wangjiawei2003
commited on
Commit
•
30c2ba8
1
Parent(s):
95c86c8
Training in progress, epoch 3
Browse files- model.safetensors +1 -1
- run-2/checkpoint-25257/config.json +25 -0
- run-2/checkpoint-25257/model.safetensors +3 -0
- run-2/checkpoint-25257/optimizer.pt +3 -0
- run-2/checkpoint-25257/rng_state.pth +3 -0
- run-2/checkpoint-25257/scheduler.pt +3 -0
- run-2/checkpoint-25257/special_tokens_map.json +7 -0
- run-2/checkpoint-25257/tokenizer.json +0 -0
- run-2/checkpoint-25257/tokenizer_config.json +55 -0
- run-2/checkpoint-25257/trainer_state.json +403 -0
- run-2/checkpoint-25257/training_args.bin +3 -0
- run-2/checkpoint-25257/vocab.txt +0 -0
- runs/May14_13-42-22_d0b6fd4b0e89/events.out.tfevents.1715698909.d0b6fd4b0e89.396.4 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:396a602b86e9b47336000b3847f184cbdd8cddba61fcf96401eb71ac6d9cb497
|
3 |
size 267832560
|
run-2/checkpoint-25257/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-2/checkpoint-25257/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:396a602b86e9b47336000b3847f184cbdd8cddba61fcf96401eb71ac6d9cb497
|
3 |
+
size 267832560
|
run-2/checkpoint-25257/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cb84843fb9b8c0cd7875414873b061e2e44cb9c82b034b4d12b7d534025c3ac
|
3 |
+
size 535727290
|
run-2/checkpoint-25257/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dc39421d19a2101c52f62917539decd7e32a659ae131a19a96b04ed40a90d15
|
3 |
+
size 14244
|
run-2/checkpoint-25257/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:779b39413c9277b7d5bf1aeb14d0ef29a2e7472c45956c49dc655cb0a6f69898
|
3 |
+
size 1064
|
run-2/checkpoint-25257/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-2/checkpoint-25257/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-2/checkpoint-25257/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-2/checkpoint-25257/trainer_state.json
ADDED
@@ -0,0 +1,403 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.9059633027522935,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-sst2/run-2/checkpoint-25257",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 25257,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.05938947618482005,
|
13 |
+
"grad_norm": 6.959882736206055,
|
14 |
+
"learning_rate": 2.20446303880587e-06,
|
15 |
+
"loss": 0.5244,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.1187789523696401,
|
20 |
+
"grad_norm": 27.900440216064453,
|
21 |
+
"learning_rate": 2.1599410240462895e-06,
|
22 |
+
"loss": 0.3407,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.17816842855446016,
|
27 |
+
"grad_norm": 16.400848388671875,
|
28 |
+
"learning_rate": 2.115419009286709e-06,
|
29 |
+
"loss": 0.3444,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.2375579047392802,
|
34 |
+
"grad_norm": 16.666898727416992,
|
35 |
+
"learning_rate": 2.0708969945271283e-06,
|
36 |
+
"loss": 0.3153,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.2969473809241002,
|
41 |
+
"grad_norm": 22.084596633911133,
|
42 |
+
"learning_rate": 2.026374979767548e-06,
|
43 |
+
"loss": 0.3076,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3563368571089203,
|
48 |
+
"grad_norm": 42.26548385620117,
|
49 |
+
"learning_rate": 1.9818529650079676e-06,
|
50 |
+
"loss": 0.3228,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.41572633329374037,
|
55 |
+
"grad_norm": 48.90976333618164,
|
56 |
+
"learning_rate": 1.937330950248387e-06,
|
57 |
+
"loss": 0.3099,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.4751158094785604,
|
62 |
+
"grad_norm": 23.298206329345703,
|
63 |
+
"learning_rate": 1.8928089354888066e-06,
