Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec982e771f291f6f3a2640f27f4e34546243a8992990c637e097eb64381f7c5
+oid sha256:020b8287f73b421e6b874533d8b2ed11de5c0eff953cef60c3f34994887f821b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce06d451780c45c8e8f16bb2d65ab2e9e67299dac915ed3e2a86fa88517759e1
+oid sha256:8856891d17903f6322204042a50f1915a9479d735ba8dd1040155c0c61bdb245
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bc3393a9340b81770a2f56f26e7c6954acce785b42d5c7c1a980acfd38e481
+oid sha256:d4a1d0fa3c6d845cfcdb586fc5456e69f414fd350362eb5b418907a512e6ec4c
 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": 2.348148822784424,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 0.8743169398907104,
+  "best_metric": 2.331716775894165,
+  "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": 30.617,
       "eval_steps_per_second": 3.831,
       "step": 1200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 2.3495,
+      "step": 1300
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 2.331716775894165,
+      "eval_runtime": 204.6122,
+      "eval_samples_per_second": 30.663,
+      "eval_steps_per_second": 3.837,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.500881324867584e+16,
+  "total_flos": 3.792256256581632e+16,
   "trial_name": null,
   "trial_params": null
 }