Training in progress, step 40250, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346b6ba8a0e7815947f20628de9f3d3af6ab8139a91118cf143cd3dc8eb146ad
+oid sha256:bdf20454bb920b5229a72d2241aded5af56bf1d40cafdc205ad2ed71ddb51ce2
 size 611073224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b8bc63fd2b8baa76ecd7886a045dc375cb875b522a59fa37376c6075b7214c5
+oid sha256:9b51bbb3052c6336fdd306188aefaf0df9e191813737b03dc83638919d7f1fd5
 size 1222241675

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57c1faacff2ef52c66c645c610107c0e55aa7d56e45f05da40e4b290dd1ba1d0
+oid sha256:c63672711fc07bad7a68a3b4c4d72bc53b6bdbd46717a715e436ced2146084e0
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:977a470143aa24e72cee7a02d2bbb1562c97dd70f900cdb3987072bece7c2dec
+oid sha256:42e39dfc5ecd7ab1c066d7ba59fe38c030dfd049fdd393d56e8651cbc6e2f98e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 39250,
   "best_metric": 2.157838821411133,
   "best_model_checkpoint": "/share/ai-lab/scandussio/stlenc_tuning_0.2/results-final/checkpoint-39250",
-  "epoch": 10.41124414367517,
+  "epoch": 10.47631441957314,
   "eval_steps": 250,
-  "global_step": 40000,
+  "global_step": 40250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6888,6 +6888,49 @@
       "eval_samples_per_second": 219.795,
       "eval_steps_per_second": 1.758,
       "step": 40000
+    },
+    {
+      "epoch": 10.424258198854764,
+      "grad_norm": 4.224571704864502,
+      "learning_rate": 1.5253340274162764e-06,
+      "loss": 1.4713,
+      "step": 40050
+    },
+    {
+      "epoch": 10.437272254034356,
+      "grad_norm": 10.799654960632324,
+      "learning_rate": 1.5209960090230782e-06,
+      "loss": 1.4412,
+      "step": 40100
+    },
+    {
+      "epoch": 10.45028630921395,
+      "grad_norm": 8.12926959991455,
+      "learning_rate": 1.5166579906298803e-06,
+      "loss": 1.4705,
+      "step": 40150
+    },
+    {
+      "epoch": 10.463300364393545,
+      "grad_norm": 4.9367756843566895,
+      "learning_rate": 1.5123199722366823e-06,
+      "loss": 1.447,
+      "step": 40200
+    },
+    {
+      "epoch": 10.47631441957314,
+      "grad_norm": 6.339715480804443,
+      "learning_rate": 1.5079819538434846e-06,
+      "loss": 1.4478,
+      "step": 40250
+    },
+    {
+      "epoch": 10.47631441957314,
+      "eval_loss": 2.1831064224243164,
+      "eval_runtime": 13.7128,
+      "eval_samples_per_second": 218.774,
+      "eval_steps_per_second": 1.75,
+      "step": 40250
     }
   ],
   "logging_steps": 50,
@@ -6907,7 +6950,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.393798126642135e+18,
+  "total_flos": 2.408760416969687e+18,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null