Training in progress, epoch 1
Browse files- config.json +91 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "urduhack/roberta-urdu-small",
|
| 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 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": 0,
|
| 16 |
+
"1": 1,
|
| 17 |
+
"2": 2,
|
| 18 |
+
"3": 3,
|
| 19 |
+
"4": 4,
|
| 20 |
+
"5": 5,
|
| 21 |
+
"6": 6,
|
| 22 |
+
"7": 7,
|
| 23 |
+
"8": 8,
|
| 24 |
+
"9": 9,
|
| 25 |
+
"10": 10,
|
| 26 |
+
"11": 11,
|
| 27 |
+
"12": 12,
|
| 28 |
+
"13": 13,
|
| 29 |
+
"14": 14,
|
| 30 |
+
"15": 15,
|
| 31 |
+
"16": 16,
|
| 32 |
+
"17": 17,
|
| 33 |
+
"18": 18,
|
| 34 |
+
"19": 19,
|
| 35 |
+
"20": 20,
|
| 36 |
+
"21": 21,
|
| 37 |
+
"22": 22,
|
| 38 |
+
"23": 23,
|
| 39 |
+
"24": 24,
|
| 40 |
+
"25": 25,
|
| 41 |
+
"26": 26,
|
| 42 |
+
"27": 27,
|
| 43 |
+
"28": 28,
|
| 44 |
+
"29": 29,
|
| 45 |
+
"30": 30,
|
| 46 |
+
"31": 31,
|
| 47 |
+
"32": 32,
|
| 48 |
+
"33": 33,
|
| 49 |
+
"34": 34,
|
| 50 |
+
"35": 35,
|
| 51 |
+
"36": 36,
|
| 52 |
+
"37": 37,
|
| 53 |
+
"38": 38,
|
| 54 |
+
"39": 39,
|
| 55 |
+
"40": 40,
|
| 56 |
+
"41": 41,
|
| 57 |
+
"42": 42,
|
| 58 |
+
"43": 43,
|
| 59 |
+
"44": 44,
|
| 60 |
+
"45": 45,
|
| 61 |
+
"46": 46,
|
| 62 |
+
"47": 47,
|
| 63 |
+
"48": 48,
|
| 64 |
+
"49": 49,
|
| 65 |
+
"50": 50,
|
| 66 |
+
"51": 51,
|
| 67 |
+
"52": 52,
|
| 68 |
+
"53": 53,
|
| 69 |
+
"54": 54,
|
| 70 |
+
"55": 55,
|
| 71 |
+
"56": 56,
|
| 72 |
+
"57": 57,
|
| 73 |
+
"58": 58,
|
| 74 |
+
"59": 59
|
| 75 |
+
},
|
| 76 |
+
"initializer_range": 0.02,
|
| 77 |
+
"intermediate_size": 3072,
|
| 78 |
+
"layer_norm_eps": 1e-05,
|
| 79 |
+
"max_position_embeddings": 514,
|
| 80 |
+
"model_type": "roberta",
|
| 81 |
+
"num_attention_heads": 12,
|
| 82 |
+
"num_hidden_layers": 12,
|
| 83 |
+
"pad_token_id": 1,
|
| 84 |
+
"position_embedding_type": "absolute",
|
| 85 |
+
"problem_type": "single_label_classification",
|
| 86 |
+
"torch_dtype": "float32",
|
| 87 |
+
"transformers_version": "4.32.1",
|
| 88 |
+
"type_vocab_size": 1,
|
| 89 |
+
"use_cache": true,
|
| 90 |
+
"vocab_size": 52000
|
| 91 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:300deb20653b5ea880100093ad6239ee8d62c3fe0887d696e747b6de3a0f0ed6
|
| 3 |
+
size 504165937
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9de645cf23f3e7a0af48661ff28e384c5b6c60fdc7bf6fe72421a4269203759
|
| 3 |
+
size 4091
|