Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55cb8be523cc641687d9a4362722a0a623c3269ed03e1aad89718ca52bf502cb
+oid sha256:2a99fb4671c16d4a85e887e4afb65ccdb23bd42514dd14bb35b064402d68e339
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1813e91f2cfa1eb270c88b0b78abf1bdd57d56bae4a2de331b9a13e01894d9b
+oid sha256:e8ea8959a235b2cf8936222f3b29ad5fb2f53e446f28d957cc38980898a9ba30
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5276bfff6a9f44b6571a60e5907a8f84a8585a1992ad727c0bb7ed37a25fe20
+oid sha256:63416c461104e18e6f2dc58027f2f497f343071f984012e0153e5a8ba969515d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3692121505737305,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 1.092896174863388,
+  "best_metric": 2.3504340648651123,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 1.1657559198542806,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,13 +217,27 @@
       "eval_samples_per_second": 30.621,
       "eval_steps_per_second": 3.831,
       "step": 1500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0002,
+      "loss": 2.3349,
+      "step": 1600
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 2.3504340648651123,
+      "eval_runtime": 205.0412,
+      "eval_samples_per_second": 30.599,
+      "eval_steps_per_second": 3.828,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.279485281605632e+16,
+  "total_flos": 4.564478592866304e+16,
   "trial_name": null,
   "trial_params": null
 }