308847844600677,
|
315 |
-
"learning_rate": 4.3876241490905037e-05,
|
316 |
-
"loss": 0.0667,
|
317 |
-
"step": 2200
|
318 |
-
},
|
319 |
-
{
|
320 |
-
"epoch": 0.7532641446267158,
|
321 |
-
"grad_norm": 0.22748568654060364,
|
322 |
-
"learning_rate": 4.373674813078898e-05,
|
323 |
-
"loss": 0.0605,
|
324 |
-
"step": 2250
|
325 |
-
},
|
326 |
-
{
|
327 |
-
"epoch": 0.7700033478406428,
|
328 |
-
"grad_norm": 0.3932187259197235,
|
329 |
-
"learning_rate": 4.359725477067292e-05,
|
330 |
-
"loss": 0.0676,
|
331 |
-
"step": 2300
|
332 |
-
},
|
333 |
-
{
|
334 |
-
"epoch": 0.7867425510545698,
|
335 |
-
"grad_norm": 0.23918767273426056,
|
336 |
-
"learning_rate": 4.345776141055686e-05,
|
337 |
-
"loss": 0.0624,
|
338 |
-
"step": 2350
|
339 |
-
},
|
340 |
-
{
|
341 |
-
"epoch": 0.8034817542684968,
|
342 |
-
"grad_norm": 0.3068426549434662,
|
343 |
-
"learning_rate": 4.33182680504408e-05,
|
344 |
-
"loss": 0.0664,
|
345 |
-
"step": 2400
|
346 |
-
},
|
347 |
-
{
|
348 |
-
"epoch": 0.8202209574824239,
|
349 |
-
"grad_norm": 0.17977873980998993,
|
350 |
-
"learning_rate": 4.317877469032474e-05,
|
351 |
-
"loss": 0.0726,
|
352 |
-
"step": 2450
|
353 |
-
},
|
354 |
-
{
|
355 |
-
"epoch": 0.8369601606963508,
|
356 |
-
"grad_norm": 0.16876642405986786,
|
357 |
-
"learning_rate": 4.303928133020869e-05,
|
358 |
-
"loss": 0.0639,
|
359 |
-
"step": 2500
|
360 |
-
},
|
361 |
-
{
|
362 |
-
"epoch": 0.8536993639102779,
|
363 |
-
"grad_norm": 0.17980250716209412,
|
364 |
-
"learning_rate": 4.289978797009263e-05,
|
365 |
-
"loss": 0.0701,
|
366 |
-
"step": 2550
|
367 |
-
},
|
368 |
-
{
|
369 |
-
"epoch": 0.8704385671242049,
|
370 |
-
"grad_norm": 0.1711459904909134,
|
371 |
-
"learning_rate": 4.276029460997656e-05,
|
372 |
-
"loss": 0.063,
|
373 |
-
"step": 2600
|
374 |
-
},
|
375 |
-
{
|
376 |
-
"epoch": 0.8871777703381319,
|
377 |
-
"grad_norm": 0.443228542804718,
|
378 |
-
"learning_rate": 4.262080124986051e-05,
|
379 |
-
"loss": 0.0675,
|
380 |
-
"step": 2650
|
381 |
-
},
|
382 |
-
{
|
383 |
-
"epoch": 0.9039169735520589,
|
384 |
-
"grad_norm": 0.2098589390516281,
|
385 |
-
"learning_rate": 4.248130788974445e-05,
|
386 |
-
"loss": 0.062,
|
387 |
-
"step": 2700
|
388 |
-
},
|
389 |
-
{
|
390 |
-
"epoch": 0.920656176765986,
|
391 |
-
"grad_norm": 0.3022039234638214,
|
392 |
-
"learning_rate": 4.234181452962839e-05,
|
393 |
-
"loss": 0.07,
|
394 |
-
"step": 2750
|
395 |
-
},
|
396 |
-
{
|
397 |
-
"epoch": 0.937395379979913,
|
398 |
-
"grad_norm": 0.19368910789489746,
|
399 |
-
"learning_rate": 4.220232116951233e-05,
|
400 |
-
"loss": 0.0621,
|
401 |
-
"step": 2800
|
402 |
-
},
|
403 |
-
{
|
404 |
-
"epoch": 0.9541345831938399,
|
405 |
-
"grad_norm": 0.18753108382225037,
|
406 |
-
"learning_rate": 4.206282780939628e-05,
|
407 |
-
"loss": 0.0631,
|
408 |
-
"step": 2850
|
409 |
-
},
|
410 |
-
{
|
411 |
-
"epoch": 0.970873786407767,
|
412 |
-
"grad_norm": 0.15517786145210266,
|
413 |
-
"learning_rate": 4.192333444928022e-05,
|
414 |
-
"loss": 0.0641,
|
415 |
-
"step": 2900
|
416 |
-
},
|
417 |
-
{
|
418 |
-
"epoch": 0.987612989621694,
|
419 |
-
"grad_norm": 0.11765792220830917,
|
420 |
-
"learning_rate": 4.178384108916415e-05,
|
421 |
-
"loss": 0.0612,
|
422 |
-
"step": 2950
|
423 |
-
},
|
424 |
-
{
|
425 |
-
"epoch": 1.0,
|
426 |
-
"eval_loss": 0.05521286651492119,
|
427 |
-
"eval_runtime": 50.415,
|
428 |
-
"eval_samples_per_second": 236.993,
|
429 |
-
"eval_steps_per_second": 14.817,
|
430 |
-
"step": 2987
|
431 |
-
},
|
432 |
-
{
|
433 |
-
"epoch": 1.004352192835621,
|
434 |
-
"grad_norm": 0.2691793739795685,
|
435 |
-
"learning_rate": 4.16443477290481e-05,
|
436 |
-
"loss": 0.059,
|
437 |
-
"step": 3000
|
438 |
-
},
|
439 |
-
{
|
440 |
-
"epoch": 1.021091396049548,
|
441 |
-
"grad_norm": 0.394694060087204,
