Training in progress, epoch 6, checkpoint

checkpoint-1272/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc5a98159252ccf9ad4f7ab31d4994f573e759d32e34664b82dfbdfc198ffe02
+oid sha256:46053eb5e684452d3fee0f3beeb85eabfb16795b15c85cbad29a529d694140e7
 size 117304221

checkpoint-1272/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ff1d5c1e6214deaa3912c66d1177a2750fbdadd271bab7567f56da7f39c6df6
+oid sha256:d08f343c7b76598335f8e92de5d8d8ff9b5da73b81cf223ce4e68b98da74eedb
 size 234652550

checkpoint-1272/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33be92081d6b8d53e2694d4fc8be88c8ba671a7631c34f09f679e994f0ccd49e
+oid sha256:49710cf0617d0f5ff85cc134b17065f112194dd8c7c7dbcde410b3496dd32a57
 size 627

checkpoint-1272/trainer_state.json

@@ -10,86 +10,86 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "learning_rate": 9.950235849056605e-06,
-      "loss": 6.539,
+      "learning_rate": 0.00019900471698113207,
+      "loss": 6.1329,
       "step": 212
     },
     {
       "epoch": 1.0,
-      "eval_loss": 6.494007587432861,
-      "eval_runtime": 2.5292,
-      "eval_samples_per_second": 267.281,
-      "eval_steps_per_second": 33.608,
+      "eval_loss": 5.14426851272583,
+      "eval_runtime": 3.8194,
+      "eval_samples_per_second": 176.991,
+      "eval_steps_per_second": 22.255,
       "step": 212
     },
     {
       "epoch": 2.0,
-      "learning_rate": 9.900235849056603e-06,
-      "loss": 6.4697,
+      "learning_rate": 0.00019800471698113207,
+      "loss": 4.6548,
       "step": 424
     },
     {
       "epoch": 2.0,
-      "eval_loss": 6.410468101501465,
-      "eval_runtime": 2.6306,
-      "eval_samples_per_second": 256.98,
-      "eval_steps_per_second": 32.313,
+      "eval_loss": 3.559998035430908,
+      "eval_runtime": 3.8713,
+      "eval_samples_per_second": 174.616,
+      "eval_steps_per_second": 21.956,
       "step": 424
     },
     {
       "epoch": 3.0,
-      "learning_rate": 9.850235849056604e-06,
-      "loss": 6.3924,
+      "learning_rate": 0.00019700471698113207,
+      "loss": 3.2979,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_loss": 6.319283962249756,
-      "eval_runtime": 2.6112,
-      "eval_samples_per_second": 258.881,
-      "eval_steps_per_second": 32.552,
+      "eval_loss": 2.3220388889312744,
+      "eval_runtime": 3.7585,
+      "eval_samples_per_second": 179.86,
+      "eval_steps_per_second": 22.616,
       "step": 636
     },
     {
       "epoch": 4.0,
-      "learning_rate": 9.800235849056604e-06,
-      "loss": 6.3093,
+      "learning_rate": 0.00019600471698113207,
+      "loss": 2.2394,
       "step": 848
     },
     {
       "epoch": 4.0,
-      "eval_loss": 6.226834297180176,
-      "eval_runtime": 2.5547,
-      "eval_samples_per_second": 264.612,
-      "eval_steps_per_second": 33.272,
+      "eval_loss": 1.5198729038238525,
+      "eval_runtime": 3.8733,
+      "eval_samples_per_second": 174.529,
+      "eval_steps_per_second": 21.945,
       "step": 848
     },
     {
       "epoch": 5.0,
-      "learning_rate": 9.750235849056605e-06,
-      "loss": 6.216,
+      "learning_rate": 0.00019500471698113208,
+      "loss": 1.5436,
       "step": 1060
     },
     {
       "epoch": 5.0,
-      "eval_loss": 6.127103328704834,
-      "eval_runtime": 2.5792,
-      "eval_samples_per_second": 262.1,
-      "eval_steps_per_second": 32.956,
+      "eval_loss": 1.0844509601593018,
+      "eval_runtime": 3.7882,
+      "eval_samples_per_second": 178.45,
+      "eval_steps_per_second": 22.438,
       "step": 1060
     },
     {
       "epoch": 6.0,
-      "learning_rate": 9.700235849056605e-06,
-      "loss": 6.1217,
+      "learning_rate": 0.0001940047169811321,
+      "loss": 1.1087,
       "step": 1272
     },
     {
       "epoch": 6.0,
-      "eval_loss": 6.023599147796631,
-      "eval_runtime": 2.6119,
-      "eval_samples_per_second": 258.818,
-      "eval_steps_per_second": 32.544,
+      "eval_loss": 0.8275050520896912,
+      "eval_runtime": 3.8596,
+      "eval_samples_per_second": 175.146,
+      "eval_steps_per_second": 22.023,
       "step": 1272
     }
   ],

checkpoint-1272/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:932083cda874171956e29a9559decb3e85350d37f61015836b2c832b21575f2e
+oid sha256:11396e77b2185e0d94bce5383c2512c5afd7f340883723b782abc68f5d11c5a6
 size 4155