Training in progress, epoch 6, checkpoint
Browse files- checkpoint-2049/adapter_config.json +1 -1
- checkpoint-2049/adapter_model.bin +3 -0
- checkpoint-2049/added_tokens.json +3 -3
- checkpoint-2049/optimizer.pt +2 -2
- checkpoint-2049/rng_state_0.pth +1 -1
- checkpoint-2049/rng_state_1.pth +1 -1
- checkpoint-2049/rng_state_2.pth +1 -1
- checkpoint-2049/rng_state_3.pth +1 -1
- checkpoint-2049/special_tokens_map.json +4 -12
- checkpoint-2049/tokenizer.json +0 -0
- checkpoint-2049/tokenizer.model +3 -0
- checkpoint-2049/tokenizer_config.json +17 -20
- checkpoint-2049/trainer_state.json +95 -129
- checkpoint-2049/training_args.bin +2 -2
checkpoint-2049/adapter_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
-
"base_model_name_or_path": "
|
4 |
"bias": "none",
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
4 |
"bias": "none",
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
checkpoint-2049/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cba262d9ac7ed8cce020be0dd4f65becfb668e0b0f412efed06fc74202d09815
|
3 |
+
size 143269386
|
checkpoint-2049/added_tokens.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
}
|
checkpoint-2049/optimizer.pt
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 sha256:58073175243c35e731f69c55fa2ed99bcebdcc1604d2747955e5c29403d121d9
|
3 |
+
size 286585234
|
checkpoint-2049/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d18d9a25c4730bc9d3f04c0d9003513d84e4b6f1243f12bf97f04570aec2e2a
|
3 |
size 15024
|
checkpoint-2049/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67d1286470d900669b6a628c6f3697476227ab6b5fb2146f4fc19ef4066daf3b
|
3 |
size 15024
|
checkpoint-2049/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:481168f77ef387bdedefb53497a818d46c7abd5c90d876747c068aa5a5e44fa2
|
3 |
size 15024
|
checkpoint-2049/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8db6609bd9f27b23164e34d3394fccd90937d2d778bccd4154fbf07b9d04a0dc
|
3 |
size 15024
|
checkpoint-2049/special_tokens_map.json
CHANGED
@@ -1,14 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
"eos_token": {
|
7 |
-
"content": "<|endoftext|>",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false
|
12 |
-
},
|
13 |
-
"pad_token": "<|endoftext|>"
|
14 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "</s>",
|
5 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
checkpoint-2049/tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-2049/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-2049/tokenizer_config.json
CHANGED
@@ -1,24 +1,23 @@
|
|
1 |
{
|
2 |
-
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
-
"
|
5 |
-
"content": "
|
6 |
"lstrip": false,
|
7 |
"normalized": false,
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
},
|
12 |
-
"
|
13 |
-
"content": "
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
-
"
|
21 |
-
"content": "
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
@@ -26,18 +25,16 @@
|
|
26 |
"special": true
|
27 |
}
|
28 |
},
|
29 |
-
"additional_special_tokens": [
|
30 |
-
|
31 |
-
"<|im_end|>"
|
32 |
-
],
|
33 |
-
"bos_token": null,
|
34 |
-
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
"clean_up_tokenization_spaces": false,
|
36 |
-
"eos_token": "
|
37 |
-
"
|
38 |
-
"model_max_length":
|
39 |
-
"pad_token": "
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
|
|
|
|
43 |
}
|
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"legacy": false,
|
33 |
+
"model_max_length": 1000000000000000019884624838656,
|
34 |
+
"pad_token": "</s>",
|
35 |
+
"padding_side": "left",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": true
|
40 |
}
|
checkpoint-2049/trainer_state.json
CHANGED
@@ -9,261 +9,227 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm": 0.2411503791809082,
|
14 |
"learning_rate": 0.0001,
|
15 |
-
"loss":
|
16 |
"step": 100
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"grad_norm": 0.22286373376846313,
|
21 |
"learning_rate": 0.0001,
|
22 |
-
"loss": 1.
|
23 |
"step": 200
|
24 |
},
|
25 |
{
|
26 |
-
"epoch": 0.
|
27 |
-
"grad_norm": 0.24079065024852753,
|
28 |
"learning_rate": 0.0001,
|
29 |
-
"loss": 1.
|
30 |
"step": 300
|
31 |
},
|
32 |
{
|
33 |
-
"epoch": 0
|
34 |
-
"eval_accuracy": 0.
|
35 |
-
"eval_loss": 3.