|
442 |
-
"learning_rate": 4.150485436893204e-05,
|
443 |
-
"loss": 0.0566,
|
444 |
-
"step": 3050
|
445 |
-
},
|
446 |
-
{
|
447 |
-
"epoch": 1.037830599263475,
|
448 |
-
"grad_norm": 0.19438503682613373,
|
449 |
-
"learning_rate": 4.136536100881598e-05,
|
450 |
-
"loss": 0.0591,
|
451 |
-
"step": 3100
|
452 |
-
},
|
453 |
-
{
|
454 |
-
"epoch": 1.0545698024774022,
|
455 |
-
"grad_norm": 0.21350933611392975,
|
456 |
-
"learning_rate": 4.122586764869992e-05,
|
457 |
-
"loss": 0.0509,
|
458 |
-
"step": 3150
|
459 |
-
},
|
460 |
-
{
|
461 |
-
"epoch": 1.071309005691329,
|
462 |
-
"grad_norm": 0.26747575402259827,
|
463 |
-
"learning_rate": 4.108637428858387e-05,
|
464 |
-
"loss": 0.0589,
|
465 |
-
"step": 3200
|
466 |
-
},
|
467 |
-
{
|
468 |
-
"epoch": 1.088048208905256,
|
469 |
-
"grad_norm": 0.31256961822509766,
|
470 |
-
"learning_rate": 4.0946880928467804e-05,
|
471 |
-
"loss": 0.0602,
|
472 |
-
"step": 3250
|
473 |
-
},
|
474 |
-
{
|
475 |
-
"epoch": 1.1047874121191832,
|
476 |
-
"grad_norm": 0.18631280958652496,
|
477 |
-
"learning_rate": 4.0807387568351745e-05,
|
478 |
-
"loss": 0.0547,
|
479 |
-
"step": 3300
|
480 |
-
},
|
481 |
-
{
|
482 |
-
"epoch": 1.12152661533311,
|
483 |
-
"grad_norm": 0.18677473068237305,
|
484 |
-
"learning_rate": 4.066789420823569e-05,
|
485 |
-
"loss": 0.0543,
|
486 |
-
"step": 3350
|
487 |
-
},
|
488 |
-
{
|
489 |
-
"epoch": 1.1382658185470371,
|
490 |
-
"grad_norm": 0.24535444378852844,
|
491 |
-
"learning_rate": 4.052840084811963e-05,
|
492 |
-
"loss": 0.0583,
|
493 |
-
"step": 3400
|
494 |
-
},
|
495 |
-
{
|
496 |
-
"epoch": 1.1550050217609642,
|
497 |
-
"grad_norm": 0.1752105951309204,
|
498 |
-
"learning_rate": 4.038890748800357e-05,
|
499 |
-
"loss": 0.0504,
|
500 |
-
"step": 3450
|
501 |
-
},
|
502 |
-
{
|
503 |
-
"epoch": 1.1717442249748913,
|
504 |
-
"grad_norm": 0.14743360877037048,
|
505 |
-
"learning_rate": 4.0249414127887514e-05,
|
506 |
-
"loss": 0.055,
|
507 |
-
"step": 3500
|
508 |
-
},
|
509 |
-
{
|
510 |
-
"epoch": 1.1884834281888181,
|
511 |
-
"grad_norm": 0.11535945534706116,
|
512 |
-
"learning_rate": 4.010992076777146e-05,
|
513 |
-
"loss": 0.0552,
|
514 |
-
"step": 3550
|
515 |
-
},
|
516 |
-
{
|
517 |
-
"epoch": 1.2052226314027452,
|
518 |
-
"grad_norm": 0.26563358306884766,
|
519 |
-
"learning_rate": 3.9970427407655395e-05,
|
520 |
-
"loss": 0.0552,
|
521 |
-
"step": 3600
|
522 |
-
},
|
523 |
-
{
|
524 |
-
"epoch": 1.2219618346166723,
|
525 |
-
"grad_norm": 0.15104246139526367,
|
526 |
-
"learning_rate": 3.9830934047539336e-05,
|
527 |
-
"loss": 0.0575,
|
528 |
-
"step": 3650
|
529 |
-
},
|
530 |
-
{
|
531 |
-
"epoch": 1.2387010378305994,
|
532 |
-
"grad_norm": 0.2198421210050583,
|
533 |
-
"learning_rate": 3.9691440687423283e-05,
|
534 |
-
"loss": 0.0567,
|
535 |
-
"step": 3700
|
536 |
-
},
|
537 |
-
{
|
538 |
-
"epoch": 1.2554402410445262,
|
539 |
-
"grad_norm": 0.20177733898162842,
|
540 |
-
"learning_rate": 3.955194732730722e-05,
|
541 |
-
"loss": 0.0556,
|
542 |
-
"step": 3750
|
543 |
-
},
|
544 |
-
{
|
545 |
-
"epoch": 1.2721794442584533,
|
546 |
-
"grad_norm": 0.36604830622673035,
|
547 |
-
"learning_rate": 3.9412453967191165e-05,
|
548 |
-
"loss": 0.0569,
|
549 |
-
"step": 3800
|
550 |
-
},
|
551 |
-
{
|
552 |
-
"epoch": 1.2889186474723804,
|
553 |
-
"grad_norm": 0.18883727490901947,
|
554 |
-
"learning_rate": 3.9272960607075105e-05,
|
555 |
-
"loss": 0.0595,
|
556 |
-
"step": 3850
|
557 |
-
},
|
558 |
-
{
|
559 |
-
"epoch": 1.3056578506863072,
|
560 |
-
"grad_norm": 0.14828617870807648,
|
561 |
-
"learning_rate": 3.9133467246959046e-05,
|
562 |
-
"loss": 0.0548,
|
563 |
-
"step": 3900
|
564 |
-
},
|
565 |
-
{
|
566 |
-
"epoch": 1.3223970539002343,
|
567 |
-
"grad_norm": 0.19220437109470367,
|
568 |
-