|
64 |
+
"loss": 0.2982,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.5345052856633804,
|
69 |
+
"grad_norm": 31.678531646728516,
|
70 |
+
"learning_rate": 1.848286920729226e-06,
|
71 |
+
"loss": 0.3012,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.5938947618482004,
|
76 |
+
"grad_norm": 14.523043632507324,
|
77 |
+
"learning_rate": 1.8037649059696455e-06,
|
78 |
+
"loss": 0.3075,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6532842380330206,
|
83 |
+
"grad_norm": 2.0264182090759277,
|
84 |
+
"learning_rate": 1.7592428912100647e-06,
|
85 |
+
"loss": 0.2902,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.7126737142178406,
|
90 |
+
"grad_norm": 1.4845110177993774,
|
91 |
+
"learning_rate": 1.7147208764504845e-06,
|
92 |
+
"loss": 0.2929,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.7720631904026607,
|
97 |
+
"grad_norm": 21.62343406677246,
|
98 |
+
"learning_rate": 1.6701988616909037e-06,
|
99 |
+
"loss": 0.3003,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.8314526665874807,
|
104 |
+
"grad_norm": 6.294283866882324,
|
105 |
+
"learning_rate": 1.6256768469313231e-06,
|
106 |
+
"loss": 0.2949,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.8908421427723008,
|
111 |
+
"grad_norm": 52.94987106323242,
|
112 |
+
"learning_rate": 1.5811548321717428e-06,
|
113 |
+
"loss": 0.2685,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.9502316189571208,
|
118 |
+
"grad_norm": 10.51728343963623,
|
119 |
+
"learning_rate": 1.5366328174121622e-06,
|
120 |
+
"loss": 0.299,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.0,
|
125 |
+
"eval_accuracy": 0.8979357798165137,
|
126 |
+
"eval_loss": 0.33407795429229736,
|
127 |
+
"eval_runtime": 1.2282,
|
128 |
+
"eval_samples_per_second": 709.994,
|
129 |
+
"eval_steps_per_second": 44.782,
|
130 |
+
"step": 8419
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 1.0096210951419409,
|
134 |
+
"grad_norm": 0.3329325318336487,
|
135 |
+
"learning_rate": 1.4921108026525816e-06,
|
136 |
+
"loss": 0.2627,
|
137 |
+
"step": 8500
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 1.0690105713267608,
|
141 |
+
"grad_norm": 2.096174716949463,
|
142 |
+
"learning_rate": 1.4475887878930012e-06,
|
143 |
+
"loss": 0.2634,
|
144 |
+
"step": 9000
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 1.128400047511581,
|
148 |
+
"grad_norm": 6.27714729309082,
|
149 |
+
"learning_rate": 1.4030667731334206e-06,
|
150 |
+
"loss": 0.2496,
|
151 |
+
"step": 9500
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 1.187789523696401,
|
155 |
+
"grad_norm": 7.023980140686035,
|
156 |
+
"learning_rate": 1.35854475837384e-06,
|
157 |
+
"loss": 0.2545,
|
158 |
+
"step": 10000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.247178999881221,
|
162 |
+
"grad_norm": 4.648576259613037,
|
163 |
+
"learning_rate": 1.3140227436142597e-06,
|
164 |
+
"loss": 0.2437,
|
165 |
+
"step": 10500
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 1.3065684760660412,
|
169 |
+
"grad_norm": 9.04944133758545,
|
170 |
+
"learning_rate": 1.269500728854679e-06,
|
171 |
+
"loss": 0.2786,
|
172 |
+
"step": 11000
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 1.3659579522508611,
|
176 |
+
"grad_norm": 46.005550384521484,
|
177 |
+
"learning_rate": 1.2249787140950985e-06,
|
178 |
+
"loss": 0.2505,
|
179 |
+
"step": 11500
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 1.425347428435681,
|
183 |
+
"grad_norm": 9.347773551940918,
|
184 |
+
"learning_rate": 1.1804566993355181e-06,
|
185 |
+
"loss": 0.253,
|
186 |
+
"step": 12000
