Training in progress, epoch 5
Browse files- model.safetensors +1 -1
- run-0/checkpoint-10690/config.json +25 -0
- run-0/checkpoint-10690/model.safetensors +3 -0
- run-0/checkpoint-10690/optimizer.pt +3 -0
- run-0/checkpoint-10690/rng_state.pth +3 -0
- run-0/checkpoint-10690/scheduler.pt +3 -0
- run-0/checkpoint-10690/special_tokens_map.json +7 -0
- run-0/checkpoint-10690/tokenizer.json +0 -0
- run-0/checkpoint-10690/tokenizer_config.json +55 -0
- run-0/checkpoint-10690/trainer_state.json +197 -0
- run-0/checkpoint-10690/training_args.bin +3 -0
- run-0/checkpoint-10690/vocab.txt +0 -0
- run-0/checkpoint-6414/config.json +25 -0
- run-0/checkpoint-6414/model.safetensors +3 -0
- run-0/checkpoint-6414/optimizer.pt +3 -0
- run-0/checkpoint-6414/rng_state.pth +3 -0
- run-0/checkpoint-6414/scheduler.pt +3 -0
- run-0/checkpoint-6414/special_tokens_map.json +7 -0
- run-0/checkpoint-6414/tokenizer.json +0 -0
- run-0/checkpoint-6414/tokenizer_config.json +55 -0
- run-0/checkpoint-6414/trainer_state.json +125 -0
- run-0/checkpoint-6414/training_args.bin +3 -0
- run-0/checkpoint-6414/vocab.txt +0 -0
- run-0/checkpoint-8552/config.json +25 -0
- run-0/checkpoint-8552/model.safetensors +3 -0
- run-0/checkpoint-8552/optimizer.pt +3 -0
- run-0/checkpoint-8552/rng_state.pth +3 -0
- run-0/checkpoint-8552/scheduler.pt +3 -0
- run-0/checkpoint-8552/special_tokens_map.json +7 -0
- run-0/checkpoint-8552/tokenizer.json +0 -0
- run-0/checkpoint-8552/tokenizer_config.json +55 -0
- run-0/checkpoint-8552/trainer_state.json +164 -0
- run-0/checkpoint-8552/training_args.bin +3 -0
- run-0/checkpoint-8552/vocab.txt +0 -0
- runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703297718.48296f50e732.508.1 +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:bf8e24880158795840c932e820aae6deea370acb3a19ddf07ea9e5d52759e460
|
3 |
size 267832560
|
run-0/checkpoint-10690/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": "4.36.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-0/checkpoint-10690/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf8e24880158795840c932e820aae6deea370acb3a19ddf07ea9e5d52759e460
|
3 |
+
size 267832560
|
run-0/checkpoint-10690/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:140e8a01f0e9e13101f700c7b4048f9cbfcb23ce4ec8cb8948e6ed3e2ee7a087
|
3 |
+
size 535727290
|
run-0/checkpoint-10690/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22a2ffb369e82afc10200872aab0d9890beada13739ada253864da0f4bf0115b
|
3 |
+
size 14308
|
run-0/checkpoint-10690/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e98ccc3dd6a04299cff9e498bc91df85d0f21a66c58dae005e24043b1311dda8
|
3 |
+
size 1064
|
run-0/checkpoint-10690/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-0/checkpoint-10690/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-10690/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-0/checkpoint-10690/trainer_state.json
ADDED
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 10690,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.23,
|
13 |
+
"learning_rate": 9.456689869150003e-05,
|
14 |
+
"loss": 0.6195,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.47,
|
19 |
+
"learning_rate": 8.992671720516538e-05,
|
20 |
+
"loss": 0.6229,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.7,
|
25 |
+
"learning_rate": 8.528653571883074e-05,
|
26 |
+
"loss": 0.6157,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.94,
|
31 |
+
"learning_rate": 8.064635423249609e-05,
|
32 |
+
"loss": 0.6166,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.0,
|
37 |
+
"eval_loss": 0.6419090628623962,
|
38 |
+
"eval_matthews_correlation": 0.0,
|
39 |
+
"eval_runtime": 0.7217,
|
40 |
+
"eval_samples_per_second": 1445.223,
|
41 |
+
