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:d19ee4c79dfa0cd8555549182186a14df743daf6e21d24b4a21011c22094a6db
+oid sha256:017b40465a6824210c164cd90f360929bd24bf4df2da26ef0da1f6730cc50238
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2cf3c991f99ae4959929db1ffcaed2fa37c4816f516b7e8f92f6a4e7d8c3342
+oid sha256:f8241aec37e10265d60eed1746d1128c009874627426900bd1df5c24eab47c9a
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15e6a41072925f3dd8dbbc32ab98519e2970544ec086a60aec53e511597d9906
+oid sha256:ab79c6a083337c9d9cd856b8d8248930e4cb230f6ea6bc6840ef563ef8c0e5cd
 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": 2.42663836479187,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 0.8743169398907104,
+  "best_metric": 2.4082868099212646,
+  "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": 30.646,
       "eval_steps_per_second": 3.834,
       "step": 1200
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0002,
+      "loss": 2.436,
+      "step": 1300
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 2.4082868099212646,
+      "eval_runtime": 204.6174,
+      "eval_samples_per_second": 30.662,
+      "eval_steps_per_second": 3.836,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.41664786505728e+16,
+  "total_flos": 3.700986147274752e+16,
   "trial_name": null,
   "trial_params": null
 }