Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a5cd18eba05dd115816c13a3783bb13f1e1949576694e94094a042fef3711c
+oid sha256:fa788ab3acb6ea0c93ad303e4064acc66353410749dbb72baf8e49908f8dd943
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9215ce1bd5f92c75520dfbe4371e05cc40405b2dcc9d096a0150122af4fe4d97
+oid sha256:0bea7d7873f5fad796e996d3ce7d1cb065bc314a9ec98082e88e9857061ba6df
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6de7f4a42b33795d5576dbfcbd59d460b4c2829c2dca4e78d73528861030ee0
+oid sha256:591a9c5e45bb1139399d3039b4c05dd34997d5462b11eb1ca1771e8044f4a6a1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5728504657745361,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 1.552846074104309,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.0200364298724955,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,13 +189,27 @@
       "eval_samples_per_second": 43.556,
       "eval_steps_per_second": 5.45,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 1.5528,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 1.552846074104309,
+      "eval_runtime": 144.0891,
+      "eval_samples_per_second": 43.543,
+      "eval_steps_per_second": 5.448,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.750875343424717e+16,
+  "total_flos": 8.347109656129536e+16,
   "trial_name": null,
   "trial_params": null
 }