Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53ba66b1d413a3c39f669246d11e75aa712a22d9ce82f15d92bbdb61412cdc88
+oid sha256:7081a0138a5a6607d5d779a29fb6a362bf282f4a1f6dba345f9cbdae40743331
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e6fc3c87b7898cacda2471f32f5ae1f948a1553856ec67e48de9896073249af
+oid sha256:c21820119f05928026f693bc389cb44eda04bf237424f6955cacebb062da0ff2
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb85d675da79c9f128ba95f0e91ab83c431eb4fb41307c6d9686f45b7ede1b07
+oid sha256:fb6764dc3e1fe015624f31dc2613389c8754599510448c4c64c983ace14a8916
 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": 0.9853964447975159,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 0.9784607887268066,
+  "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": 2.481,
       "eval_steps_per_second": 0.311,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 0.8091,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.9784607887268066,
+      "eval_runtime": 780.7522,
+      "eval_samples_per_second": 2.472,
+      "eval_steps_per_second": 0.31,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 2.8493512017395712e+17,
+  "total_flos": 3.108344477177856e+17,
   "trial_name": null,
   "trial_params": null
 }