Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07cd658deed4152b4fb8a7f91d7be81dc965feaabeda4a4323c1f4673916564e
+oid sha256:05000e36c627807d10f5b2a2a12fef5b7ae8bc4f815bc0f4baef1067e14f8a7e
 size 50349441

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172478bc9fb12c145cf132494a3826cc171c86e2549f424b65342c8ed470fa57
+oid sha256:3a255d88304c99a62eb2a041b92e091d0389471f9d3d2cac1a1197d365e75ecb
 size 100691721

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b2ca29d141327e8ea4b65cb34013d406e6299309d494d75934267332233dda3
+oid sha256:d6de7f4a42b33795d5576dbfcbd59d460b4c2829c2dca4e78d73528861030ee0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5974311828613281,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 0.8743169398907104,
+  "best_metric": 1.5751127004623413,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 0.9471766848816029,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,13 +175,27 @@
       "eval_samples_per_second": 21.508,
       "eval_steps_per_second": 2.691,
       "step": 1200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 1.6021,
+      "step": 1300
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 1.5751127004623413,
+      "eval_runtime": 289.9524,
+      "eval_samples_per_second": 21.638,
+      "eval_steps_per_second": 2.707,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.153994046622925e+16,
+  "total_flos": 7.750875343424717e+16,
   "trial_name": null,
   "trial_params": null
 }