Training in progress, epoch 9, checkpoint

checkpoint-1908/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba71f9dbbcf53f380304a03f0a1d0e4ed45da7de87acd86f5aba0f54e5e67d4
+oid sha256:eba549afb42c0f84ab90545fea12ddf0287519aa6ce155295d00a6718daddb12
 size 117304221

checkpoint-1908/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706d07b08d506df71684f15ac775cf71b142c72e28bfbb2983f60d71c7bfecb1
+oid sha256:ee7a4a04b8cf69d213e4230acaf9f22ad9b4e4b7d8171968111e018534132b65
 size 234652550

checkpoint-1908/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02f3caca399083cabba358f846274a7abe83547ec4554cb47be136e0a89f73b2
+oid sha256:8dd5ec14497c9a395bf15af07c1379cb7f464223285ce22f8bfe084ba1e26f66
 size 627

checkpoint-1908/trainer_state.json

@@ -10,128 +10,128 @@
   "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
     },
     {
       "epoch": 7.0,
-      "learning_rate": 9.650235849056606e-06,
-      "loss": 6.0274,
+      "learning_rate": 0.00019300943396226416,
+      "loss": 0.8094,
       "step": 1484
     },
     {
       "epoch": 7.0,
-      "eval_loss": 5.916015625,
-      "eval_runtime": 2.7327,
-      "eval_samples_per_second": 247.379,
-      "eval_steps_per_second": 31.105,
+      "eval_loss": 0.6410268545150757,
+      "eval_runtime": 3.826,
+      "eval_samples_per_second": 176.686,
+      "eval_steps_per_second": 22.216,
       "step": 1484
     },
     {
       "epoch": 8.0,
-      "learning_rate": 9.600235849056605e-06,
-      "loss": 5.9233,
+      "learning_rate": 0.00019200943396226417,
+      "loss": 0.5999,
       "step": 1696
     },
     {
       "epoch": 8.0,
-      "eval_loss": 5.803537368774414,
-      "eval_runtime": 2.6768,
-      "eval_samples_per_second": 252.536,
-      "eval_steps_per_second": 31.754,
+      "eval_loss": 0.5242534279823303,
+      "eval_runtime": 3.7888,
+      "eval_samples_per_second": 178.42,
+      "eval_steps_per_second": 22.434,
       "step": 1696
     },
     {
       "epoch": 9.0,
-      "learning_rate": 9.550235849056605e-06,
-      "loss": 5.8234,
+      "learning_rate": 0.00019100943396226417,
+      "loss": 0.4333,
       "step": 1908
     },
     {
       "epoch": 9.0,
-      "eval_loss": 5.689106464385986,
-      "eval_runtime": 2.688,
-      "eval_samples_per_second": 251.488,
-      "eval_steps_per_second": 31.622,
+      "eval_loss": 0.4525991678237915,
+      "eval_runtime": 3.7762,
+      "eval_samples_per_second": 179.014,
+      "eval_steps_per_second": 22.509,
       "step": 1908
     }
   ],

checkpoint-1908/training_args.bin

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