Training in progress, step 60
Browse files- config.json +3 -8
- pytorch_model.bin +2 -2
- runs/Apr13_12-42-06_rogue/events.out.tfevents.1681414934.rogue.2948899.0 +2 -2
- runs/Apr13_18-23-53_rogue/1681435442.6428072/events.out.tfevents.1681435442.rogue.3067847.1 +3 -0
- runs/Apr13_18-23-53_rogue/events.out.tfevents.1681435442.rogue.3067847.0 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
@@ -87,7 +87,7 @@
|
|
87 |
},
|
88 |
"decoder_start_token_id": 101,
|
89 |
"encoder": {
|
90 |
-
"_name_or_path": "",
|
91 |
"add_cross_attention": false,
|
92 |
"architectures": [
|
93 |
"BertForMaskedLM"
|
@@ -127,12 +127,10 @@
|
|
127 |
},
|
128 |
"layer_norm_eps": 1e-12,
|
129 |
"length_penalty": 1.0,
|
130 |
-
"loss_func": "mse",
|
131 |
-
"margin": null,
|
132 |
"max_length": 20,
|
133 |
"max_position_embeddings": 512,
|
134 |
"min_length": 0,
|
135 |
-
"model_type": "
|
136 |
"no_repeat_ngram_size": 0,
|
137 |
"num_attention_heads": 12,
|
138 |
"num_beam_groups": 1,
|
@@ -145,16 +143,13 @@
|
|
145 |
"pad_token_id": 0,
|
146 |
"position_embedding_type": "absolute",
|
147 |
"prefix": null,
|
148 |
-
"problem_type":
|
149 |
"pruned_heads": {},
|
150 |
"remove_invalid_values": false,
|
151 |
"repetition_penalty": 1.0,
|
152 |
"return_dict": true,
|
153 |
"return_dict_in_generate": false,
|
154 |
-
"rule_sentence_encoding": "cls",
|
155 |
"sep_token_id": null,
|
156 |
-
"spec_dropout": 0.1,
|
157 |
-
"spec_encoding": null,
|
158 |
"suppress_tokens": null,
|
159 |
"task_specific_params": null,
|
160 |
"temperature": 1.0,
|
|
|
87 |
},
|
88 |
"decoder_start_token_id": 101,
|
89 |
"encoder": {
|
90 |
+
"_name_or_path": "bert-base-uncased",
|
91 |
"add_cross_attention": false,
|
92 |
"architectures": [
|
93 |
"BertForMaskedLM"
|
|
|
127 |
},
|
128 |
"layer_norm_eps": 1e-12,
|
129 |
"length_penalty": 1.0,
|
|
|
|
|
130 |
"max_length": 20,
|
131 |
"max_position_embeddings": 512,
|
132 |
"min_length": 0,
|
133 |
+
"model_type": "bert",
|
134 |
"no_repeat_ngram_size": 0,
|
135 |
"num_attention_heads": 12,
|
136 |
"num_beam_groups": 1,
|
|
|
143 |
"pad_token_id": 0,
|
144 |
"position_embedding_type": "absolute",
|
145 |
"prefix": null,
|
146 |
+
"problem_type": null,
|
147 |
"pruned_heads": {},
|
148 |
"remove_invalid_values": false,
|
149 |
"repetition_penalty": 1.0,
|
150 |
"return_dict": true,
|
151 |
"return_dict_in_generate": false,
|
|
|
152 |
"sep_token_id": null,
|
|
|
|
|
153 |
"suppress_tokens": null,
|
154 |
"task_specific_params": null,
|
155 |
"temperature": 1.0,
|
pytorch_model.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 sha256:46ef316068e1c1aa8d3f5d94da794c370f535a8eb1b76468acf2e8da93cf8225
|
3 |
+
size 989647929
|
runs/Apr13_12-42-06_rogue/events.out.tfevents.1681414934.rogue.2948899.0
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 sha256:4cde044b01f3706d556e226f7f6382eb5a3c96a4f347ec16cde0c82779242612
|
3 |
+
size 38814
|
runs/Apr13_18-23-53_rogue/1681435442.6428072/events.out.tfevents.1681435442.rogue.3067847.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:942de8832786ace06827acf70ae1f7a1d32450cd2f9ff426ad444a82d864dda1
|
3 |
+
size 5857
|
runs/Apr13_18-23-53_rogue/events.out.tfevents.1681435442.rogue.3067847.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:593d63ebb289f74053621e4f0f73cb1d44a8ae6e9c3ad5489f5d3e195232f776
|
3 |
+
size 9281
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3643
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:907c940ac85beec359b96c55bdcda9ec54fef07e9960f33b635fca1532347bdf
|
3 |
size 3643
|