|
36 |
-
"eval_runtime":
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 341
|
40 |
},
|
41 |
{
|
42 |
-
"epoch": 0
|
43 |
-
"eval_bleu": 0.
|
44 |
-
"eval_exact_match": 0.
|
45 |
-
"eval_prefix_exact_match": 0.
|
46 |
"step": 341
|
47 |
},
|
48 |
{
|
49 |
-
"epoch": 1.
|
50 |
-
"grad_norm": 0.33546799421310425,
|
51 |
"learning_rate": 0.0001,
|
52 |
-
"loss": 1.
|
53 |
"step": 400
|
54 |
},
|
55 |
{
|
56 |
-
"epoch": 1.
|
57 |
-
"grad_norm": 0.3515666723251343,
|
58 |
"learning_rate": 0.0001,
|
59 |
-
"loss": 1.
|
60 |
"step": 500
|
61 |
},
|
62 |
{
|
63 |
-
"epoch": 1.
|
64 |
-
"grad_norm": 0.35733896493911743,
|
65 |
"learning_rate": 0.0001,
|
66 |
-
"loss": 1.
|
67 |
"step": 600
|
68 |
},
|
69 |
{
|
70 |
"epoch": 2.0,
|
71 |
-
"eval_accuracy": 0.
|
72 |
-
"eval_loss":
|
73 |
-
"eval_runtime":
|
74 |
-
"eval_samples_per_second":
|
75 |
-
"eval_steps_per_second":
|
76 |
"step": 683
|
77 |
},
|
78 |
{
|
79 |
"epoch": 2.0,
|
80 |
-
"eval_bleu": 0.
|
81 |
-
"eval_exact_match": 0.
|
82 |
-
"eval_prefix_exact_match": 0.
|
83 |
"step": 683
|
84 |
},
|
85 |
{
|
86 |
-
"epoch": 2.
|
87 |
-
"grad_norm": 0.3784458339214325,
|
88 |
"learning_rate": 0.0001,
|
89 |
-
"loss": 1.
|
90 |
"step": 700
|
91 |
},
|
92 |
{
|
93 |
-
"epoch": 2.
|
94 |
-
"grad_norm": 0.46702849864959717,
|
95 |
"learning_rate": 0.0001,
|
96 |
-
"loss": 1.
|
97 |
"step": 800
|
98 |
},
|
99 |
{
|
100 |
-
"epoch": 2.
|
101 |
-
"grad_norm": 0.5156407356262207,
|
102 |
"learning_rate": 0.0001,
|
103 |
-
"loss": 1.
|
104 |
"step": 900
|
105 |
},
|
106 |
{
|
107 |
-
"epoch": 2.
|
108 |
-
"grad_norm": 0.4755038619041443,
|
109 |
"learning_rate": 0.0001,
|
110 |
-
"loss": 1.
|
111 |
"step": 1000
|
112 |
},
|
113 |
{
|
114 |
-
"epoch":
|
115 |
-
"eval_accuracy": 0.
|
116 |
-
"eval_loss":
|
117 |
-
"eval_runtime":
|
118 |
-
"eval_samples_per_second":
|
119 |
-
"eval_steps_per_second":
|
120 |
"step": 1024
|
121 |
},
|
122 |
{
|
123 |
-
"epoch":
|
124 |
-
"eval_bleu": 0.
|
125 |
-
"eval_exact_match": 0.
|
126 |
-
"eval_prefix_exact_match": 0.
|
127 |
"step": 1024
|
128 |
},
|
129 |
{
|
130 |
-
"epoch": 3.
|
131 |
-
"grad_norm": 0.5288150906562805,
|
132 |
"learning_rate": 0.0001,
|
133 |
-
"loss": 1.
|
134 |
"step": 1100
|
135 |
},
|
136 |
{
|
137 |
-
"epoch": 3.
|
138 |
-
"grad_norm": 0.5784010887145996,
|
139 |
"learning_rate": 0.0001,
|
140 |
-
"loss": 1.
|
141 |
"step": 1200
|
142 |
},
|
143 |
{
|
144 |
-
"epoch": 3.
|
145 |
-
"grad_norm": 0.6458429098129272,
|
146 |
"learning_rate": 0.0001,
|
147 |
-
"loss": 1.
|
148 |
"step": 1300
|
149 |
},
|
150 |
{
|
151 |
"epoch": 4.0,
|
152 |
-
"eval_accuracy": 0.
|
153 |
-
"eval_loss":
|
154 |
-
"eval_runtime": 4.
|
155 |
-
"eval_samples_per_second":
|
156 |
-
"eval_steps_per_second":
|
157 |
"step": 1366
|
158 |
},
|
159 |
{
|
160 |
"epoch": 4.0,
|
161 |
-
"eval_bleu": 0.