"learning_rate": 3.899397388684299e-05,
|
569 |
-
"loss": 0.053,
|
570 |
-
"step": 3950
|
571 |
-
},
|
572 |
-
{
|
573 |
-
"epoch": 1.3391362571141614,
|
574 |
-
"grad_norm": 0.16049669682979584,
|
575 |
-
"learning_rate": 3.885448052672693e-05,
|
576 |
-
"loss": 0.0581,
|
577 |
-
"step": 4000
|
578 |
-
},
|
579 |
-
{
|
580 |
-
"epoch": 1.3558754603280883,
|
581 |
-
"grad_norm": 0.22821515798568726,
|
582 |
-
"learning_rate": 3.8714987166610875e-05,
|
583 |
-
"loss": 0.0518,
|
584 |
-
"step": 4050
|
585 |
-
},
|
586 |
-
{
|
587 |
-
"epoch": 1.3726146635420153,
|
588 |
-
"grad_norm": 0.1879580318927765,
|
589 |
-
"learning_rate": 3.857549380649481e-05,
|
590 |
-
"loss": 0.0574,
|
591 |
-
"step": 4100
|
592 |
-
},
|
593 |
-
{
|
594 |
-
"epoch": 1.3893538667559424,
|
595 |
-
"grad_norm": 0.16026251018047333,
|
596 |
-
"learning_rate": 3.8436000446378756e-05,
|
597 |
-
"loss": 0.063,
|
598 |
-
"step": 4150
|
599 |
-
},
|
600 |
-
{
|
601 |
-
"epoch": 1.4060930699698695,
|
602 |
-
"grad_norm": 0.26868143677711487,
|
603 |
-
"learning_rate": 3.82965070862627e-05,
|
604 |
-
"loss": 0.0571,
|
605 |
-
"step": 4200
|
606 |
-
},
|
607 |
-
{
|
608 |
-
"epoch": 1.4228322731837966,
|
609 |
-
"grad_norm": 0.2529687285423279,
|
610 |
-
"learning_rate": 3.815701372614664e-05,
|
611 |
-
"loss": 0.0528,
|
612 |
-
"step": 4250
|
613 |
-
},
|
614 |
-
{
|
615 |
-
"epoch": 1.4395714763977234,
|
616 |
-
"grad_norm": 0.19138221442699432,
|
617 |
-
"learning_rate": 3.801752036603058e-05,
|
618 |
-
"loss": 0.0584,
|
619 |
-
"step": 4300
|
620 |
-
},
|
621 |
-
{
|
622 |
-
"epoch": 1.4563106796116505,
|
623 |
-
"grad_norm": 0.16359661519527435,
|
624 |
-
"learning_rate": 3.787802700591452e-05,
|
625 |
-
"loss": 0.0539,
|
626 |
-
"step": 4350
|
627 |
-
},
|
628 |
-
{
|
629 |
-
"epoch": 1.4730498828255776,
|
630 |
-
"grad_norm": 0.1373494267463684,
|
631 |
-
"learning_rate": 3.7738533645798466e-05,
|
632 |
-
"loss": 0.0557,
|
633 |
-
"step": 4400
|
634 |
-
},
|
635 |
-
{
|
636 |
-
"epoch": 1.4897890860395044,
|
637 |
-
"grad_norm": 0.15695162117481232,
|
638 |
-
"learning_rate": 3.75990402856824e-05,
|
639 |
-
"loss": 0.0491,
|
640 |
-
"step": 4450
|
641 |
-
},
|
642 |
-
{
|
643 |
-
"epoch": 1.5065282892534315,
|
644 |
-
"grad_norm": 0.18462614715099335,
|
645 |
-
"learning_rate": 3.745954692556635e-05,
|
646 |
-
"loss": 0.0495,
|
647 |
-
"step": 4500
|
648 |
-
},
|
649 |
-
{
|
650 |
-
"epoch": 1.5232674924673586,
|
651 |
-
"grad_norm": 0.27876704931259155,
|
652 |
-
"learning_rate": 3.732005356545029e-05,
|
653 |
-
"loss": 0.0523,
|
654 |
-
"step": 4550
|
655 |
-
},
|
656 |
-
{
|
657 |
-
"epoch": 1.5400066956812855,
|
658 |
-
"grad_norm": 0.30491840839385986,
|
659 |
-
"learning_rate": 3.718056020533423e-05,
|
660 |
-
"loss": 0.0564,
|
661 |
-
"step": 4600
|
662 |
-
},
|
663 |
-
{
|
664 |
-
"epoch": 1.5567458988952128,
|
665 |
-
"grad_norm": 0.18721336126327515,
|
666 |
-
"learning_rate": 3.704106684521817e-05,
|
667 |
-
"loss": 0.0524,
|
668 |
-
"step": 4650
|
669 |
-
},
|
670 |
-
{
|
671 |
-
"epoch": 1.5734851021091396,
|
672 |
-
"grad_norm": 0.21216215193271637,
|
673 |
-
"learning_rate": 3.690157348510211e-05,
|
674 |
-
"loss": 0.0521,
|
675 |
-
"step": 4700
|
676 |
-
},
|
677 |
-
{
|
678 |
-
"epoch": 1.5902243053230665,
|
679 |
-
"grad_norm": 0.1368396282196045,
|
680 |
-
"learning_rate": 3.676208012498605e-05,
|
681 |
-
"loss": 0.056,
|
682 |
-
"step": 4750
|
683 |
-
},
|
684 |
-
{
|
685 |
-
"epoch": 1.6069635085369938,
|
686 |
-
"grad_norm": 0.13692086935043335,
|
687 |
-
"learning_rate": 3.662258676486999e-05,
|
688 |
-
"loss": 0.0443,
|
689 |
-
"step": 4800
|
690 |
-
},
|
691 |
-
{
|
692 |
-
"epoch": 1.6237027117509206,
|
693 |
-
"grad_norm": 0.11640128493309021,
|
694 |
-
"learning_rate": 3.648309340475394e-05,
