zrthxn commited on
Commit
697f2d7
·
0 Parent(s):
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. config.json +34 -0
  3. training_stats.json +1 -0
.gitattributes ADDED
@@ -0,0 +1 @@
 
 
1
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/Users/alisamar/Desktop/grover/.checkpoints/grover",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_ids": 0,
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-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "num_rnn_layer": 1,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "position_embedding_type": "absolute",
24
+ "problem_type": "multi_label_classification",
25
+ "rnn": "lstm",
26
+ "rnn_dropout": 0.0,
27
+ "rnn_hidden": 768,
28
+ "split": 10,
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 609
34
+ }
training_stats.json ADDED
@@ -0,0 +1 @@
 
 
1
+ [{"epoch": 1, "Training Loss": 0.2313814305984054, "Valid. Loss": 0.22472524732351304, "Valid. Metrics": {"0": {"precision": 0.9265734265734266, "recall": 0.916955017301038, "f1-score": 0.9217391304347826, "support": 289.0}, "1": {"precision": 0.9209621993127147, "recall": 0.9273356401384083, "f1-score": 0.9241379310344827, "support": 289.0}, "micro avg": {"precision": 0.9237435008665511, "recall": 0.9221453287197232, "f1-score": 0.922943722943723, "support": 578.0}, "macro avg": {"precision": 0.9237678129430706, "recall": 0.9221453287197232, "f1-score": 0.9229385307346327, "support": 578.0}, "weighted avg": {"precision": 0.9237678129430708, "recall": 0.9221453287197232, "f1-score": 0.9229385307346327, "support": 578.0}, "samples avg": {"precision": 0.9221453287197232, "recall": 0.9221453287197232, "f1-score": 0.9221453287197232, "support": 578.0}}, "Training Time": "0:15:02", "Validation Time": "0:00:03"}, {"epoch": 2, "Training Loss": 0.12850270645455275, "Valid. Loss": 0.34306993175297973, "Valid. Metrics": {"0": {"precision": 0.9588014981273408, "recall": 0.8858131487889274, "f1-score": 0.920863309352518, "support": 289.0}, "1": {"precision": 0.8938906752411575, "recall": 0.9619377162629758, "f1-score": 0.9266666666666666, "support": 289.0}, "micro avg": {"precision": 0.9238754325259516, "recall": 0.9238754325259516, "f1-score": 0.9238754325259516, "support": 578.0}, "macro avg": {"precision": 0.9263460866842492, "recall": 0.9238754325259515, "f1-score": 0.9237649880095924, "support": 578.0}, "weighted avg": {"precision": 0.9263460866842491, "recall": 0.9238754325259516, "f1-score": 0.9237649880095923, "support": 578.0}, "samples avg": {"precision": 0.9238754325259516, "recall": 0.9238754325259516, "f1-score": 0.9238754325259516, "support": 578.0}}, "Training Time": "0:14:57", "Validation Time": "0:00:03"}, {"epoch": 3, "Training Loss": 0.07388239269117927, "Valid. Loss": 0.2788318060338497, "Valid. Metrics": {"0": {"precision": 0.928082191780822, "recall": 0.9377162629757786, "f1-score": 0.9328743545611016, "support": 289.0}, "1": {"precision": 0.9370629370629371, "recall": 0.9273356401384083, "f1-score": 0.9321739130434783, "support": 289.0}, "micro avg": {"precision": 0.9325259515570934, "recall": 0.9325259515570934, "f1-score": 0.9325259515570934, "support": 578.0}, "macro avg": {"precision": 0.9325725644218795, "recall": 0.9325259515570934, "f1-score": 0.9325241338022899, "support": 578.0}, "weighted avg": {"precision": 0.9325725644218793, "recall": 0.9325259515570934, "f1-score": 0.93252413380229, "support": 578.0}, "samples avg": {"precision": 0.9325259515570934, "recall": 0.9325259515570934, "f1-score": 0.9325259515570934, "support": 578.0}}, "Training Time": "0:14:58", "Validation Time": "0:00:03"}, {"epoch": 4, "Training Loss": 0.034447011300888966, "Valid. Loss": 0.3008968627639115, "Valid. Metrics": {"0": {"precision": 0.9407665505226481, "recall": 0.9342560553633218, "f1-score": 0.9375, "support": 289.0}, "1": {"precision": 0.9347079037800687, "recall": 0.9411764705882353, "f1-score": 0.9379310344827586, "support": 289.0}, "micro avg": {"precision": 0.9377162629757786, "recall": 0.9377162629757786, "f1-score": 0.9377162629757786, "support": 578.0}, "macro avg": {"precision": 0.9377372271513584, "recall": 0.9377162629757785, "f1-score": 0.9377155172413794, "support": 578.0}, "weighted avg": {"precision": 0.9377372271513584, "recall": 0.9377162629757786, "f1-score": 0.9377155172413794, "support": 578.0}, "samples avg": {"precision": 0.9377162629757786, "recall": 0.9377162629757786, "f1-score": 0.9377162629757786, "support": 578.0}}, "Training Time": "0:14:57", "Validation Time": "0:00:03"}, {"epoch": 5, "Training Loss": 0.013856497977643904, "Valid. Loss": 0.3578405526286224, "Valid. Metrics": {"0": {"precision": 0.9498207885304659, "recall": 0.916955017301038, "f1-score": 0.9330985915492958, "support": 289.0}, "1": {"precision": 0.9228187919463087, "recall": 0.9515570934256056, "f1-score": 0.9369676320272572, "support": 289.0}, "micro avg": {"precision": 0.9358752166377816, "recall": 0.9342560553633218, "f1-score": 0.935064935064935, "support": 578.0}, "macro avg": {"precision": 0.9363197902383873, "recall": 0.9342560553633218, "f1-score": 0.9350331117882764, "support": 578.0}, "weighted avg": {"precision": 0.9363197902383873, "recall": 0.9342560553633218, "f1-score": 0.9350331117882764, "support": 578.0}, "samples avg": {"precision": 0.9342560553633218, "recall": 0.9342560553633218, "f1-score": 0.9342560553633218, "support": 578.0}}, "Training Time": "0:14:57", "Validation Time": "0:00:03"}]