Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a07b7d4a9c1b86f87d485901d5e37ea7b953f9e365829f31dbaea704f076c7bd
+oid sha256:c3fc925c5996c1a83a5ddb1a6c38c4d8439fac65dad95db78497618749ba9df6
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:868dd0dcf987dbe3fc0f6e805629c90bab980bfee1dec1990f93a52eeb7c144f
+oid sha256:04a5ddead50161901fc017bbc88ff23e8b30f8312bf923149cb57ab17f54567c
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a1ccd9f7066dca55443398dffdd4e76ff6f9b9071f99d8222f75921367ac98
+oid sha256:243bed054e6ca95566a31f84929c545f9505688d6a662df2d1ba4f4954f9e518
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6602c18a1ebe894c1d51ce5c9cea3744db091c466423f123d4fa8b7754d9378a
+oid sha256:57298e368684a7f74b8580ab500ef876b797e959380e8c09da0e2d665556ed4b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,63 +1,34 @@
 {
-  "best_metric": 0.9013135433197021,
-  "best_model_checkpoint": "./opt_trained3/checkpoint-2720",
-  "epoch": 1.99898924928788,
+  "best_metric": 0.9017300605773926,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-1361",
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 2720,
+  "global_step": 1361,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.3675457134981163,
-      "grad_norm": 1.054343342781067,
+      "grad_norm": 1.3510414361953735,
       "learning_rate": 9.189154158168292e-05,
-      "loss": 0.9192,
+      "loss": 0.9069,
       "step": 500
     },
     {
       "epoch": 0.7350914269962326,
-      "grad_norm": 1.1676549911499023,
+      "grad_norm": 1.1864418983459473,
       "learning_rate": 7.019605024359474e-05,
-      "loss": 0.9147,
+      "loss": 0.9081,
       "step": 1000
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.9048793911933899,
-      "eval_runtime": 768.112,
-      "eval_samples_per_second": 50.377,
-      "eval_steps_per_second": 12.595,
+      "eval_loss": 0.9017300605773926,
+      "eval_runtime": 764.7068,
+      "eval_samples_per_second": 50.601,
+      "eval_steps_per_second": 12.651,
       "step": 1361
-    },
-    {
-      "epoch": 1.1021777083524764,
-      "grad_norm": 1.1806821823120117,
-      "learning_rate": 4.195020556092935e-05,
-      "loss": 0.9113,
-      "step": 1500
-    },
-    {
-      "epoch": 1.4697234218505928,
-      "grad_norm": 1.2350996732711792,
-      "learning_rate": 1.631521781767214e-05,
-      "loss": 0.907,
-      "step": 2000
-    },
-    {
-      "epoch": 1.837269135348709,
-      "grad_norm": 0.9862784147262573,
-      "learning_rate": 1.6054963006338742e-06,
-      "loss": 0.9047,
-      "step": 2500
-    },
-    {
-      "epoch": 1.99898924928788,
-      "eval_loss": 0.9013135433197021,
-      "eval_runtime": 765.3687,
-      "eval_samples_per_second": 50.557,
-      "eval_steps_per_second": 12.64,
-      "step": 2720
     }
   ],
   "logging_steps": 500,
@@ -72,12 +43,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.37491227277056e+17,
+  "total_flos": 6.8780176144128e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a452ae32a30f3ff55dc4f63985dae2c59ba5cf468734128941ae47abda2b6cbd
+oid sha256:f33fb5eb763ecb18f713e3ce572f1cd2a04862eab8b3ede5970af390529cb8ee
 size 5368