|
695 |
-
"loss": 0.0488,
|
696 |
-
"step": 4850
|
697 |
-
},
|
698 |
-
{
|
699 |
-
"epoch": 1.6404419149648477,
|
700 |
-
"grad_norm": 0.19953882694244385,
|
701 |
-
"learning_rate": 3.634360004463788e-05,
|
702 |
-
"loss": 0.0553,
|
703 |
-
"step": 4900
|
704 |
-
},
|
705 |
-
{
|
706 |
-
"epoch": 1.6571811181787748,
|
707 |
-
"grad_norm": 0.1966984122991562,
|
708 |
-
"learning_rate": 3.6204106684521813e-05,
|
709 |
-
"loss": 0.0536,
|
710 |
-
"step": 4950
|
711 |
-
},
|
712 |
-
{
|
713 |
-
"epoch": 1.6739203213927016,
|
714 |
-
"grad_norm": 0.2324533313512802,
|
715 |
-
"learning_rate": 3.606461332440576e-05,
|
716 |
-
"loss": 0.0493,
|
717 |
-
"step": 5000
|
718 |
-
},
|
719 |
-
{
|
720 |
-
"epoch": 1.6906595246066287,
|
721 |
-
"grad_norm": 0.16217607259750366,
|
722 |
-
"learning_rate": 3.59251199642897e-05,
|
723 |
-
"loss": 0.0503,
|
724 |
-
"step": 5050
|
725 |
-
},
|
726 |
-
{
|
727 |
-
"epoch": 1.7073987278205558,
|
728 |
-
"grad_norm": 0.23949602246284485,
|
729 |
-
"learning_rate": 3.578562660417364e-05,
|
730 |
-
"loss": 0.0556,
|
731 |
-
"step": 5100
|
732 |
-
},
|
733 |
-
{
|
734 |
-
"epoch": 1.7241379310344827,
|
735 |
-
"grad_norm": 0.21387897431850433,
|
736 |
-
"learning_rate": 3.564613324405758e-05,
|
737 |
-
"loss": 0.0548,
|
738 |
-
"step": 5150
|
739 |
-
},
|
740 |
-
{
|
741 |
-
"epoch": 1.7408771342484097,
|
742 |
-
"grad_norm": 0.2055111676454544,
|
743 |
-
"learning_rate": 3.550663988394153e-05,
|
744 |
-
"loss": 0.06,
|
745 |
-
"step": 5200
|
746 |
-
},
|
747 |
-
{
|
748 |
-
"epoch": 1.7576163374623368,
|
749 |
-
"grad_norm": 0.20280921459197998,
|
750 |
-
"learning_rate": 3.5367146523825464e-05,
|
751 |
-
"loss": 0.0508,
|
752 |
-
"step": 5250
|
753 |
-
},
|
754 |
-
{
|
755 |
-
"epoch": 1.7743555406762637,
|
756 |
-
"grad_norm": 0.14165103435516357,
|
757 |
-
"learning_rate": 3.5227653163709405e-05,
|
758 |
-
"loss": 0.0581,
|
759 |
-
"step": 5300
|
760 |
-
},
|
761 |
-
{
|
762 |
-
"epoch": 1.791094743890191,
|
763 |
-
"grad_norm": 0.18099863827228546,
|
764 |
-
"learning_rate": 3.508815980359335e-05,
|
765 |
-
"loss": 0.0562,
|
766 |
-
"step": 5350
|
767 |
-
},
|
768 |
-
{
|
769 |
-
"epoch": 1.8078339471041178,
|
770 |
-
"grad_norm": 0.21743184328079224,
|
771 |
-
"learning_rate": 3.494866644347729e-05,
|
772 |
-
"loss": 0.0498,
|
773 |
-
"step": 5400
|
774 |
-
},
|
775 |
-
{
|
776 |
-
"epoch": 1.824573150318045,
|
777 |
-
"grad_norm": 0.20934534072875977,
|
778 |
-
"learning_rate": 3.4809173083361234e-05,
|
779 |
-
"loss": 0.0549,
|
780 |
-
"step": 5450
|
781 |
-
},
|
782 |
-
{
|
783 |
-
"epoch": 1.841312353531972,
|
784 |
-
"grad_norm": 0.1582174152135849,
|
785 |
-
"learning_rate": 3.4669679723245174e-05,
|
786 |
-
"loss": 0.0556,
|
787 |
-
"step": 5500
|
788 |
-
},
|
789 |
-
{
|
790 |
-
"epoch": 1.8580515567458988,
|
791 |
-
"grad_norm": 0.1624903827905655,
|
792 |
-
"learning_rate": 3.453018636312912e-05,
|
793 |
-
"loss": 0.0516,
|
794 |
-
"step": 5550
|
795 |
-
},
|
796 |
-
{
|
797 |
-
"epoch": 1.874790759959826,
|
798 |
-
"grad_norm": 0.16255798935890198,
|
799 |
-
"learning_rate": 3.4390693003013056e-05,
|
800 |
-
"loss": 0.0542,
|
801 |
-
"step": 5600
|
802 |
-
},
|
803 |
-
{
|
804 |
-
"epoch": 1.891529963173753,
|
805 |
-
"grad_norm": 0.1269742250442505,
|
806 |
-
"learning_rate": 3.4251199642896996e-05,
|
807 |
-
"loss": 0.0565,
|
808 |
-
"step": 5650
|
809 |
-
},
|
810 |
-
{
|
811 |
-
"epoch": 1.9082691663876798,
|
812 |
-
"grad_norm": 0.15966229140758514,
|
813 |
-
"learning_rate": 3.4111706282780944e-05,
|
814 |
-
"loss": 0.0538,
|
815 |
-
"step": 5700
|
816 |
-
},
|
817 |
-
{
|
818 |
-
"epoch": 1.925008369601607,
|
819 |
-
"grad_norm": 0.21506330370903015,
|
820 |
-
"learning_rate": 3.3972212922664884e-05,
|
821 |
-
"loss": 0.0505,