"eval_steps_per_second": 91.452,
|
42 |
+
"step": 2138
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.17,
|
46 |
+
"learning_rate": 7.600617274616145e-05,
|
47 |
+
"loss": 0.6097,
|
48 |
+
"step": 2500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.4,
|
52 |
+
"learning_rate": 7.13659912598268e-05,
|
53 |
+
"loss": 0.6152,
|
54 |
+
"step": 3000
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.64,
|
58 |
+
"learning_rate": 6.672580977349217e-05,
|
59 |
+
"loss": 0.6082,
|
60 |
+
"step": 3500
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.87,
|
64 |
+
"learning_rate": 6.208562828715752e-05,
|
65 |
+
"loss": 0.6177,
|
66 |
+
"step": 4000
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 2.0,
|
70 |
+
"eval_loss": 0.6392126083374023,
|
71 |
+
"eval_matthews_correlation": 0.0,
|
72 |
+
"eval_runtime": 0.7452,
|
73 |
+
"eval_samples_per_second": 1399.645,
|
74 |
+
"eval_steps_per_second": 88.568,
|
75 |
+
"step": 4276
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.1,
|
79 |
+
"learning_rate": 5.7445446800822885e-05,
|
80 |
+
"loss": 0.6101,
|
81 |
+
"step": 4500
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.34,
|
85 |
+
"learning_rate": 5.2805265314488234e-05,
|
86 |
+
"loss": 0.6274,
|
87 |
+
"step": 5000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.57,
|
91 |
+
"learning_rate": 4.81650838281536e-05,
|
92 |
+
"loss": 0.6133,
|
93 |
+
"step": 5500
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.81,
|
97 |
+
"learning_rate": 4.352490234181895e-05,
|
98 |
+
"loss": 0.5974,
|
99 |
+
"step": 6000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 3.0,
|
103 |
+
"eval_loss": 0.6237232089042664,
|
104 |
+
"eval_matthews_correlation": 0.0,
|
105 |
+
"eval_runtime": 0.757,
|
106 |
+
"eval_samples_per_second": 1377.809,
|
107 |
+
"eval_steps_per_second": 87.186,
|
108 |
+
"step": 6414
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 3.04,
|
112 |
+
"learning_rate": 3.888472085548431e-05,
|
113 |
+
"loss": 0.608,
|
114 |
+
"step": 6500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.27,
|
118 |
+
"learning_rate": 3.4244539369149664e-05,
|
119 |
+
"loss": 0.6216,
|
120 |
+
"step": 7000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 3.51,
|
124 |
+
"learning_rate": 2.960435788281502e-05,
|
125 |
+
"loss": 0.6076,
|
126 |
+
"step": 7500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 3.74,
|
130 |
+
"learning_rate": 2.4964176396480383e-05,
|
131 |
+
"loss": 0.6187,
|
132 |
+
"step": 8000
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 3.98,
|
136 |
+
"learning_rate": 2.0323994910145736e-05,
|
137 |
+
"loss": 0.5935,
|
138 |
+
"step": 8500
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 4.0,
|
142 |
+
"eval_loss": 0.6235376000404358,
|
143 |
+
"eval_matthews_correlation": 0.0,
|
144 |
+
"eval_runtime": 0.7514,
|
145 |
+
"eval_samples_per_second": 1388.129,
|
146 |
+
"eval_steps_per_second": 87.839,
|
147 |
+
"step": 8552
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 4.21,
|
151 |
+
"learning_rate": 1.568381342381109e-05,
|
152 |
+
"loss": 0.6258,
|
153 |
+
"step": 9000
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 4.44,
|
157 |
+
"learning_rate": 1.104363193747645e-05,
|
158 |
+
"loss": 0.62,
|
159 |
+
"step": 9500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 4.68,
|
163 |
+
"learning_rate": 6.403450451141807e-06,
|
164 |
+
"loss": 0.6027,
|
165 |
+
"step": 10000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 4.91,
|
169 |
+
"learning_rate": 1.7632689648071642e-06,
|
170 |
+
"loss": 0.6029,
|
171 |
+
"step": 10500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 5.0,
|
175 |
+
"eval_loss": 0.6506770253181458,
|
176 |
+
"eval_matthews_correlation": 0.0,
|