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 1.4847369046205012,
|
190 |
+
"grad_norm": 0.32879364490509033,
|
191 |
+
"learning_rate": 1.1359346845759375e-06,
|
192 |
+
"loss": 0.2645,
|
193 |
+
"step": 12500
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 1.5441263808053214,
|
197 |
+
"grad_norm": 5.314579963684082,
|
198 |
+
"learning_rate": 1.0914126698163572e-06,
|
199 |
+
"loss": 0.245,
|
200 |
+
"step": 13000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.6035158569901413,
|
204 |
+
"grad_norm": 109.37725067138672,
|
205 |
+
"learning_rate": 1.0468906550567764e-06,
|
206 |
+
"loss": 0.254,
|
207 |
+
"step": 13500
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.6629053331749613,
|
211 |
+
"grad_norm": 31.469161987304688,
|
212 |
+
"learning_rate": 1.002368640297196e-06,
|
213 |
+
"loss": 0.2301,
|
214 |
+
"step": 14000
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 1.7222948093597814,
|
218 |
+
"grad_norm": 70.80547332763672,
|
219 |
+
"learning_rate": 9.578466255376154e-07,
|
220 |
+
"loss": 0.2229,
|
221 |
+
"step": 14500
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.7816842855446016,
|
225 |
+
"grad_norm": 0.23098599910736084,
|
226 |
+
"learning_rate": 9.133246107780349e-07,
|
227 |
+
"loss": 0.2528,
|
228 |
+
"step": 15000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 1.8410737617294215,
|
232 |
+
"grad_norm": 32.48334503173828,
|
233 |
+
"learning_rate": 8.688025960184545e-07,
|
234 |
+
"loss": 0.2302,
|
235 |
+
"step": 15500
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 1.9004632379142414,
|
239 |
+
"grad_norm": 7.071863651275635,
|
240 |
+
"learning_rate": 8.242805812588738e-07,
|
241 |
+
"loss": 0.2388,
|
242 |
+
"step": 16000
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.9598527140990618,
|
246 |
+
"grad_norm": 24.40359115600586,
|
247 |
+
"learning_rate": 7.797585664992933e-07,
|
248 |
+
"loss": 0.2594,
|
249 |
+
"step": 16500
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.0,
|
253 |
+
"eval_accuracy": 0.9013761467889908,
|
254 |
+
"eval_loss": 0.37052449584007263,
|
255 |
+
"eval_runtime": 1.2139,
|
256 |
+
"eval_samples_per_second": 718.356,
|
257 |
+
"eval_steps_per_second": 45.309,
|
258 |
+
"step": 16838
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 2.0192421902838817,
|
262 |
+
"grad_norm": 0.2496776133775711,
|
263 |
+
"learning_rate": 7.352365517397128e-07,
|
264 |
+
"loss": 0.2314,
|
265 |
+
"step": 17000
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 2.0786316664687017,
|
269 |
+
"grad_norm": 10.829848289489746,
|
270 |
+
"learning_rate": 6.907145369801322e-07,
|
271 |
+
"loss": 0.2058,
|
272 |
+
"step": 17500
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.1380211426535216,
|
276 |
+
"grad_norm": 1.5813004970550537,
|
277 |
+
"learning_rate": 6.461925222205517e-07,
|
278 |
+
"loss": 0.2284,
|
279 |
+
"step": 18000
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 2.197410618838342,
|
283 |
+
"grad_norm": 1.1905676126480103,
|
284 |
+
"learning_rate": 6.016705074609713e-07,
|
285 |
+
"loss": 0.211,
|
286 |
+
"step": 18500
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 2.256800095023162,
|
290 |
+
"grad_norm": 10.768214225769043,
|
291 |
+
"learning_rate": 5.571484927013907e-07,
|
292 |
+
"loss": 0.2349,
|
293 |
+
"step": 19000
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 2.316189571207982,
|
297 |
+
"grad_norm": 1.3178966045379639,
|
298 |
+
"learning_rate": 5.126264779418102e-07,
|
299 |
+
"loss": 0.204,
|
300 |
+
"step": 19500
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 2.375579047392802,
