Training in progress, step 50

best_trial.txt

@@ -0,0 +1 @@
+BestRun(run_id='17', objective=0.33777202905463155, hyperparameters={'learning_rate': 0.0003735194908471509, 'weight_decay': 0.020625116983982793, 'gradient_accumulation_steps': 32, 'lr_scheduler_type': 'cosine'})

config.json

@@ -9,13 +9,13 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 312,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 1200,
+  "intermediate_size": 3072,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 12,
+  "num_attention_heads": 16,
   "num_hidden_layers": 4,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01cd9a9a4941c99c3d72da97df4ee84df7ab0673cc805b283991fd62001a39c2
-size 82272516
+oid sha256:be6b8e9b28bf7e68ae6e467ad3485bfa72abc9c78211079747a22a28d62ddec5
+size 380407940

runs/Feb14_00-12-10_monica.sm.unibocconi.it/1676330009.9275696/events.out.tfevents.1676330009.monica.sm.unibocconi.it.4164817.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b7770176617640b37e17b11de20fd99eac2847fce76ae3a6fe600ff73a6d8df
+size 5587

runs/Feb14_00-12-10_monica.sm.unibocconi.it/events.out.tfevents.1676330009.monica.sm.unibocconi.it.4164817.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb5583e5c5463bc8e2c4b7de975e2ce29e6a044b3476918fe3f8fbeed1ab2165
+size 4964

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c62fd1ba279015e3d3e33ceba84ad3728b9cc1372c29782ec766a7ee20d5a050
-size 3439
+oid sha256:a554cfbb97467f4b15be7f79c1c2ce3b4bc1fcf7e924cc7468efcd250919f2f1
+size 3503