Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a9a39b49dc8af48cc4147e9762b14c8e860aef41fd18ec146ac27c65dc6812
+oid sha256:f746b5739e28ed8ae2191cfc3a28ef9dd9cbc44604b6789cd53bf9eda7d42a17
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35af0ead48eb3e1b4330ce43fd33be1a5ff3cebe1cf0458eba7bb56fce618b03
+oid sha256:f1fd180c6763f5d63483fe0a8c08012dd8b4705c90fd0583248dda0dc4539572
 size 1002078330

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.9235808253288269,
+  "best_metric": 0.9197561740875244,
   "best_model_checkpoint": "./opt_trained3/checkpoint-1361",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,24 +10,24 @@
   "log_history": [
     {
       "epoch": 0.3675457134981163,
-      "grad_norm": 1.4956048727035522,
+      "grad_norm": 1.09419846534729,
       "learning_rate": 9.189154158168292e-05,
-      "loss": 0.939,
+      "loss": 0.9262,
       "step": 500
     },
     {
       "epoch": 0.7350914269962326,
-      "grad_norm": 1.0351307392120361,
+      "grad_norm": 1.0400797128677368,
       "learning_rate": 7.019605024359474e-05,
-      "loss": 0.9314,
+      "loss": 0.9246,
       "step": 1000
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.9235808253288269,
-      "eval_runtime": 760.9492,
-      "eval_samples_per_second": 50.851,
-      "eval_steps_per_second": 12.713,
+      "eval_loss": 0.9197561740875244,
+      "eval_runtime": 761.7722,
+      "eval_samples_per_second": 50.796,
+      "eval_steps_per_second": 12.699,
       "step": 1361
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ece721c919142a4326911838f17a116511a7a472a5798db73eacd9dc97d85ed
+oid sha256:ae610ca3ba358abeebc6af3521a544fd6c45bd94a76da5a597144463f080a452
 size 5368