Training in progress, epoch 1
Browse files- config.json +4 -6
- model.safetensors +1 -1
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/bart-base",
|
| 3 |
"activation_dropout": 0.1,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"add_bias_logits": false,
|
|
@@ -18,13 +17,12 @@
|
|
| 18 |
"decoder_layers": 6,
|
| 19 |
"decoder_start_token_id": 2,
|
| 20 |
"dropout": 0.1,
|
| 21 |
-
"early_stopping":
|
| 22 |
"encoder_attention_heads": 12,
|
| 23 |
"encoder_ffn_dim": 3072,
|
| 24 |
"encoder_layerdrop": 0.0,
|
| 25 |
"encoder_layers": 6,
|
| 26 |
"eos_token_id": 2,
|
| 27 |
-
"forced_bos_token_id": 0,
|
| 28 |
"forced_eos_token_id": 2,
|
| 29 |
"gradient_checkpointing": false,
|
| 30 |
"id2label": {
|
|
@@ -41,10 +39,10 @@
|
|
| 41 |
},
|
| 42 |
"max_position_embeddings": 1024,
|
| 43 |
"model_type": "bart",
|
| 44 |
-
"no_repeat_ngram_size":
|
| 45 |
"normalize_before": false,
|
| 46 |
"normalize_embedding": true,
|
| 47 |
-
"num_beams":
|
| 48 |
"num_hidden_layers": 6,
|
| 49 |
"pad_token_id": 1,
|
| 50 |
"scale_embedding": false,
|
|
@@ -69,7 +67,7 @@
|
|
| 69 |
}
|
| 70 |
},
|
| 71 |
"torch_dtype": "float32",
|
| 72 |
-
"transformers_version": "4.
|
| 73 |
"use_cache": true,
|
| 74 |
"vocab_size": 50265
|
| 75 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_dropout": 0.1,
|
| 3 |
"activation_function": "gelu",
|
| 4 |
"add_bias_logits": false,
|
|
|
|
| 17 |
"decoder_layers": 6,
|
| 18 |
"decoder_start_token_id": 2,
|
| 19 |
"dropout": 0.1,
|
| 20 |
+
"early_stopping": null,
|
| 21 |
"encoder_attention_heads": 12,
|
| 22 |
"encoder_ffn_dim": 3072,
|
| 23 |
"encoder_layerdrop": 0.0,
|
| 24 |
"encoder_layers": 6,
|
| 25 |
"eos_token_id": 2,
|
|
|
|
| 26 |
"forced_eos_token_id": 2,
|
| 27 |
"gradient_checkpointing": false,
|
| 28 |
"id2label": {
|
|
|
|
| 39 |
},
|
| 40 |
"max_position_embeddings": 1024,
|
| 41 |
"model_type": "bart",
|
| 42 |
+
"no_repeat_ngram_size": null,
|
| 43 |
"normalize_before": false,
|
| 44 |
"normalize_embedding": true,
|
| 45 |
+
"num_beams": null,
|
| 46 |
"num_hidden_layers": 6,
|
| 47 |
"pad_token_id": 1,
|
| 48 |
"scale_embedding": false,
|
|
|
|
| 67 |
}
|
| 68 |
},
|
| 69 |
"torch_dtype": "float32",
|
| 70 |
+
"transformers_version": "4.52.4",
|
| 71 |
"use_cache": true,
|
| 72 |
"vocab_size": 50265
|
| 73 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557912620
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e023031dc8470c7ab78b849c436def0179130a6127ace0f24b4442a93242b5b9
|
| 3 |
size 557912620
|
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:d497cf064d1bba9169e44216fbf12728be037d0bc15fe7ea5fc2b5e0ec83e5fe
|
| 3 |
+
size 5304
|