Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:474b993621dcf0bddfe1abd8c429bde1a78e3cd28d23183ebdc1cfb5f798f9fb
+oid sha256:3a65f77de1eb62cec0f629cb19463346793fec80e1454deff0266de4d5ef2c55
 size 430935892

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3373cbddd58f49d7ee1bee615e1e87f0d764904fd125e2f94c5c1ca6b82737
+oid sha256:e1381267deba7fff5c23ccbe019de55935969197d9c8386d0b1e2e7bdb75daf0
 size 861991482

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8904498d0ea4278d68a668aa846964ce80df1ff9136c37871ee274669dc57f
+oid sha256:7d79b618e9c3de1ee0de1ae85c648b3b80a40cb85b291159a42ac076a903c57e
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9de563a795946068ee2943aa801ab2757eb65d8f36f8743830ce3a1cd4b5ce
+oid sha256:0e65eb7d8463989e20eaa15c5cb44e7258208d340b08446887fbe12fa3673349
 size 1064

trainer_state.json

@@ -1,100 +1,107 @@
 {
-  "best_global_step": 609,
-  "best_metric": 0.010163484141230583,
-  "best_model_checkpoint": "projects/PetBERT_annonymisation/data/augment/arrow_4/checkpoint-609",
+  "best_global_step": 1376,
+  "best_metric": 0.012005209922790527,
+  "best_model_checkpoint": "projects/PetHarbor/data/augment/arrow_v5/model/checkpoint-1376",
   "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 2436,
+  "global_step": 2752,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0,
-      "eval_f1": 0.0125291815966952,
-      "eval_loss": 2.3777594566345215,
-      "eval_precision": 0.09023052095482559,
-      "eval_recall": 0.0881670915774344,
-      "eval_runtime": 12.1157,
-      "eval_samples_per_second": 136.764,
-      "eval_steps_per_second": 4.292,
+      "eval_f1": 0.011655798995725575,
+      "eval_loss": 2.4493634700775146,
+      "eval_precision": 0.09168997185092281,
+      "eval_recall": 0.05262704226436905,
+      "eval_runtime": 12.3437,
+      "eval_samples_per_second": 134.238,
+      "eval_steps_per_second": 4.213,
       "step": 0
     },
     {
-      "epoch": 0.8210180623973727,
-      "grad_norm": 0.28877386450767517,
-      "learning_rate": 4.9959031198686376e-05,
+      "epoch": 0.7267441860465116,
+      "grad_norm": 0.2848288416862488,
+      "learning_rate": 4.996373546511628e-05,
       "loss": 0.0484,
       "step": 500
     },
     {
       "epoch": 1.0,
-      "eval_f1": 0.9208551148897809,
-      "eval_loss": 0.010163484141230583,
-      "eval_precision": 0.9173087088894764,
-      "eval_recall": 0.9271621325936177,
-      "eval_runtime": 12.5384,
-      "eval_samples_per_second": 132.154,
-      "eval_steps_per_second": 4.147,
-      "step": 609
+      "eval_f1": 0.8927075594912149,
+      "eval_loss": 0.013240625150501728,
+      "eval_precision": 0.8758418145856814,
+      "eval_recall": 0.9170635030650058,
+      "eval_runtime": 12.5123,
+      "eval_samples_per_second": 132.429,
+      "eval_steps_per_second": 4.156,
+      "step": 688
     },
     {
-      "epoch": 1.6420361247947455,
-      "grad_norm": 0.3570762574672699,
-      "learning_rate": 4.99179802955665e-05,
-      "loss": 0.0065,
+      "epoch": 1.4534883720930232,
+      "grad_norm": 0.19568854570388794,
+      "learning_rate": 4.992739825581396e-05,
+      "loss": 0.0071,
       "step": 1000
     },
     {
       "epoch": 2.0,
-      "eval_f1": 0.9295632654722351,
-      "eval_loss": 0.010717815719544888,
-      "eval_precision": 0.9179765798631134,
-      "eval_recall": 0.9419352898275708,
-      "eval_runtime": 12.5527,
-      "eval_samples_per_second": 132.004,
-      "eval_steps_per_second": 4.143,
-      "step": 1218
+      "eval_f1": 0.9068541971529176,
+      "eval_loss": 0.012005209922790527,
+      "eval_precision": 0.9104600842733132,
+      "eval_recall": 0.9040660692132211,
+      "eval_runtime": 12.5166,
+      "eval_samples_per_second": 132.384,
+      "eval_steps_per_second": 4.154,
+      "step": 1376
     },
     {
-      "epoch": 2.4630541871921183,
-      "grad_norm": 0.006953490898013115,
-      "learning_rate": 4.987692939244664e-05,
-      "loss": 0.0033,
+      "epoch": 2.1802325581395348,
+      "grad_norm": 0.035110026597976685,
+      "learning_rate": 4.989106104651163e-05,
+      "loss": 0.0038,
       "step": 1500
     },
+    {
+      "epoch": 2.9069767441860463,
+      "grad_norm": 0.008144177496433258,
+      "learning_rate": 4.985472383720931e-05,
+      "loss": 0.0025,
+      "step": 2000
+    },
     {
       "epoch": 3.0,
-      "eval_f1": 0.9048958394614014,
-      "eval_loss": 0.013671835884451866,
-      "eval_precision": 0.8760752650167597,
-      "eval_recall": 0.9419362439194514,
-      "eval_runtime": 12.5648,
-      "eval_samples_per_second": 131.877,
-      "eval_steps_per_second": 4.139,
-      "step": 1827
+      "eval_f1": 0.9162870645176323,
+      "eval_loss": 0.01785987988114357,
+      "eval_precision": 0.9166192713919116,
+      "eval_recall": 0.9175617135937298,
+      "eval_runtime": 12.5589,
+      "eval_samples_per_second": 131.939,
+      "eval_steps_per_second": 4.14,
+      "step": 2064
     },
     {
-      "epoch": 3.284072249589491,
-      "grad_norm": 0.03194739297032356,
-      "learning_rate": 4.983587848932677e-05,
-      "loss": 0.0024,
-      "step": 2000
+      "epoch": 3.633720930232558,
+      "grad_norm": 0.44367948174476624,
+      "learning_rate": 4.981838662790698e-05,
+      "loss": 0.0021,
+      "step": 2500
     },
     {
       "epoch": 4.0,
-      "eval_f1": 0.926800098647886,
-      "eval_loss": 0.013943095691502094,
-      "eval_precision": 0.9002957711004475,
-      "eval_recall": 0.9554729790053276,
-      "eval_runtime": 12.6182,
-      "eval_samples_per_second": 131.319,
-      "eval_steps_per_second": 4.121,
-      "step": 2436
+      "eval_f1": 0.9225461672714073,
+      "eval_loss": 0.016809402033686638,
+      "eval_precision": 0.920670658749496,
+      "eval_recall": 0.9248274530000097,
+      "eval_runtime": 12.5585,
+      "eval_samples_per_second": 131.942,
+      "eval_steps_per_second": 4.141,
+      "step": 2752
     }
   ],
   "logging_steps": 500,
-  "max_steps": 609000,
+  "max_steps": 688000,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1000,
   "save_steps": 500,
@@ -105,7 +112,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -114,12 +121,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.035249251765043e+16,
+  "total_flos": 2.2993895044079616e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d352a09e2aecd9422bdcc1bf58522262d82cd9de793273e937f615b15344c1
+oid sha256:18049da023690507d75e521ee5b9996b1c940ec5354febc2d3364798461dae1e
 size 5304