|
822 |
-
"step": 5750
|
823 |
-
},
|
824 |
-
{
|
825 |
-
"epoch": 1.941747572815534,
|
826 |
-
"grad_norm": 0.2145415097475052,
|
827 |
-
"learning_rate": 3.3832719562548825e-05,
|
828 |
-
"loss": 0.0521,
|
829 |
-
"step": 5800
|
830 |
-
},
|
831 |
-
{
|
832 |
-
"epoch": 1.9584867760294609,
|
833 |
-
"grad_norm": 0.10960496962070465,
|
834 |
-
"learning_rate": 3.3693226202432766e-05,
|
835 |
-
"loss": 0.0513,
|
836 |
-
"step": 5850
|
837 |
-
},
|
838 |
-
{
|
839 |
-
"epoch": 1.9752259792433882,
|
840 |
-
"grad_norm": 0.13635843992233276,
|
841 |
-
"learning_rate": 3.355373284231671e-05,
|
842 |
-
"loss": 0.0499,
|
843 |
-
"step": 5900
|
844 |
-
},
|
845 |
-
{
|
846 |
-
"epoch": 1.991965182457315,
|
847 |
-
"grad_norm": 0.1542210429906845,
|
848 |
-
"learning_rate": 3.341423948220065e-05,
|
849 |
-
"loss": 0.0556,
|
850 |
-
"step": 5950
|
851 |
-
},
|
852 |
-
{
|
853 |
-
"epoch": 2.0,
|
854 |
-
"eval_loss": 0.04946442320942879,
|
855 |
-
"eval_runtime": 55.6114,
|
856 |
-
"eval_samples_per_second": 214.848,
|
857 |
-
"eval_steps_per_second": 13.432,
|
858 |
-
"step": 5974
|
859 |
-
},
|
860 |
-
{
|
861 |
-
"epoch": 2.008704385671242,
|
862 |
-
"grad_norm": 0.1718842089176178,
|
863 |
-
"learning_rate": 3.327474612208459e-05,
|
864 |
-
"loss": 0.0503,
|
865 |
-
"step": 6000
|
866 |
-
},
|
867 |
-
{
|
868 |
-
"epoch": 2.025443588885169,
|
869 |
-
"grad_norm": 0.1528020203113556,
|
870 |
-
"learning_rate": 3.3135252761968535e-05,
|
871 |
-
"loss": 0.0479,
|
872 |
-
"step": 6050
|
873 |
-
},
|
874 |
-
{
|
875 |
-
"epoch": 2.042182792099096,
|
876 |
-
"grad_norm": 0.19148772954940796,
|
877 |
-
"learning_rate": 3.299575940185247e-05,
|
878 |
-
"loss": 0.0443,
|
879 |
-
"step": 6100
|
880 |
-
},
|
881 |
-
{
|
882 |
-
"epoch": 2.058921995313023,
|
883 |
-
"grad_norm": 0.18125496804714203,
|
884 |
-
"learning_rate": 3.2856266041736416e-05,
|
885 |
-
"loss": 0.0473,
|
886 |
-
"step": 6150
|
887 |
-
},
|
888 |
-
{
|
889 |
-
"epoch": 2.07566119852695,
|
890 |
-
"grad_norm": 0.20772996544837952,
|
891 |
-
"learning_rate": 3.271677268162036e-05,
|
892 |
-
"loss": 0.0539,
|
893 |
-
"step": 6200
|
894 |
-
},
|
895 |
-
{
|
896 |
-
"epoch": 2.092400401740877,
|
897 |
-
"grad_norm": 0.2518468201160431,
|
898 |
-
"learning_rate": 3.25772793215043e-05,
|
899 |
-
"loss": 0.0468,
|
900 |
-
"step": 6250
|
901 |
-
},
|
902 |
-
{
|
903 |
-
"epoch": 2.1091396049548043,
|
904 |
-
"grad_norm": 0.1350301206111908,
|
905 |
-
"learning_rate": 3.243778596138824e-05,
|
906 |
-
"loss": 0.0431,
|
907 |
-
"step": 6300
|
908 |
-
},
|
909 |
-
{
|
910 |
-
"epoch": 2.125878808168731,
|
911 |
-
"grad_norm": 0.19141735136508942,
|
912 |
-
"learning_rate": 3.229829260127218e-05,
|
913 |
-
"loss": 0.048,
|
914 |
-
"step": 6350
|
915 |
-
},
|
916 |
-
{
|
917 |
-
"epoch": 2.142618011382658,
|
918 |
-
"grad_norm": 0.2404586374759674,
|
919 |
-
"learning_rate": 3.2158799241156126e-05,
|
920 |
-
"loss": 0.0516,
|
921 |
-
"step": 6400
|
922 |
-
},
|
923 |
-
{
|
924 |
-
"epoch": 2.1593572145965854,
|
925 |
-
"grad_norm": 0.21710112690925598,
|
926 |
-
"learning_rate": 3.201930588104006e-05,
|
927 |
-
"loss": 0.0472,
|
928 |
-
"step": 6450
|
929 |
-
},
|
930 |
-
{
|
931 |
-
"epoch": 2.176096417810512,
|
932 |
-
"grad_norm": 0.14395031332969666,
|
933 |
-
"learning_rate": 3.187981252092401e-05,
|
934 |
-
"loss": 0.0438,
|
935 |
-
"step": 6500
|
936 |
-
},
|
937 |
-
{
|
938 |
-
"epoch": 2.192835621024439,
|
939 |
-
"grad_norm": 0.20882932841777802,
|
940 |
-
"learning_rate": 3.174031916080795e-05,
|
941 |
-
"loss": 0.0488,
|
942 |
-
"step": 6550
|
943 |
-
},
|
944 |
-
{
|
945 |
-
"epoch": 2.2095748242383664,
|
946 |
-
"grad_norm": 0.13824905455112457,
|
947 |
-
"learning_rate": 3.160082580069189e-05,
|
948 |
-
"loss": 0.0464,
|
