Training in progress, epoch 2
Browse files- config.json +7 -6
- model.safetensors +1 -1
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -21,8 +21,8 @@
|
|
| 21 |
"hidden_activation": "gelu",
|
| 22 |
"hidden_size": 768,
|
| 23 |
"id2label": {
|
| 24 |
-
"0": "
|
| 25 |
-
"1": "
|
| 26 |
"2": "QUANTITATIVE_KNOWLEDGE",
|
| 27 |
"3": "VISUAL_REASONING"
|
| 28 |
},
|
|
@@ -30,8 +30,8 @@
|
|
| 30 |
"initializer_range": 0.02,
|
| 31 |
"intermediate_size": 1152,
|
| 32 |
"label2id": {
|
| 33 |
-
"COMPREHENSION_KNOWLEDGE": "
|
| 34 |
-
"FLUID_REASONING": "
|
| 35 |
"QUANTITATIVE_KNOWLEDGE": "2",
|
| 36 |
"VISUAL_REASONING": "3"
|
| 37 |
},
|
|
@@ -49,11 +49,12 @@
|
|
| 49 |
"pad_token_id": 50283,
|
| 50 |
"position_embedding_type": "absolute",
|
| 51 |
"problem_type": "single_label_classification",
|
| 52 |
-
"reference_compile":
|
|
|
|
| 53 |
"sep_token_id": 50282,
|
| 54 |
"sparse_pred_ignore_index": -100,
|
| 55 |
"sparse_prediction": false,
|
| 56 |
"torch_dtype": "float32",
|
| 57 |
-
"transformers_version": "4.48.0
|
| 58 |
"vocab_size": 50368
|
| 59 |
}
|
|
|
|
| 21 |
"hidden_activation": "gelu",
|
| 22 |
"hidden_size": 768,
|
| 23 |
"id2label": {
|
| 24 |
+
"0": "FLUID_REASONING",
|
| 25 |
+
"1": "COMPREHENSION_KNOWLEDGE",
|
| 26 |
"2": "QUANTITATIVE_KNOWLEDGE",
|
| 27 |
"3": "VISUAL_REASONING"
|
| 28 |
},
|
|
|
|
| 30 |
"initializer_range": 0.02,
|
| 31 |
"intermediate_size": 1152,
|
| 32 |
"label2id": {
|
| 33 |
+
"COMPREHENSION_KNOWLEDGE": "1",
|
| 34 |
+
"FLUID_REASONING": "0",
|
| 35 |
"QUANTITATIVE_KNOWLEDGE": "2",
|
| 36 |
"VISUAL_REASONING": "3"
|
| 37 |
},
|
|
|
|
| 49 |
"pad_token_id": 50283,
|
| 50 |
"position_embedding_type": "absolute",
|
| 51 |
"problem_type": "single_label_classification",
|
| 52 |
+
"reference_compile": false,
|
| 53 |
+
"repad_logits_with_grad": false,
|
| 54 |
"sep_token_id": 50282,
|
| 55 |
"sparse_pred_ignore_index": -100,
|
| 56 |
"sparse_prediction": false,
|
| 57 |
"torch_dtype": "float32",
|
| 58 |
+
"transformers_version": "4.48.0",
|
| 59 |
"vocab_size": 50368
|
| 60 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 598445936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73090be362f45cb02915d91aa8dbe920053087ea283029c4b3332664e8f81fc2
|
| 3 |
size 598445936
|
training_args.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:c02dfc7b956c7a4c519ba888f79aec6174bdeb90be13637f2740c1ffa344c26d
|
| 3 |
+
size 5368
|