Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fd6665b3fca8307b4a850466143a7febba5378fb87299f6c228b334280a8be8
+oid sha256:505d619dab8bf9ec17129628444e97a26e93b6239cde8f1aaeb08304e9031790
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80609acf10ab518787737b5f6a0c39d203f2316a6b68a05cf35e2f798c8eeddb
+oid sha256:fe339b1fcc946bcd8cc5d20d73cca29bdf3dda80ad3e51a3090a119e28d3b984
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c40dab02973b1cc46cf9629cd02e8f44b9b493929030f20bf23390e0e7e4d8
+oid sha256:ffde39b50896bc17b78a0302958b86632bce20c81789b1dc8c76995d55dbbd05
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1321903467178345,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.1260673999786377,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.6,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 10.889,
       "eval_steps_per_second": 1.365,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 0.9282,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.1260673999786377,
+      "eval_runtime": 177.157,
+      "eval_samples_per_second": 10.894,
+      "eval_steps_per_second": 1.366,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.219848108179456e+16,
+  "total_flos": 8.96699552329728e+16,
   "trial_name": null,
   "trial_params": null
 }