Training in progress, epoch 5, checkpoint

last-checkpoint/config.json

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

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172a879e54f0613ed34fc2ebe311f2f27a68a3f88d233f7000673e5598a77685
+oid sha256:a6f13d3f381449f8d84b7ca05fb821a8b2c0861629beaa791e6c2b5fc00bbb5d
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0385300931157697e4a915b5ce3364c3ef452b5cc6f19883fa9a9bcbdfdaf3b4
+oid sha256:9765040586104af3a74cdbea9cc7074b0e48ef0d1226c3c15c17be1de83b9f59
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b2cbbcfce68a465b5dc9649714636223f26c4334afe4a2b30c904f877d83a7
+oid sha256:675b9a4f8cd0e254dcba3b5459763afcac5d970080440d891cee0ad59e24dfb1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2410c1bb6e04ddda81f1a5814723f61652cb286cac246e7b64a7b46322f8b053
+oid sha256:74a0adf096c9eebfe9a2fa6c4d4fa6dd5ed912c3085653d4e028c18b90b90dc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6361710372570955,
   "best_model_checkpoint": "training_dir/checkpoint-250",
-  "epoch": 3.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 375,
+  "global_step": 625,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,12 +64,50 @@
       "eval_samples_per_second": 79.297,
       "eval_steps_per_second": 9.912,
       "step": 375
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 27.72207260131836,
+      "learning_rate": 0.0001,
+      "loss": 0.2795,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.611451048951049,
+      "eval_f1": 0.5839059582567918,
+      "eval_loss": 1.4940129518508911,
+      "eval_precision": 0.6264845385709801,
+      "eval_recall": 0.611451048951049,
+      "eval_runtime": 26.4977,
+      "eval_samples_per_second": 86.347,
+      "eval_steps_per_second": 10.793,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.975765705108643,
+      "learning_rate": 5e-05,
+      "loss": 0.2239,
+      "step": 625
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6324300699300699,
+      "eval_f1": 0.6186338450685905,
+      "eval_loss": 1.4131898880004883,
+      "eval_precision": 0.657121853967928,
+      "eval_recall": 0.6324300699300699,
+      "eval_runtime": 26.1975,
+      "eval_samples_per_second": 87.337,
+      "eval_steps_per_second": 10.917,
+      "step": 625
     }
   ],
   "logging_steps": 500,
-  "max_steps": 375,
+  "max_steps": 750,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 6,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -78,12 +116,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 611637724728000.0,
+  "total_flos": 1019396207880000.0,
   "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 sha256:2e12f88c03a5bd8b8e87382f55cb509de4b19cb32f104c0c58580a43586af693
+oid sha256:fc57af78e6fe472d6ff8fcdc48d3f980e6db66111852185ec17fc1a8cd98a77e
 size 5176