Training in progress, epoch 5, checkpoint

checkpoint-1060/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da03c2e5cf329852b66a01b89622223c2fcbf52ce53827113df9fd71e5e2ed56
+oid sha256:a165d057937c0f9ad48256a4be3c3509f26597825e42a7bc669a2dce3a47f763
 size 117304221

checkpoint-1060/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c00b93bdd0a6a507e95b4c90dfc918a379c6fae01ac789e9d44fbeceeb84ebe
+oid sha256:1c7260f7f4f2b74f9b79bbc4083d22fdfa463b16a583171c34744ad81b434435
 size 234652550

checkpoint-1060/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d775f6e462a916c86b1c3e21f113a5b0e8205fa7ec7a56531a81c04f452f2305
+oid sha256:5d00bccdb7f8ffe15e6546492e7657db0a06b88f5411f0e5ef23c450b812dbf0
 size 627

checkpoint-1060/trainer_state.json

@@ -10,72 +10,72 @@
   "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
     }
   ],

checkpoint-1060/training_args.bin

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