949 |
-
"step": 6600
|
950 |
-
},
|
951 |
-
{
|
952 |
-
"epoch": 2.2263140274522932,
|
953 |
-
"grad_norm": 0.1783577799797058,
|
954 |
-
"learning_rate": 3.146133244057583e-05,
|
955 |
-
"loss": 0.0459,
|
956 |
-
"step": 6650
|
957 |
-
},
|
958 |
-
{
|
959 |
-
"epoch": 2.24305323066622,
|
960 |
-
"grad_norm": 0.22147531807422638,
|
961 |
-
"learning_rate": 3.132183908045977e-05,
|
962 |
-
"loss": 0.0476,
|
963 |
-
"step": 6700
|
964 |
-
},
|
965 |
-
{
|
966 |
-
"epoch": 2.2597924338801474,
|
967 |
-
"grad_norm": 0.17393821477890015,
|
968 |
-
"learning_rate": 3.118234572034371e-05,
|
969 |
-
"loss": 0.0436,
|
970 |
-
"step": 6750
|
971 |
-
},
|
972 |
-
{
|
973 |
-
"epoch": 2.2765316370940742,
|
974 |
-
"grad_norm": 0.15850785374641418,
|
975 |
-
"learning_rate": 3.104285236022765e-05,
|
976 |
-
"loss": 0.0476,
|
977 |
-
"step": 6800
|
978 |
-
},
|
979 |
-
{
|
980 |
-
"epoch": 2.2932708403080015,
|
981 |
-
"grad_norm": 0.16232182085514069,
|
982 |
-
"learning_rate": 3.09033590001116e-05,
|
983 |
-
"loss": 0.0473,
|
984 |
-
"step": 6850
|
985 |
-
},
|
986 |
-
{
|
987 |
-
"epoch": 2.3100100435219284,
|
988 |
-
"grad_norm": 0.1816001981496811,
|
989 |
-
"learning_rate": 3.076386563999554e-05,
|
990 |
-
"loss": 0.0427,
|
991 |
-
"step": 6900
|
992 |
-
},
|
993 |
-
{
|
994 |
-
"epoch": 2.3267492467358553,
|
995 |
-
"grad_norm": 0.13417834043502808,
|
996 |
-
"learning_rate": 3.062437227987948e-05,
|
997 |
-
"loss": 0.0448,
|
998 |
-
"step": 6950
|
999 |
-
},
|
1000 |
-
{
|
1001 |
-
"epoch": 2.3434884499497826,
|
1002 |
-
"grad_norm": 0.12576530873775482,
|
1003 |
-
"learning_rate": 3.048487891976342e-05,
|
1004 |
-
"loss": 0.0453,
|
1005 |
-
"step": 7000
|
1006 |
-
},
|
1007 |
-
{
|
1008 |
-
"epoch": 2.3602276531637094,
|
1009 |
-
"grad_norm": 0.33120718598365784,
|
1010 |
-
"learning_rate": 3.0345385559647362e-05,
|
1011 |
-
"loss": 0.0462,
|
1012 |
-
"step": 7050
|
1013 |
-
},
|
1014 |
-
{
|
1015 |
-
"epoch": 2.3769668563776363,
|
1016 |
-
"grad_norm": 0.22310969233512878,
|
1017 |
-
"learning_rate": 3.0205892199531306e-05,
|
1018 |
-
"loss": 0.0475,
|
1019 |
-
"step": 7100
|
1020 |
-
},
|
1021 |
-
{
|
1022 |
-
"epoch": 2.3937060595915636,
|
1023 |
-
"grad_norm": 0.18150626122951508,
|
1024 |
-
"learning_rate": 3.0066398839415243e-05,
|
1025 |
-
"loss": 0.0489,
|
1026 |
-
"step": 7150
|
1027 |
-
},
|
1028 |
-
{
|
1029 |
-
"epoch": 2.4104452628054904,
|
1030 |
-
"grad_norm": 0.28730452060699463,
|
1031 |
-
"learning_rate": 2.9926905479299187e-05,
|
1032 |
-
"loss": 0.0536,
|
1033 |
-
"step": 7200
|
1034 |
-
},
|
1035 |
-
{
|
1036 |
-
"epoch": 2.4271844660194173,
|
1037 |
-
"grad_norm": 0.1918480098247528,
|
1038 |
-
"learning_rate": 2.9787412119183128e-05,
|
1039 |
-
"loss": 0.0426,
|
1040 |
-
"step": 7250
|
1041 |
-
},
|
1042 |
-
{
|
1043 |
-
"epoch": 2.4439236692333446,
|
1044 |
-
"grad_norm": 0.16158398985862732,
|
1045 |
-
"learning_rate": 2.964791875906707e-05,
|
1046 |
-
"loss": 0.0458,
|
1047 |
-
"step": 7300
|
1048 |
-
},
|
1049 |
-
{
|
1050 |
-
"epoch": 2.4606628724472714,
|
1051 |
-
"grad_norm": 0.27141231298446655,
|
1052 |
-
"learning_rate": 2.9508425398951012e-05,
|
1053 |
-
"loss": 0.0454,
|
1054 |
-
"step": 7350
|
1055 |
-
},
|
1056 |
-
{
|
1057 |
-
"epoch": 2.4774020756611987,
|
1058 |
-
"grad_norm": 0.1777345836162567,
|
1059 |
-
"learning_rate": 2.936893203883495e-05,
|
1060 |
-
"loss": 0.0435,
|
1061 |
-
"step": 7400
|
1062 |
-
},
|
1063 |
-
{
|
1064 |
-
"epoch": 2.4941412788751256,
|
1065 |
-
"grad_norm": 0.14735421538352966,
|
1066 |
-
"learning_rate": 2.9229438678718897e-05,
|
1067 |
-
"loss": 0.0489,
|
1068 |
-
"step": 7450
|
1069 |
-
},
|
1070 |
-
{
|
1071 |
-
"epoch": 2.5108804820890525,
|
1072 |
-
"grad_norm": 0.1486055999994278,
|
1073 |
-