177 |
+
"eval_runtime": 0.7746,
|
178 |
+
"eval_samples_per_second": 1346.479,
|
179 |
+
"eval_steps_per_second": 85.204,
|
180 |
+
"step": 10690
|
181 |
+
}
|
182 |
+
],
|
183 |
+
"logging_steps": 500,
|
184 |
+
"max_steps": 10690,
|
185 |
+
"num_input_tokens_seen": 0,
|
186 |
+
"num_train_epochs": 5,
|
187 |
+
"save_steps": 500,
|
188 |
+
"total_flos": 171363138586368.0,
|
189 |
+
"train_batch_size": 4,
|
190 |
+
"trial_name": null,
|
191 |
+
"trial_params": {
|
192 |
+
"learning_rate": 9.920708017783467e-05,
|
193 |
+
"num_train_epochs": 5,
|
194 |
+
"per_device_train_batch_size": 4,
|
195 |
+
"seed": 31
|
196 |
+
}
|
197 |
+
}
|
run-0/checkpoint-10690/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c864ad0b0686dfaa2454427080519f24d7ce414d236604b49409835d4e23b3cb
|
3 |
+
size 4792
|
run-0/checkpoint-10690/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-6414/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": "4.36.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-0/checkpoint-6414/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14dd7232312fa3de498499afe6b679f2023f024f439950f6abd03b349d535cdb
|
3 |
+
size 267832560
|
run-0/checkpoint-6414/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71bb50f45f5cc8ca163d7c64a25689d25a944167a8988b9906aabfdf1d751e3e
|
3 |
+
size 535727290
|
run-0/checkpoint-6414/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2cf45ff203d40a7da65bf1517c38d5c60b21193bc79079199baa779d11e41481
|
3 |
+
size 14308
|
run-0/checkpoint-6414/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:574602e528e440ef14c64c6444be920beff890fae30c87eae31b39fe165b05ea
|
3 |
+
size 1064
|
run-0/checkpoint-6414/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-0/checkpoint-6414/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-6414/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-0/checkpoint-6414/trainer_state.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6414,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.23,
|
13 |
+
"learning_rate": 9.456689869150003e-05,
|
14 |
+
"loss": 0.6195,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.47,
|
19 |
+
"learning_rate": 8.992671720516538e-05,
|
20 |
+
"loss": 0.6229,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.7,
|
25 |
+
"learning_rate": 8.528653571883074e-05,
|
26 |
+
"loss": 0.6157,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.94,
|
31 |
+
"learning_rate": 8.064635423249609e-05,
|
32 |
+
"loss": 0.6166,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.0,
|
37 |
+
"eval_loss": 0.6419090628623962,
|
38 |
+
"eval_matthews_correlation": 0.0,
|
39 |
+
"eval_runtime": 0.7217,
|
40 |
+
"eval_samples_per_second": 1445.223,
|
41 |
+
"eval_steps_per_second": 91.452,
|
42 |
+
"step": 2138
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.17,
|
46 |
+
"learning_rate": 7.600617274616145e-05,
|
47 |
+
"loss": 0.6097,
|
48 |
+
"step": 2500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.4,
|
52 |
+
"learning_rate": 7.13659912598268e-05,
|
53 |
+
"loss": 0.6152,
|
54 |
+
"step": 3000
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.64,
|
58 |
+
"learning_rate": 6.672580977349217e-05,
|
59 |
+
"loss": 0.6082,
|
60 |
+
"step": 3500
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.87,
|
64 |
+
"learning_rate": 6.208562828715752e-05,
|
65 |
+
"loss": 0.6177,
|
66 |
+
"step": 4000
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 2.0,
|
70 |
+
"eval_loss": 0.6392126083374023,
|
71 |
+
"eval_matthews_correlation": 0.0,
|
72 |
+
"eval_runtime": 0.7452,
|
73 |
+
"eval_samples_per_second": 1399.645,
|
74 |
+
"eval_steps_per_second": 88.568,
|
75 |
+
"step": 4276
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.1,
|
