Training in progress, epoch 1

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "google/electra-small-discriminator",
+  "_name_or_path": "distilbert/distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "ElectraForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "embedding_size": 128,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 256,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "sadness",
     "1": "joy",
@@ -18,7 +17,6 @@
     "5": "surprise"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1024,
   "label2id": {
     "anger": 3,
     "fear": 4,
@@ -27,21 +25,17 @@
     "sadness": 0,
     "surprise": 5
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "electra",
-  "num_attention_heads": 4,
-  "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",
-  "summary_activation": "gelu",
-  "summary_last_dropout": 0.1,
-  "summary_type": "first",
-  "summary_use_proj": true,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e57e6c9ac9d8cabe61f720f1ddaae1d7debeea0ea4f3f64041aab0f872d50c
-size 54225312
+oid sha256:ac73e1fb62549e23d69e6463798f4788cce7fa580e6bfdbe128d17c4608e7737
+size 267844872

runs/Jul02_20-19-20_0929e644167e/events.out.tfevents.1719951561.0929e644167e.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31035645f096239c2bf13d881fd4f722e5656b581b6a9d2ae6d1343fede94534
+size 9017

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

tokenizer_config.json

@@ -50,6 +50,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "ElectraTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5936c7e90a2a1c5800979b1697405f0c987b80b53f34faaa703d416e356cd456
+oid sha256:c7bfc3b65f08b2ab169c7d49b1633caf814450b8d01d87ecbabeeae7d1cfcfe2
 size 5112