|
304 |
+
"grad_norm": 89.94540405273438,
|
305 |
+
"learning_rate": 4.6810446318222967e-07,
|
306 |
+
"loss": 0.2094,
|
307 |
+
"step": 20000
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 2.434968523577622,
|
311 |
+
"grad_norm": 83.14887237548828,
|
312 |
+
"learning_rate": 4.2358244842264914e-07,
|
313 |
+
"loss": 0.2208,
|
314 |
+
"step": 20500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 2.494357999762442,
|
318 |
+
"grad_norm": 1.2761434316635132,
|
319 |
+
"learning_rate": 3.7906043366306855e-07,
|
320 |
+
"loss": 0.2298,
|
321 |
+
"step": 21000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 2.553747475947262,
|
325 |
+
"grad_norm": 27.40999984741211,
|
326 |
+
"learning_rate": 3.3453841890348807e-07,
|
327 |
+
"loss": 0.2302,
|
328 |
+
"step": 21500
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 2.6131369521320824,
|
332 |
+
"grad_norm": 0.43853724002838135,
|
333 |
+
"learning_rate": 2.9001640414390754e-07,
|
334 |
+
"loss": 0.2238,
|
335 |
+
"step": 22000
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 2.6725264283169023,
|
339 |
+
"grad_norm": 0.7176188826560974,
|
340 |
+
"learning_rate": 2.45494389384327e-07,
|
341 |
+
"loss": 0.2256,
|
342 |
+
"step": 22500
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 2.7319159045017223,
|
346 |
+
"grad_norm": 1.2089786529541016,
|
347 |
+
"learning_rate": 2.009723746247465e-07,
|
348 |
+
"loss": 0.2053,
|
349 |
+
"step": 23000
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 2.791305380686542,
|
353 |
+
"grad_norm": 48.92116165161133,
|
354 |
+
"learning_rate": 1.5645035986516597e-07,
|
355 |
+
"loss": 0.2301,
|
356 |
+
"step": 23500
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 2.850694856871362,
|
360 |
+
"grad_norm": 1.1826889514923096,
|
361 |
+
"learning_rate": 1.1192834510558544e-07,
|
362 |
+
"loss": 0.208,
|
363 |
+
"step": 24000
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 2.9100843330561825,
|
367 |
+
"grad_norm": 16.557043075561523,
|
368 |
+
"learning_rate": 6.740633034600492e-08,
|
369 |
+
"loss": 0.2303,
|
370 |
+
"step": 24500
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 2.9694738092410025,
|
374 |
+
"grad_norm": 1.251015067100525,
|
375 |
+
"learning_rate": 2.2884315586424388e-08,
|
376 |
+
"loss": 0.2196,
|
377 |
+
"step": 25000
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 3.0,
|
381 |
+
"eval_accuracy": 0.9059633027522935,
|
382 |
+
"eval_loss": 0.37748080492019653,
|
383 |
+
"eval_runtime": 1.2054,
|
384 |
+
"eval_samples_per_second": 723.412,
|
385 |
+
"eval_steps_per_second": 45.628,
|
386 |
+
"step": 25257
|
387 |
+
}
|
388 |
+
],
|
389 |
+
"logging_steps": 500,
|
390 |
+
"max_steps": 25257,
|
391 |
+
"num_input_tokens_seen": 0,
|
392 |
+
"num_train_epochs": 3,
|
393 |
+
"save_steps": 500,
|
394 |
+
"total_flos": 1538900160176328.0,
|
395 |
+
"train_batch_size": 8,
|
396 |
+
"trial_name": null,
|
397 |
+
"trial_params": {
|
398 |
+
"learning_rate": 2.2489850535654507e-06,
|
399 |
+
"num_train_epochs": 3,
|
400 |
+
"per_device_train_batch_size": 8,
|
401 |
+
"seed": 11
|
402 |
+
}
|
403 |
+
}
|
run-2/checkpoint-25257/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f28c54c631beb4aad19ce06fef9fbf9a411e80177ae39964fa9c31526a231b3
|
3 |
+
size 5048
|
run-2/checkpoint-25257/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/May14_13-42-22_d0b6fd4b0e89/events.out.tfevents.1715698909.d0b6fd4b0e89.396.4
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:f1aa58c4bedb0196a81dece0046e420a287958d5b1e84e4ab9efb7732834cba5
|
3 |
+
size 16601
|