Training in progress, step 500
Browse files- config.json +10 -1
- model.safetensors +2 -2
- runs/May21_16-11-27_dgx-2.eden/events.out.tfevents.1716300688.dgx-2.eden.553646.0 +3 -0
- tokenizer.json +3 -12
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "FacebookAI/roberta-base",
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"bos_token_id": 0,
|
|
@@ -10,8 +10,16 @@
|
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"intermediate_size": 3072,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
"layer_norm_eps": 1e-05,
|
| 16 |
"max_position_embeddings": 514,
|
| 17 |
"model_type": "roberta",
|
|
@@ -19,6 +27,7 @@
|
|
| 19 |
"num_hidden_layers": 12,
|
| 20 |
"pad_token_id": 1,
|
| 21 |
"position_embedding_type": "absolute",
|
|
|
|
| 22 |
"torch_dtype": "float32",
|
| 23 |
"transformers_version": "4.40.0",
|
| 24 |
"type_vocab_size": 1,
|
|
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "FacebookAI/roberta-base",
|
| 3 |
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"bos_token_id": 0,
|
|
|
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "NEGATIVE",
|
| 15 |
+
"1": "POSITIVE"
|
| 16 |
+
},
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"NEGATIVE": 0,
|
| 21 |
+
"POSITIVE": 1
|
| 22 |
+
},
|
| 23 |
"layer_norm_eps": 1e-05,
|
| 24 |
"max_position_embeddings": 514,
|
| 25 |
"model_type": "roberta",
|
|
|
|
| 27 |
"num_hidden_layers": 12,
|
| 28 |
"pad_token_id": 1,
|
| 29 |
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
"torch_dtype": "float32",
|
| 32 |
"transformers_version": "4.40.0",
|
| 33 |
"type_vocab_size": 1,
|
model.safetensors
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 sha256:54bb5e1d9e9afeaad00d9e2a17e5a51522fa4c5572b3930c2acd08237b4de5ad
|
| 3 |
+
size 498612824
|
runs/May21_16-11-27_dgx-2.eden/events.out.tfevents.1716300688.dgx-2.eden.553646.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5492b9e9543718540ab474df23fc307f32876aa9548d07dcf8154d8acd152875
|
| 3 |
+
size 5052
|
tokenizer.json
CHANGED
|
@@ -2,20 +2,11 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
-
"strategy": "
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
-
"padding":
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 384
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 1,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "<pad>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
| 12 |
"id": 0,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66b0481d86dcc4d35e7d4801f8fb454806abc188ea6835363d04b8f91ad10e78
|
| 3 |
size 4984
|