Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fb97c1964b635d7be1205ccef676d0caa1dd98ed0ac8b59e7c755533e32712
+oid sha256:4ab237cb7a4a12b5913039477bbfb178aac5c8809b3264af22d9311f26c092d4
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2323db34f8f05f4d09cb6d1278b45c569a36b0afe0f5fd1eacf32a59e4fbd607
+oid sha256:c7587ea383570bccad6d8c4d94834efb8793ba6d29c3ce414358d378cac00fe4
 size 2894813242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238f89c7881608a89c144adfd8d2cd6859c09e7f2d8a8e8db71c7c86758fd97b
+oid sha256:0c785df7642646aef2a39d5240ed589e73b085e3b34051de846243fbbdb4deb6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.344450980424881,
   "best_model_checkpoint": "./opt_trained2/checkpoint-803",
-  "epoch": 4.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 3212,
+  "global_step": 4015,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -81,6 +81,28 @@
       "eval_samples_per_second": 10.474,
       "eval_steps_per_second": 2.619,
       "step": 3212
+    },
+    {
+      "epoch": 4.35865504358655,
+      "grad_norm": 1.3971993923187256,
+      "learning_rate": 0.000312826899128269,
+      "loss": 1.5169,
+      "step": 3500
+    },
+    {
+      "epoch": 4.981320049813201,
+      "grad_norm": 1.8089447021484375,
+      "learning_rate": 0.000300373599003736,
+      "loss": 1.3553,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5129567384719849,
+      "eval_runtime": 272.4812,
+      "eval_samples_per_second": 10.481,
+      "eval_steps_per_second": 2.62,
+      "step": 4015
     }
   ],
   "logging_steps": 500,
@@ -100,7 +122,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2514885666272e+17,
+  "total_flos": 1.564360708284e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null