Training in progress, epoch 1, checkpoint

checkpoint-7/config.json

@@ -1,41 +1,33 @@
 {
   "architectures": [
-    "MobileBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "classifier_activation": false,
   "classifier_dropout": null,
-  "embedding_size": 128,
-  "hidden_act": "relu",
-  "hidden_dropout_prob": 0.0,
-  "hidden_size": 512,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
   "id2label": {
-    "LABEL_0": "negative",
-    "LABEL_1": "positive"
+    "0": "negative",
+    "1": "positive"
   },
   "initializer_range": 0.02,
   "intermediate_size": 512,
-  "intra_bottleneck_size": 128,
-  "key_query_shared_bottleneck": true,
   "label2id": {
     "negative": 0,
     "positive": 1
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "mobilebert",
-  "normalization_type": "no_norm",
-  "num_attention_heads": 4,
-  "num_feedforward_networks": 4,
-  "num_hidden_layers": 24,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.51.3",
-  "trigram_input": true,
-  "true_hidden_size": 128,
   "type_vocab_size": 2,
-  "use_bottleneck": true,
-  "use_bottleneck_attention": false,
+  "use_cache": true,
   "vocab_size": 30522
 }

checkpoint-7/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136f376ae8b3568a5384dd2d0ed7746f242fc6bdb65bab79e3e540894d0e4cb4
-size 98470112
+oid sha256:2184a7cc5dbbbcdb1e1a91c486097cc53da6a9c2dc89707d45273cc01936e771
+size 17549312

checkpoint-7/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e821d3bde33cca939b3da702c510b695fac7dea0507bf683139ba8b935bb8e85
-size 197593757
+oid sha256:c6a0e1e832ddc526f7b84ede6014f4111837c3c71cee073c419fef4514d2c230
+size 35123898

checkpoint-7/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85d6eca64aa942b1fb6242ccacdb356b249b16a5213116b7a463df59ba8a0592
+oid sha256:f42508f1fa811c01793b47e142274e8086f1d7bcec910eff64443ea1ee4491a6
 size 14244

checkpoint-7/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 7,
-  "best_metric": 0.30054421768707484,
+  "best_metric": 0.5122424242424242,
   "best_model_checkpoint": "./results\\checkpoint-7",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,12 +11,12 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.47,
-      "eval_f1": 0.30054421768707484,
-      "eval_loss": 385655.125,
-      "eval_runtime": 3.9911,
-      "eval_samples_per_second": 25.055,
-      "eval_steps_per_second": 1.754,
+      "eval_accuracy": 0.52,
+      "eval_f1": 0.5122424242424242,
+      "eval_loss": 0.6942550539970398,
+      "eval_runtime": 0.1652,
+      "eval_samples_per_second": 605.351,
+      "eval_steps_per_second": 42.375,
       "step": 7
     }
   ],
@@ -37,7 +37,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6270852096000.0,
+  "total_flos": 127048704000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

checkpoint-7/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44f69621aecf7a08f867fee0043d9ee8f500abe3775060b6b17f40f3cfc9663f
+oid sha256:861141fd327e8a87b5ad48a55f3c4959aee6676f59daa8e247b802539e325862
 size 5304