|
162 |
-
"eval_exact_match": 0.
|
163 |
-
"eval_prefix_exact_match": 0.
|
164 |
"step": 1366
|
165 |
},
|
166 |
{
|
167 |
-
"epoch": 4.
|
168 |
-
"grad_norm": 0.732841432094574,
|
169 |
"learning_rate": 0.0001,
|
170 |
-
"loss": 1.
|
171 |
"step": 1400
|
172 |
},
|
173 |
{
|
174 |
-
"epoch": 4.
|
175 |
-
"grad_norm": 0.7372816205024719,
|
176 |
"learning_rate": 0.0001,
|
177 |
-
"loss":
|
178 |
"step": 1500
|
179 |
},
|
180 |
{
|
181 |
-
"epoch": 4.
|
182 |
-
"grad_norm": 0.8235049247741699,
|
183 |
"learning_rate": 0.0001,
|
184 |
-
"loss": 1.
|
185 |
"step": 1600
|
186 |
},
|
187 |
{
|
188 |
-
"epoch": 4.
|
189 |
-
"grad_norm": 0.7765743732452393,
|
190 |
"learning_rate": 0.0001,
|
191 |
-
"loss":
|
192 |
"step": 1700
|
193 |
},
|
194 |
{
|
195 |
-
"epoch":
|
196 |
-
"eval_accuracy": 0.
|
197 |
-
"eval_loss":
|
198 |
-
"eval_runtime": 4.
|
199 |
-
"eval_samples_per_second":
|
200 |
-
"eval_steps_per_second": 12.
|
201 |
"step": 1707
|
202 |
},
|
203 |
{
|
204 |
-
"epoch":
|
205 |
-
"eval_bleu": 0.
|
206 |
-
"eval_exact_match": 0.
|
207 |
-
"eval_prefix_exact_match": 0.
|
208 |
"step": 1707
|
209 |
},
|
210 |
{
|
211 |
-
"epoch": 5.
|
212 |
-
"grad_norm": 0.9119400978088379,
|
213 |
"learning_rate": 0.0001,
|
214 |
-
"loss":
|
215 |
"step": 1800
|
216 |
},
|
217 |
{
|
218 |
-
"epoch": 5.
|
219 |
-
"grad_norm": 0.8966185450553894,
|
220 |
"learning_rate": 0.0001,
|
221 |
-
"loss":
|
222 |
"step": 1900
|
223 |
},
|
224 |
{
|
225 |
-
"epoch": 5.
|
226 |
-
"grad_norm": 0.9629669189453125,
|
227 |
"learning_rate": 0.0001,
|
228 |
-
"loss":
|
229 |
"step": 2000
|
230 |
},
|
231 |
{
|
232 |
"epoch": 6.0,
|
233 |
-
"eval_accuracy": 0.
|
234 |
-
"eval_loss":
|
235 |
-
"eval_runtime": 4.
|
236 |
-
"eval_samples_per_second":
|
237 |
-
"eval_steps_per_second":
|
238 |
"step": 2049
|
239 |
},
|
240 |
{
|
241 |
"epoch": 6.0,
|
242 |
-
"eval_bleu": 0.
|
243 |
-
"eval_exact_match": 0.
|
244 |
-
"eval_prefix_exact_match": 0.
