Training in progress, step 2972, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6108d5fc15eac39666d7d8946b105849460a794e2612d980177b45493ae9c867
+oid sha256:b8515efda803ef8bef233e3cfd356ff1989d857b0323229b36dd021c1f637e0c
 size 430662508

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:773e19e06a2d5b30e8fb0f8ba5ce6a5c64eaf57fbb2eb993e0a5c74e5c9fa482
+oid sha256:cec343eaf3ec90dcfa2cb5c146d36ebdef964ddfb3f32a26819b696032d54450
 size 861448011

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de713ad836ac2a6b95daa8ebda70a2ab44ed35690af2f2553b0f07bee69a7d75
+oid sha256:c247a1c27ea92d0f9537e5dc2de3c2133cbca7edc87c27620b9ddf470aa12e3d
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b395f36c1065f9c23984017cce241f708faf612ff255e494dd1099cec47d815
+oid sha256:69c3205a8951467b50ad397fe93754303c66d8710b2259939d6728fb38517dec
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66888136d67deff3e973c8956f772d3dd35e158601562f8a1fb2cfb066f1ff1c
+oid sha256:9586b5907a02d2d6a0b1232c6bac387f9d2ff5619761451c685a8b534a0534e5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 2400,
   "best_metric": 0.9193424851234314,
   "best_model_checkpoint": "/content/drive/MyDrive/my_works/Work/CSA/models/comparison/BioLinkBERT/checkpoints/checkpoint-2400",
-  "epoch": 1.8172332547963648,
+  "epoch": 2.0,
   "eval_steps": 300,
-  "global_step": 2700,
+  "global_step": 2972,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -593,6 +593,41 @@
       "eval_samples_per_second": 293.839,
       "eval_steps_per_second": 9.235,
       "step": 2700
+    },
+    {
+      "epoch": 1.850891955570515,
+      "grad_norm": 0.19244159758090973,
+      "learning_rate": 3.412487186003988e-07,
+      "loss": 0.025279722213745116,
+      "step": 2750
+    },
+    {
+      "epoch": 1.8845506563446652,
+      "grad_norm": 0.2358558177947998,
+      "learning_rate": 2.058465195282e-07,
+      "loss": 0.022235231399536134,
+      "step": 2800
+    },
+    {
+      "epoch": 1.9182093571188152,
+      "grad_norm": 0.4195547103881836,
+      "learning_rate": 1.0423204634579354e-07,
+      "loss": 0.025367400646209716,
+      "step": 2850
+    },
+    {
+      "epoch": 1.9518680578929652,
+      "grad_norm": 0.17993882298469543,
+      "learning_rate": 3.6755847160593327e-08,
+      "loss": 0.02375290870666504,
+      "step": 2900
+    },
+    {
+      "epoch": 1.9855267586671155,
+      "grad_norm": 0.07394929975271225,
+      "learning_rate": 3.6507003670482875e-09,
+      "loss": 0.03331618070602417,
+      "step": 2950
     }
   ],
   "logging_steps": 50,
@@ -607,12 +642,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5643905456973312.0,
+  "total_flos": 6211419091749888.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null