"learning_rate": 2.9089945318602834e-05,
|
1074 |
-
"loss": 0.0477,
|
1075 |
-
"step": 7500
|
1076 |
-
},
|
1077 |
-
{
|
1078 |
-
"epoch": 2.5276196853029793,
|
1079 |
-
"grad_norm": 0.17078754305839539,
|
1080 |
-
"learning_rate": 2.895045195848678e-05,
|
1081 |
-
"loss": 0.0444,
|
1082 |
-
"step": 7550
|
1083 |
-
},
|
1084 |
-
{
|
1085 |
-
"epoch": 2.5443588885169066,
|
1086 |
-
"grad_norm": 0.19276435673236847,
|
1087 |
-
"learning_rate": 2.881095859837072e-05,
|
1088 |
-
"loss": 0.0486,
|
1089 |
-
"step": 7600
|
1090 |
-
},
|
1091 |
-
{
|
1092 |
-
"epoch": 2.5610980917308335,
|
1093 |
-
"grad_norm": 0.21209606528282166,
|
1094 |
-
"learning_rate": 2.8671465238254656e-05,
|
1095 |
-
"loss": 0.0497,
|
1096 |
-
"step": 7650
|
1097 |
-
},
|
1098 |
-
{
|
1099 |
-
"epoch": 2.5778372949447608,
|
1100 |
-
"grad_norm": 0.21018877625465393,
|
1101 |
-
"learning_rate": 2.8531971878138604e-05,
|
1102 |
-
"loss": 0.0441,
|
1103 |
-
"step": 7700
|
1104 |
-
},
|
1105 |
-
{
|
1106 |
-
"epoch": 2.5945764981586876,
|
1107 |
-
"grad_norm": 0.15666617453098297,
|
1108 |
-
"learning_rate": 2.839247851802254e-05,
|
1109 |
-
"loss": 0.0467,
|
1110 |
-
"step": 7750
|
1111 |
-
},
|
1112 |
-
{
|
1113 |
-
"epoch": 2.6113157013726145,
|
1114 |
-
"grad_norm": 0.1940685212612152,
|
1115 |
-
"learning_rate": 2.8252985157906485e-05,
|
1116 |
-
"loss": 0.0523,
|
1117 |
-
"step": 7800
|
1118 |
-
},
|
1119 |
-
{
|
1120 |
-
"epoch": 2.628054904586542,
|
1121 |
-
"grad_norm": 0.28480586409568787,
|
1122 |
-
"learning_rate": 2.8113491797790426e-05,
|
1123 |
-
"loss": 0.0481,
|
1124 |
-
"step": 7850
|
1125 |
-
},
|
1126 |
-
{
|
1127 |
-
"epoch": 2.6447941078004686,
|
1128 |
-
"grad_norm": 0.2223973125219345,
|
1129 |
-
"learning_rate": 2.797399843767437e-05,
|
1130 |
-
"loss": 0.0432,
|
1131 |
-
"step": 7900
|
1132 |
-
},
|
1133 |
-
{
|
1134 |
-
"epoch": 2.661533311014396,
|
1135 |
-
"grad_norm": 0.15986157953739166,
|
1136 |
-
"learning_rate": 2.783450507755831e-05,
|
1137 |
-
"loss": 0.0454,
|
1138 |
-
"step": 7950
|
1139 |
-
},
|
1140 |
-
{
|
1141 |
-
"epoch": 2.678272514228323,
|
1142 |
-
"grad_norm": 0.1384258270263672,
|
1143 |
-
"learning_rate": 2.7695011717442248e-05,
|
1144 |
-
"loss": 0.0477,
|
1145 |
-
"step": 8000
|
1146 |
-
},
|
1147 |
-
{
|
1148 |
-
"epoch": 2.6950117174422497,
|
1149 |
-
"grad_norm": 0.1721869707107544,
|
1150 |
-
"learning_rate": 2.7555518357326192e-05,
|
1151 |
-
"loss": 0.0453,
|
1152 |
-
"step": 8050
|
1153 |
-
},
|
1154 |
-
{
|
1155 |
-
"epoch": 2.7117509206561765,
|
1156 |
-
"grad_norm": 0.20737840235233307,
|
1157 |
-
"learning_rate": 2.7416024997210132e-05,
|
1158 |
-
"loss": 0.0504,
|
1159 |
-
"step": 8100
|
1160 |
-
},
|
1161 |
-
{
|
1162 |
-
"epoch": 2.728490123870104,
|
1163 |
-
"grad_norm": 0.18823584914207458,
|
1164 |
-
"learning_rate": 2.7276531637094077e-05,
|
1165 |
-
"loss": 0.0453,
|
1166 |
-
"step": 8150
|
1167 |
-
},
|
1168 |
-
{
|
1169 |
-
"epoch": 2.7452293270840307,
|
1170 |
-
"grad_norm": 0.13201962411403656,
|
1171 |
-
"learning_rate": 2.7137038276978017e-05,
|
1172 |
-
"loss": 0.0433,
|
1173 |
-
"step": 8200
|
1174 |
-
},
|
1175 |
-
{
|
1176 |
-
"epoch": 2.761968530297958,
|
1177 |
-
"grad_norm": 0.1443973183631897,
|
1178 |
-
"learning_rate": 2.699754491686196e-05,
|
1179 |
-
"loss": 0.0486,
|
1180 |
-
"step": 8250
|
1181 |
-
},
|
1182 |
-
{
|
1183 |
-
"epoch": 2.778707733511885,
|
1184 |
-
"grad_norm": 0.29314514994621277,
|
1185 |
-
"learning_rate": 2.68580515567459e-05,
|
1186 |
-
"loss": 0.05,
|
1187 |
-
"step": 8300
|
1188 |
-
},
|
1189 |
-
{
|
1190 |
-
"epoch": 2.7954469367258117,
|
1191 |
-
"grad_norm": 0.14852124452590942,
|
1192 |
-
"learning_rate": 2.671855819662984e-05,
|
1193 |
-
"loss": 0.0495,
|
1194 |
-
"step": 8350
|
1195 |
-
},
|
1196 |
-
{
|
1197 |
-
