Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3fc925c5996c1a83a5ddb1a6c38c4d8439fac65dad95db78497618749ba9df6
+oid sha256:c16b73333678c236b8757e747e700d424720248447c0f93337b9da820e5ef97e
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04a5ddead50161901fc017bbc88ff23e8b30f8312bf923149cb57ab17f54567c
+oid sha256:13dc739cf79cd9740af64038e31eedec29e43eadee01272202a6d67bb7ba5765
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:243bed054e6ca95566a31f84929c545f9505688d6a662df2d1ba4f4954f9e518
+oid sha256:759145ece1000f3e66fd124e9d92191400585f54ff12c451de1a4fc9d6ebb688
 size 14244

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9017300605773926,
   "best_model_checkpoint": "./opt_trained3/checkpoint-1361",
-  "epoch": 1.0,
+  "epoch": 1.99898924928788,
   "eval_steps": 500,
-  "global_step": 1361,
+  "global_step": 2720,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -29,6 +29,27 @@
       "eval_samples_per_second": 50.601,
       "eval_steps_per_second": 12.651,
       "step": 1361
+    },
+    {
+      "epoch": 1.1021777083524764,
+      "grad_norm": 1.2064156532287598,
+      "learning_rate": 4.195020556092935e-05,
+      "loss": 0.8997,
+      "step": 1500
+    },
+    {
+      "epoch": 1.4697234218505928,
+      "grad_norm": 1.2276240587234497,
+      "learning_rate": 1.631521781767214e-05,
+      "loss": 0.8969,
+      "step": 2000
+    },
+    {
+      "epoch": 1.837269135348709,
+      "grad_norm": 1.193297266960144,
+      "learning_rate": 1.6054963006338742e-06,
+      "loss": 0.8947,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
@@ -43,12 +64,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.8780176144128e+16,
+  "total_flos": 1.37491227277056e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null