Training in progress, epoch 1
Browse files- config.json +10 -9
- pytorch_model.bin +2 -2
- runs/May10_17-20-18_25056aed8f14/events.out.tfevents.1652203236.25056aed8f14.79.18 +2 -2
- runs/May10_17-20-18_25056aed8f14/events.out.tfevents.1652205267.25056aed8f14.79.20 +3 -0
- runs/May10_17-57-40_25056aed8f14/1652205478.643892/events.out.tfevents.1652205478.25056aed8f14.79.22 +3 -0
- runs/May10_17-57-40_25056aed8f14/events.out.tfevents.1652205478.25056aed8f14.79.21 +3 -0
- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "nreimers/
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
8 |
-
"
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 384,
|
@@ -317,16 +318,16 @@
|
|
317 |
"who_made_you": "96",
|
318 |
"yes": "107"
|
319 |
},
|
320 |
-
"layer_norm_eps": 1e-
|
321 |
-
"max_position_embeddings":
|
322 |
-
"model_type": "
|
323 |
"num_attention_heads": 12,
|
324 |
"num_hidden_layers": 6,
|
325 |
-
"pad_token_id":
|
326 |
"position_embedding_type": "absolute",
|
327 |
"torch_dtype": "float32",
|
328 |
"transformers_version": "4.18.0",
|
329 |
-
"type_vocab_size":
|
330 |
"use_cache": true,
|
331 |
-
"vocab_size":
|
332 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large",
|
3 |
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 384,
|
|
|
318 |
"who_made_you": "96",
|
319 |
"yes": "107"
|
320 |
},
|
321 |
+
"layer_norm_eps": 1e-05,
|
322 |
+
"max_position_embeddings": 514,
|
323 |
+
"model_type": "roberta",
|
324 |
"num_attention_heads": 12,
|
325 |
"num_hidden_layers": 6,
|
326 |
+
"pad_token_id": 1,
|
327 |
"position_embedding_type": "absolute",
|
328 |
"torch_dtype": "float32",
|
329 |
"transformers_version": "4.18.0",
|
330 |
+
"type_vocab_size": 1,
|
331 |
"use_cache": true,
|
332 |
+
"vocab_size": 50265
|
333 |
}
|
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 sha256:092d529c6a847ca9a5464e5b3dc982af6932aa4ddddc27bf7635856362669138
|
3 |
+
size 121451181
|
runs/May10_17-20-18_25056aed8f14/events.out.tfevents.1652203236.25056aed8f14.79.18
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 sha256:74a06912734e721bd3f4e72ce2f8519e93648b1d2ca6401add862e0811278d7f
|
3 |
+
size 17196
|
runs/May10_17-20-18_25056aed8f14/events.out.tfevents.1652205267.25056aed8f14.79.20
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:513362a7f1f831647ba6c1b1296eae30a35d9bcd21d93478a703ec23006577c5
|
3 |
+
size 363
|
runs/May10_17-57-40_25056aed8f14/1652205478.643892/events.out.tfevents.1652205478.25056aed8f14.79.22
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7fbffe082f72180a3c9632583f0f888e6ccae34867a2c97d58a93dab9856748
|
3 |
+
size 4892
|
runs/May10_17-57-40_25056aed8f14/events.out.tfevents.1652205478.25056aed8f14.79.21
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4165284557470d92e2ece352b69c3f64d5aad329ada7676cec08de450e93e86
|
3 |
+
size 11643
|
special_tokens_map.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"unk_token": "
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"
|
|
|
1 |
+
{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "nreimers/MiniLMv2-L6-H384-distilled-from-RoBERTa-Large", "tokenizer_class": "RobertaTokenizer"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3119
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bee2f932ecb41316c0f2c5e0787f86c09746f330486e43479cbf7d58f682d1ad
|
3 |
size 3119
|