"epoch": 2.812186139939739,
|
1198 |
-
"grad_norm": 0.19024662673473358,
|
1199 |
-
"learning_rate": 2.6579064836513783e-05,
|
1200 |
-
"loss": 0.0508,
|
1201 |
-
"step": 8400
|
1202 |
-
},
|
1203 |
-
{
|
1204 |
-
"epoch": 2.828925343153666,
|
1205 |
-
"grad_norm": 0.1745578795671463,
|
1206 |
-
"learning_rate": 2.6439571476397724e-05,
|
1207 |
-
"loss": 0.0443,
|
1208 |
-
"step": 8450
|
1209 |
-
},
|
1210 |
-
{
|
1211 |
-
"epoch": 2.845664546367593,
|
1212 |
-
"grad_norm": 0.18390017747879028,
|
1213 |
-
"learning_rate": 2.6300078116281668e-05,
|
1214 |
-
"loss": 0.0468,
|
1215 |
-
"step": 8500
|
1216 |
-
},
|
1217 |
-
{
|
1218 |
-
"epoch": 2.86240374958152,
|
1219 |
-
"grad_norm": 0.22483347356319427,
|
1220 |
-
"learning_rate": 2.616058475616561e-05,
|
1221 |
-
"loss": 0.0467,
|
1222 |
-
"step": 8550
|
1223 |
-
},
|
1224 |
-
{
|
1225 |
-
"epoch": 2.879142952795447,
|
1226 |
-
"grad_norm": 0.18160563707351685,
|
1227 |
-
"learning_rate": 2.6021091396049553e-05,
|
1228 |
-
"loss": 0.0441,
|
1229 |
-
"step": 8600
|
1230 |
-
},
|
1231 |
-
{
|
1232 |
-
"epoch": 2.8958821560093737,
|
1233 |
-
"grad_norm": 0.13408955931663513,
|
1234 |
-
"learning_rate": 2.588159803593349e-05,
|
1235 |
-
"loss": 0.0446,
|
1236 |
-
"step": 8650
|
1237 |
-
},
|
1238 |
-
{
|
1239 |
-
"epoch": 2.912621359223301,
|
1240 |
-
"grad_norm": 0.16038326919078827,
|
1241 |
-
"learning_rate": 2.574210467581743e-05,
|
1242 |
-
"loss": 0.0456,
|
1243 |
-
"step": 8700
|
1244 |
-
},
|
1245 |
-
{
|
1246 |
-
"epoch": 2.929360562437228,
|
1247 |
-
"grad_norm": 0.22738413512706757,
|
1248 |
-
"learning_rate": 2.5602611315701375e-05,
|
1249 |
-
"loss": 0.0479,
|
1250 |
-
"step": 8750
|
1251 |
-
},
|
1252 |
-
{
|
1253 |
-
"epoch": 2.946099765651155,
|
1254 |
-
"grad_norm": 0.20327210426330566,
|
1255 |
-
"learning_rate": 2.5463117955585315e-05,
|
1256 |
-
"loss": 0.0511,
|
1257 |
-
"step": 8800
|
1258 |
-
},
|
1259 |
-
{
|
1260 |
-
"epoch": 2.962838968865082,
|
1261 |
-
"grad_norm": 0.15756353735923767,
|
1262 |
-
"learning_rate": 2.532362459546926e-05,
|
1263 |
-
"loss": 0.0426,
|
1264 |
-
"step": 8850
|
1265 |
-
},
|
1266 |
-
{
|
1267 |
-
"epoch": 2.979578172079009,
|
1268 |
-
"grad_norm": 0.1305045783519745,
|
1269 |
-
"learning_rate": 2.5184131235353197e-05,
|
1270 |
-
"loss": 0.0442,
|
1271 |
-
"step": 8900
|
1272 |
-
},
|
1273 |
-
{
|
1274 |
-
"epoch": 2.996317375292936,
|
1275 |
-
"grad_norm": 0.1610562801361084,
|
1276 |
-
"learning_rate": 2.5044637875237144e-05,
|
1277 |
-
"loss": 0.0467,
|
1278 |
-
"step": 8950
|
1279 |
-
},
|
1280 |
-
{
|
1281 |
-
"epoch": 3.0,
|
1282 |
-
"eval_loss": 0.04702676460146904,
|
1283 |
-
"eval_runtime": 52.8989,
|
1284 |
-
"eval_samples_per_second": 225.865,
|
1285 |
-
"eval_steps_per_second": 14.121,
|
1286 |
-
"step": 8961
|
1287 |
-
}
|
1288 |
-
],
|
1289 |
-
"logging_steps": 50,
|
1290 |
-
"max_steps": 17922,
|
1291 |
-
"num_input_tokens_seen": 0,
|
1292 |
-
"num_train_epochs": 6,
|
1293 |
-
"save_steps": 500,
|
1294 |
-
"stateful_callbacks": {
|
1295 |
-
"TrainerControl": {
|
1296 |
-
"args": {
|
1297 |
-
"should_epoch_stop": false,
|
1298 |
-
"should_evaluate": false,
|
1299 |
-
"should_log": false,
|
1300 |
-
"should_save": true,
|
1301 |
-
"should_training_stop": false
|
1302 |
-
},
|
1303 |
-
"attributes": {}
|
1304 |
-
}
|
1305 |
-
},
|
1306 |
-
"total_flos": 1.944084787966771e+16,
|
1307 |
-
"train_batch_size": 16,
|
1308 |
-
"trial_name": null,
|
1309 |
-
"trial_params": null
|
1310 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoint-8961/training_args.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:37dd546b69fb60d8deb15a8b88e40b23e367c0e9f5a053ea3ae7c730b3874f2e
|
3 |
-
size 5304
|
|
|
|
|
|
|
|
checkpoint-8961/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|