|
245 |
"step": 2049
|
246 |
}
|
247 |
],
|
248 |
"logging_steps": 100,
|
249 |
"max_steps": 17050,
|
250 |
-
"num_input_tokens_seen": 0,
|
251 |
"num_train_epochs": 50,
|
252 |
"save_steps": 500,
|
253 |
-
"
|
254 |
-
"TrainerControl": {
|
255 |
-
"args": {
|
256 |
-
"should_epoch_stop": false,
|
257 |
-
"should_evaluate": false,
|
258 |
-
"should_log": false,
|
259 |
-
"should_save": true,
|
260 |
-
"should_training_stop": false
|
261 |
-
},
|
262 |
-
"attributes": {}
|
263 |
-
}
|
264 |
-
},
|
265 |
-
"total_flos": 1.7594902430036787e+17,
|
266 |
-
"train_batch_size": 1,
|
267 |
"trial_name": null,
|
268 |
"trial_params": null
|
269 |
}
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.29,
|
|
|
13 |
"learning_rate": 0.0001,
|
14 |
+
"loss": 1.4842,
|
15 |
"step": 100
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.59,
|
|
|
19 |
"learning_rate": 0.0001,
|
20 |
+
"loss": 1.4016,
|
21 |
"step": 200
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.88,
|
|
|
25 |
"learning_rate": 0.0001,
|
26 |
+
"loss": 1.3892,
|
27 |
"step": 300
|
28 |
},
|
29 |
{
|
30 |
+
"epoch": 1.0,
|
31 |
+
"eval_accuracy": 0.4543589743589744,
|
32 |
+
"eval_loss": 3.4055869579315186,
|
33 |
+
"eval_runtime": 4.1688,
|
34 |
+
"eval_samples_per_second": 119.938,
|
35 |
+
"eval_steps_per_second": 15.112,
|
36 |
"step": 341
|
37 |
},
|
38 |
{
|
39 |
+
"epoch": 1.0,
|
40 |
+
"eval_bleu": 0.09711501224106496,
|
41 |
+
"eval_exact_match": 0.0,
|
42 |
+
"eval_prefix_exact_match": 0.054,
|
43 |
"step": 341
|
44 |
},
|
45 |
{
|
46 |
+
"epoch": 1.17,
|
|
|
47 |
"learning_rate": 0.0001,
|
48 |
+
"loss": 1.3608,
|
49 |
"step": 400
|
50 |
},
|
51 |
{
|
52 |
+
"epoch": 1.46,
|
|
|
53 |
"learning_rate": 0.0001,
|
54 |
+
"loss": 1.3456,
|
55 |
"step": 500
|
56 |
},
|
57 |
{
|
58 |
+
"epoch": 1.76,
|
|
|
59 |
"learning_rate": 0.0001,
|
60 |
+
"loss": 1.3499,
|
61 |
"step": 600
|
62 |
},
|
63 |
{
|
64 |
"epoch": 2.0,
|
65 |
+
"eval_accuracy": 0.4576923076923077,
|
66 |
+
"eval_loss": 3.453113317489624,
|
67 |
+
"eval_runtime": 4.4031,
|
68 |
+
"eval_samples_per_second": 113.556,
|
69 |
+
"eval_steps_per_second": 14.308,
|
70 |
"step": 683
|
71 |
},
|
72 |
{
|
73 |
"epoch": 2.0,
|
74 |
+
"eval_bleu": 0.1225593574040313,
|
75 |
+
"eval_exact_match": 0.0,
|
76 |
+
"eval_prefix_exact_match": 0.056,
|
77 |
"step": 683
|
78 |
},
|
79 |
{
|
80 |
+
"epoch": 2.05,
|
|
|
81 |
"learning_rate": 0.0001,
|
82 |
+
"loss": 1.3238,
|
83 |
"step": 700
|
84 |
},
|
85 |
{
|
86 |
+
"epoch": 2.34,
|
|
|
87 |
"learning_rate": 0.0001,
|
88 |
+
"loss": 1.2486,
|
89 |
"step": 800
|
90 |
},
|
91 |
{
|
92 |
+
"epoch": 2.64,
|
|
|
93 |
"learning_rate": 0.0001,
|
94 |
+
"loss": 1.2452,
|
95 |
"step": 900
|
96 |
},
|
97 |
{
|
98 |
+
"epoch": 2.93,
|
|
|
99 |
"learning_rate": 0.0001,
|
100 |
+
"loss": 1.2427,
|
101 |
"step": 1000
|
102 |
},
|
103 |
{
|
104 |
+
"epoch": 3.0,
|
105 |
+
"eval_accuracy": 0.4584102564102564,
|
106 |
+
"eval_loss": 3.671137809753418,
|
107 |
+
"eval_runtime": 4.4094,
|
108 |
+
"eval_samples_per_second": 113.393,
|
109 |
+
"eval_steps_per_second": 14.288,
|
110 |
"step": 1024
|
111 |
},
|
112 |
{
|
113 |
+
"epoch": 3.0,
|
114 |
+
"eval_bleu": 0.13165889774889974,
|
115 |
+
"eval_exact_match": 0.0,
|
116 |
+