79 |
+
"learning_rate": 5.7445446800822885e-05,
|
80 |
+
"loss": 0.6101,
|
81 |
+
"step": 4500
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.34,
|
85 |
+
"learning_rate": 5.2805265314488234e-05,
|
86 |
+
"loss": 0.6274,
|
87 |
+
"step": 5000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.57,
|
91 |
+
"learning_rate": 4.81650838281536e-05,
|
92 |
+
"loss": 0.6133,
|
93 |
+
"step": 5500
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.81,
|
97 |
+
"learning_rate": 4.352490234181895e-05,
|
98 |
+
"loss": 0.5974,
|
99 |
+
"step": 6000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 3.0,
|
103 |
+
"eval_loss": 0.6237232089042664,
|
104 |
+
"eval_matthews_correlation": 0.0,
|
105 |
+
"eval_runtime": 0.757,
|
106 |
+
"eval_samples_per_second": 1377.809,
|
107 |
+
"eval_steps_per_second": 87.186,
|
108 |
+
"step": 6414
|
109 |
+
}
|
110 |
+
],
|
111 |
+
"logging_steps": 500,
|
112 |
+
"max_steps": 10690,
|
113 |
+
"num_input_tokens_seen": 0,
|
114 |
+
"num_train_epochs": 5,
|
115 |
+
"save_steps": 500,
|
116 |
+
"total_flos": 97840368902244.0,
|
117 |
+
"train_batch_size": 4,
|
118 |
+
"trial_name": null,
|
119 |
+
"trial_params": {
|
120 |
+
"learning_rate": 9.920708017783467e-05,
|
121 |
+
"num_train_epochs": 5,
|
122 |
+
"per_device_train_batch_size": 4,
|
123 |
+
"seed": 31
|
124 |
+
}
|
125 |
+
}
|
run-0/checkpoint-6414/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c864ad0b0686dfaa2454427080519f24d7ce414d236604b49409835d4e23b3cb
|
3 |
+
size 4792
|
run-0/checkpoint-6414/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-8552/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": "4.36.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-0/checkpoint-8552/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90c3391f2aea2542cc44981721756eed910903e9da44116fd3f1de2926ff6e6f
|
3 |
+
size 267832560
|
run-0/checkpoint-8552/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:303bb1dee8f3c624330d4e45174e9beab17ea9448d6d5d6a67e435b23058cccc
|
3 |
+
size 535727290
|
run-0/checkpoint-8552/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68abdd6c7ec4be76c8ac7ae5566ae833dd284ed9158ed288de43cfeb71a64af4
|
3 |
+
size 14308
|
run-0/checkpoint-8552/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22f8d6941a227700968e85a611fe68ce9c5f665293094020803454a3ea01f306
|
3 |
+
size 1064
|
run-0/checkpoint-8552/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-0/checkpoint-8552/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-8552/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-0/checkpoint-8552/trainer_state.json
ADDED
@@ -0,0 +1,164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.0,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-2138",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8552,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.23,
|
13 |
+
"learning_rate": 9.456689869150003e-05,
|
14 |
+
"loss": 0.6195,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.47,
|
19 |
+
"learning_rate": 8.992671720516538e-05,
|
20 |
+
"loss": 0.6229,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.7,
|
25 |
+
"learning_rate": 8.528653571883074e-05,
|
26 |
+
"loss": 0.6157,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.94,
|
31 |
+
"learning_rate": 8.064635423249609e-05,
|
32 |
+
"loss": 0.6166,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.0,
|
37 |
+
"eval_loss": 0.6419090628623962,
|
38 |
+
"eval_matthews_correlation": 0.0,
|
39 |
+
"eval_runtime": 0.7217,
|
40 |
+
"eval_samples_per_second": 1445.223,
|
41 |
+
"eval_steps_per_second": 91.452,
|
42 |
+
"step": 2138
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 1.17,
|
46 |
+
"learning_rate": 7.600617274616145e-05,
|
47 |
+
