Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6855c333ac1c697e6d06a877d9e75bb8a598912c0b6bd089af9789e465ca3dac
+oid sha256:58eadfa6617e3e1d0ff3394dcf553eabd47aba1de02ab15fdac8eaab8c08cf66
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e8039c70b87ed8bb202c149c44024b2e5af04921eef6a357d9e91ca56ccf729
+oid sha256:07eeb9ee2ce78c05124fba829a27d09a26082535809e93a9d89c7a7c42331fb5
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf0a8d4e9a6653930f212c4ac0808e06254e1f11ce9e27417a57091c7e3e0282
+oid sha256:0215b9b0c756446a0a4927e0fe6fa21e780ad4150be2177b0182afb17c78ac6a
 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": 0.9988044500350952,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 0.994540810585022,
+  "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": 5.438,
       "eval_steps_per_second": 0.682,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 0.8584,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.994540810585022,
+      "eval_runtime": 353.5912,
+      "eval_samples_per_second": 5.458,
+      "eval_steps_per_second": 0.684,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.110486213260984e+17,
+  "total_flos": 3.392066003002245e+17,
   "trial_name": null,
   "trial_params": null
 }