"eval_prefix_exact_match": 0.056,
|
117 |
"step": 1024
|
118 |
},
|
119 |
{
|
120 |
+
"epoch": 3.22,
|
|
|
121 |
"learning_rate": 0.0001,
|
122 |
+
"loss": 1.1507,
|
123 |
"step": 1100
|
124 |
},
|
125 |
{
|
126 |
+
"epoch": 3.51,
|
|
|
127 |
"learning_rate": 0.0001,
|
128 |
+
"loss": 1.1218,
|
129 |
"step": 1200
|
130 |
},
|
131 |
{
|
132 |
+
"epoch": 3.81,
|
|
|
133 |
"learning_rate": 0.0001,
|
134 |
+
"loss": 1.1231,
|
135 |
"step": 1300
|
136 |
},
|
137 |
{
|
138 |
"epoch": 4.0,
|
139 |
+
"eval_accuracy": 0.45697435897435895,
|
140 |
+
"eval_loss": 3.7999510765075684,
|
141 |
+
"eval_runtime": 4.0886,
|
142 |
+
"eval_samples_per_second": 122.29,
|
143 |
+
"eval_steps_per_second": 15.409,
|
144 |
"step": 1366
|
145 |
},
|
146 |
{
|
147 |
"epoch": 4.0,
|
148 |
+
"eval_bleu": 0.15413978034957934,
|
149 |
+
"eval_exact_match": 0.0,
|
150 |
+
"eval_prefix_exact_match": 0.054,
|
151 |
"step": 1366
|
152 |
},
|
153 |
{
|
154 |
+
"epoch": 4.1,
|
|
|
155 |
"learning_rate": 0.0001,
|
156 |
+
"loss": 1.0823,
|
157 |
"step": 1400
|
158 |
},
|
159 |
{
|
160 |
+
"epoch": 4.39,
|
|
|
161 |
"learning_rate": 0.0001,
|
162 |
+
"loss": 0.997,
|
163 |
"step": 1500
|
164 |
},
|
165 |
{
|
166 |
+
"epoch": 4.69,
|
|
|
167 |
"learning_rate": 0.0001,
|
168 |
+
"loss": 1.0024,
|
169 |
"step": 1600
|
170 |
},
|
171 |
{
|
172 |
+
"epoch": 4.98,
|
|
|
173 |
"learning_rate": 0.0001,
|
174 |
+
"loss": 0.995,
|
175 |
"step": 1700
|
176 |
},
|
177 |
{
|
178 |
+
"epoch": 5.0,
|
179 |
+
"eval_accuracy": 0.4552307692307692,
|
180 |
+
"eval_loss": 3.953216314315796,
|
181 |
+
"eval_runtime": 4.9824,
|
182 |
+
"eval_samples_per_second": 100.354,
|
183 |
+
"eval_steps_per_second": 12.645,
|
184 |
"step": 1707
|
185 |
},
|
186 |
{
|
187 |
+
"epoch": 5.0,
|
188 |
+
"eval_bleu": 0.1611344512465791,
|
189 |
+
"eval_exact_match": 0.0,
|
190 |
+
"eval_prefix_exact_match": 0.046,
|
191 |
"step": 1707
|
192 |
},
|
193 |
{
|
194 |
+
"epoch": 5.27,
|
|
|
195 |
"learning_rate": 0.0001,
|
196 |
+
"loss": 0.8495,
|
197 |
"step": 1800
|
198 |
},
|
199 |
{
|
200 |
+
"epoch": 5.56,
|
|
|
201 |
"learning_rate": 0.0001,
|
202 |
+
"loss": 0.854,
|
203 |
"step": 1900
|
204 |
},
|
205 |
{
|
206 |
+
"epoch": 5.86,
|
|
|
207 |
"learning_rate": 0.0001,
|
208 |
+
"loss": 0.8693,
|
209 |
"step": 2000
|
210 |
},
|
211 |
{
|
212 |
"epoch": 6.0,
|
213 |
+
"eval_accuracy": 0.45261538461538464,
|
214 |
+
"eval_loss": 4.0766072273254395,
|
215 |
+
"eval_runtime": 4.8095,
|
216 |
+
"eval_samples_per_second": 103.961,
|
217 |
+
"eval_steps_per_second": 13.099,
|
218 |
"step": 2049
|
219 |
},
|
220 |
{
|
221 |
"epoch": 6.0,
|
222 |
+
"eval_bleu": 0.1489904300924264,
|
223 |
+
"eval_exact_match": 0.0,
|
224 |
+
"eval_prefix_exact_match": 0.044,
|
225 |
"step": 2049
|
226 |
}
|
227 |
],
|
228 |
"logging_steps": 100,
|
229 |
"max_steps": 17050,
|
|
|
230 |
"num_train_epochs": 50,
|
231 |
"save_steps": 500,
|
232 |
+
"total_flos": 4.058144497152819e+17,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
233 |
"trial_name": null,
|
234 |
"trial_params": null
|
235 |
}
|
checkpoint-2049/training_args.bin
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 sha256:3c60050af374bb2df141f4673c8141d59d83a5bd892d35ffa56ce8af555309ff
|
3 |
+
size 4728
|