"loss": 0.6097,
|
48 |
+
"step": 2500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.4,
|
52 |
+
"learning_rate": 7.13659912598268e-05,
|
53 |
+
"loss": 0.6152,
|
54 |
+
"step": 3000
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.64,
|
58 |
+
"learning_rate": 6.672580977349217e-05,
|
59 |
+
"loss": 0.6082,
|
60 |
+
"step": 3500
|
61 |
+
},
|
62 |
+
{
|
63 |
+
"epoch": 1.87,
|
64 |
+
"learning_rate": 6.208562828715752e-05,
|
65 |
+
"loss": 0.6177,
|
66 |
+
"step": 4000
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 2.0,
|
70 |
+
"eval_loss": 0.6392126083374023,
|
71 |
+
"eval_matthews_correlation": 0.0,
|
72 |
+
"eval_runtime": 0.7452,
|
73 |
+
"eval_samples_per_second": 1399.645,
|
74 |
+
"eval_steps_per_second": 88.568,
|
75 |
+
"step": 4276
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.1,
|
79 |
+
"learning_rate": 5.7445446800822885e-05,
|
80 |
+
"loss": 0.6101,
|
81 |
+
"step": 4500
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.34,
|
85 |
+
"learning_rate": 5.2805265314488234e-05,
|
86 |
+
"loss": 0.6274,
|
87 |
+
"step": 5000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 2.57,
|
91 |
+
"learning_rate": 4.81650838281536e-05,
|
92 |
+
"loss": 0.6133,
|
93 |
+
"step": 5500
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.81,
|
97 |
+
"learning_rate": 4.352490234181895e-05,
|
98 |
+
"loss": 0.5974,
|
99 |
+
"step": 6000
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 3.0,
|
103 |
+
"eval_loss": 0.6237232089042664,
|
104 |
+
"eval_matthews_correlation": 0.0,
|
105 |
+
"eval_runtime": 0.757,
|
106 |
+
"eval_samples_per_second": 1377.809,
|
107 |
+
"eval_steps_per_second": 87.186,
|
108 |
+
"step": 6414
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 3.04,
|
112 |
+
"learning_rate": 3.888472085548431e-05,
|
113 |
+
"loss": 0.608,
|
114 |
+
"step": 6500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.27,
|
118 |
+
"learning_rate": 3.4244539369149664e-05,
|
119 |
+
"loss": 0.6216,
|
120 |
+
"step": 7000
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 3.51,
|
124 |
+
"learning_rate": 2.960435788281502e-05,
|
125 |
+
"loss": 0.6076,
|
126 |
+
"step": 7500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 3.74,
|
130 |
+
"learning_rate": 2.4964176396480383e-05,
|
131 |
+
"loss": 0.6187,
|
132 |
+
"step": 8000
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 3.98,
|
136 |
+
"learning_rate": 2.0323994910145736e-05,
|
137 |
+
"loss": 0.5935,
|
138 |
+
"step": 8500
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 4.0,
|
142 |
+
"eval_loss": 0.6235376000404358,
|
143 |
+
"eval_matthews_correlation": 0.0,
|
144 |
+
"eval_runtime": 0.7514,
|
145 |
+
"eval_samples_per_second": 1388.129,
|
146 |
+
"eval_steps_per_second": 87.839,
|
147 |
+
"step": 8552
|
148 |
+
}
|
149 |
+
],
|
150 |
+
"logging_steps": 500,
|
151 |
+
"max_steps": 10690,
|
152 |
+
"num_input_tokens_seen": 0,
|
153 |
+
"num_train_epochs": 5,
|
154 |
+
"save_steps": 500,
|
155 |
+
"total_flos": 138735797356464.0,
|
156 |
+
"train_batch_size": 4,
|
157 |
+
"trial_name": null,
|
158 |
+
"trial_params": {
|
159 |
+
"learning_rate": 9.920708017783467e-05,
|
160 |
+
"num_train_epochs": 5,
|
161 |
+
"per_device_train_batch_size": 4,
|
162 |
+
"seed": 31
|
163 |
+
}
|
164 |
+
}
|
run-0/checkpoint-8552/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c864ad0b0686dfaa2454427080519f24d7ce414d236604b49409835d4e23b3cb
|
3 |
+
size 4792
|
run-0/checkpoint-8552/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Dec23_01-55-51_48296f50e732/events.out.tfevents.1703297718.48296f50e732.508.1
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 sha256:8bda058147eca9d75f0a91663585b9aa2040dcddf1bc2d8d316ae5d69a5c69ea
|
3 |
+
size 9671
|