Training in progress, step 18000, checkpoint

last-checkpoint/config.json

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

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07394dd2da2fc8953cab465ecc516b2b637a9ad1e5f80b5e3ea2227894fa654a
+oid sha256:8c0993f79e87ceb2f67241551b142860a2ebe82a3edfa67010d613c814739a79
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78de506312ed56afb09869d301b9813ec41093ce0949b835b41413fe2335de94
+oid sha256:9ad6e5d8a61a0cc0c39fe09042ba5a631f10ad06a4c95e1a6007655a5a716fce
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d92adf6dbb6d04b5365a21d7e5c277f9e5493f67b515b76e0f0b04c6e28d7e18
+oid sha256:736c40d0654e0cb3acac2a9532ac7024c7ad4e6f82f18a4d9303901ad5151c42
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efac40282b6ccc72dd2d6d02d04092dc1f619670b356e71b004fd44491288981
+oid sha256:d87e2d34c5e7abb12d8317a9d10122164cc658c9667d977c9f29cf450d2605fe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7260786855980778,
-  "best_model_checkpoint": "training_dir/checkpoint-12000",
-  "epoch": 1.3775564268305605,
+  "best_metric": 0.7293202496323148,
+  "best_model_checkpoint": "training_dir/checkpoint-16000",
+  "epoch": 1.9073858217653914,
   "eval_steps": 1000,
-  "global_step": 13000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -254,6 +254,101 @@
       "eval_samples_per_second": 88.122,
       "eval_steps_per_second": 11.015,
       "step": 13000
+    },
+    {
+      "epoch": 1.4835223058175266,
+      "grad_norm": 19.44073486328125,
+      "learning_rate": 8.56184084372004e-06,
+      "loss": 0.3967,
+      "step": 14000
+    },
+    {
+      "epoch": 1.4835223058175266,
+      "eval_accuracy": 0.7377622377622378,
+      "eval_f1": 0.7275954782820151,
+      "eval_loss": 0.9781323671340942,
+      "eval_precision": 0.7423521044319988,
+      "eval_recall": 0.7377622377622378,
+      "eval_runtime": 29.6474,
+      "eval_samples_per_second": 77.174,
+      "eval_steps_per_second": 9.647,
+      "step": 14000
+    },
+    {
+      "epoch": 1.5894881848044928,
+      "grad_norm": 0.27897197008132935,
+      "learning_rate": 8.45531053584745e-06,
+      "loss": 0.4048,
+      "step": 15000
+    },
+    {
+      "epoch": 1.5894881848044928,
+      "eval_accuracy": 0.7246503496503497,
+      "eval_f1": 0.7134343410409786,
+      "eval_loss": 1.0050002336502075,
+      "eval_precision": 0.7324782904105448,
+      "eval_recall": 0.7246503496503497,
+      "eval_runtime": 28.5313,
+      "eval_samples_per_second": 80.192,
+      "eval_steps_per_second": 10.024,
+      "step": 15000
+    },
+    {
+      "epoch": 1.695454063791459,
+      "grad_norm": 17.813819885253906,
+      "learning_rate": 8.34878022797486e-06,
+      "loss": 0.4002,
+      "step": 16000
+    },
+    {
+      "epoch": 1.695454063791459,
+      "eval_accuracy": 0.7351398601398601,
+      "eval_f1": 0.7293202496323148,
+      "eval_loss": 0.9046709537506104,
+      "eval_precision": 0.7368475219229782,
+      "eval_recall": 0.7351398601398601,
+      "eval_runtime": 29.0485,
+      "eval_samples_per_second": 78.765,
+      "eval_steps_per_second": 9.846,
+      "step": 16000
+    },
+    {
+      "epoch": 1.8014199427784252,
+      "grad_norm": 11.392443656921387,
+      "learning_rate": 8.24224992010227e-06,
+      "loss": 0.3906,
+      "step": 17000
+    },
+    {
+      "epoch": 1.8014199427784252,
+      "eval_accuracy": 0.7312062937062938,
+      "eval_f1": 0.7210893936836806,
+      "eval_loss": 0.9010310769081116,
+      "eval_precision": 0.7345691438075613,
+      "eval_recall": 0.7312062937062938,
+      "eval_runtime": 28.5861,
+      "eval_samples_per_second": 80.039,
+      "eval_steps_per_second": 10.005,
+      "step": 17000
+    },
+    {
+      "epoch": 1.9073858217653914,
+      "grad_norm": 10.869200706481934,
+      "learning_rate": 8.13571961222968e-06,
+      "loss": 0.3847,
+      "step": 18000
+    },
+    {
+      "epoch": 1.9073858217653914,
+      "eval_accuracy": 0.7229020979020979,
+      "eval_f1": 0.7136781919341553,
+      "eval_loss": 0.9686246514320374,
+      "eval_precision": 0.7275042194736051,
+      "eval_recall": 0.7229020979020979,
+      "eval_runtime": 28.6996,
+      "eval_samples_per_second": 79.722,
+      "eval_steps_per_second": 9.965,
+      "step": 18000
     }
   ],
   "logging_steps": 1000,
@@ -273,7 +368,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2625401075755184e+16,
+  "total_flos": 1.7482435911300384e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null