Training in progress, epoch 1

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "none",
     "1": "like",
@@ -23,7 +22,6 @@
     "9": "meme"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "express_abashed": "10",
     "express_sad": "7",
@@ -37,17 +35,17 @@
     "tease": "8",
     "unlike": "2"
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.27.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

logs/1686801026.404191/events.out.tfevents.1686801026.ls.3972074.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bceeded2f3cc2c22040449bcc63184fa4f013a75257e040e4edd1037c379712e
+size 5791

logs/events.out.tfevents.1686801026.ls.3972074.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53cd8c3f5c180664aa990e93928bb3977d60ae745795dd953828bd0b16baf501
+size 4808

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e06cceef3eefe5e21831011c8afabb789e5584ff3feccfa1c6b5c87067e09b5
-size 438035573
+oid sha256:408571547fd9b95d791961eea5cd4b63ca25fb0aa8621ec82223d02f0a42a012
+size 267883181

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2006d2b8b6d65831100ae61207fc0c767eab5baf2f7791488cb5c789b93cf22d
+oid sha256:758effd6e8891c593a864281f10a42e9c315404096144e88f495c543577d6278
 size 3579