Training in progress, step 1100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4928efdbbd5aa110866a4550fbed482684cef52cf70ddd2abc0dc6aaef51935c
+oid sha256:328e511f2d707a3a5f2e4f3e13b8fca6d5787e0d4b456d94ca6fc144757dbf81
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14fe84a5e07525f8f22ee24c3e0a0477c0777c448e80bbd4cfdaa2a718ff6aa3
+oid sha256:7410f2b9e82a61e479380c683e0fe1f478b2937ab33f326d0703465bdee9c579
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e120a915f7acf0f917c5e62ffff73a270c236e2220dbb5ce0d14adfe3e96685b
+oid sha256:3cdf360eed736a9a453b77189edcc26992b441f5547b33e72ad2bf313f6d61f2
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
+oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9894721508026123,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.4204545454545454,
+  "best_metric": 0.9814682006835938,
+  "best_model_checkpoint": "./outputs/checkpoint-1100",
+  "epoch": 1.5625,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 12.018,
       "eval_steps_per_second": 1.506,
       "step": 1000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0002,
+      "loss": 1.1196,
+      "step": 1100
+    },
+    {
+      "epoch": 1.56,
+      "eval_loss": 0.9814682006835938,
+      "eval_runtime": 124.3036,
+      "eval_samples_per_second": 12.003,
+      "eval_steps_per_second": 1.504,
+      "step": 1100
     }
   ],
   "logging_steps": 100,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.620616308242432e+16,
+  "total_flos": 6.182618126727168e+16,
   "trial_name": null,
   "trial_params": null
 }