Training in progress, epoch 4, checkpoint

last-checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
+  "_name_or_path": "Francesco0101/FRABERT-distilbert-base-uncased-51086",
   "activation": "gelu",
   "architectures": [
     "DistilBertForSequenceClassification"

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f4f42ed8726a01ec1769407ef1ce59631c300e93dc2a837e341dffecd02c17
+oid sha256:c9acbbe59cc669bdd8860b3794df868e64b8903a4b29ed3a4f9607ba004dcb07
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:687fdb80383701a262471eb09c7d2a63664bc1c45e3e06d64da2b2d8a6f07348
+oid sha256:af56ec53953a4ce58073c6101f5d14112919323e7ff06caab1a8bc1ef88a4714
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5829fdfb8ea3cfd8973041e1f4b84b188f3f51504415d377549403e604291433
+oid sha256:fdf0dc39fa720efae5c87e2de3716c48674926551f71a0ba6dd10c6c02d77977
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a69b3a106ff3c8a053e64914963cacbd3b7c2581f1211e4c028a3c55f28ee8e
+oid sha256:9de7e2d35d1ac9cba6b442f08642ba93349bda77fc797f94a4764ad943e52ad2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6955057953127977,
   "best_model_checkpoint": "training_dir/checkpoint-3193",
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 9579,
+  "global_step": 12772,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,12 +64,31 @@
       "eval_samples_per_second": 82.493,
       "eval_steps_per_second": 10.312,
       "step": 9579
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.0213212966918945,
+      "learning_rate": 6.0954502068087814e-05,
+      "loss": 0.2568,
+      "step": 12772
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6853146853146853,
+      "eval_f1": 0.6752368731633129,
+      "eval_loss": 1.3729437589645386,
+      "eval_precision": 0.6983670162522349,
+      "eval_recall": 0.6853146853146853,
+      "eval_runtime": 30.1468,
+      "eval_samples_per_second": 75.895,
+      "eval_steps_per_second": 9.487,
+      "step": 12772
     }
   ],
   "logging_steps": 500,
-  "max_steps": 19158,
+  "max_steps": 31930,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
+  "num_train_epochs": 10,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -83,7 +102,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.000505291334038e+16,
+  "total_flos": 2.6676379106990172e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adc25bad5e22cb00ec67cc5c6a1989c8fa44a7021556e9019cbdec8c4516a3cb
+oid sha256:fb92a7fd44c3795edeffedfd95925fc357be78e9278a301e4f880ffc172a22b1
 size 5176