Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1263cfb0a5cbb250895383d1c540603d992511fb7c6bfb7133d1b9d81fd20d87
+oid sha256:7b19523cdf981f300ad310d2250ec0665ea8b86064e428ff6ff02dc42bc4f985
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2d417062abbaf7a8b2f3f4d99618349508a564be2ea7944c9b47e50a8a78a25
+oid sha256:c8bddc6bad4d734a9e5d394ad7b12ec5df6debf2ce5c05e88a5d4baffa40f348
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2a97244d4c9e36a92ce9603501239216f8b35c73f1c473a49ecf7c2bcaecde
+oid sha256:43a793a4bb6d7ad0c9ab597d723f0209456c5c120d347f8afa1ae7dbad7c5d74
 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": 1.2016816139221191,
-  "best_model_checkpoint": "./outputs/checkpoint-1500",
-  "epoch": 2.0,
+  "best_metric": 1.2005386352539062,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 2.1333333333333333,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 4.219,
       "eval_steps_per_second": 0.529,
       "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 0.9755,
+      "step": 1600
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.2005386352539062,
+      "eval_runtime": 458.0891,
+      "eval_samples_per_second": 4.213,
+      "eval_steps_per_second": 0.528,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.991433715954483e+16,
+  "total_flos": 5.32352337813504e+16,
   "trial_name": null,
   "trial_params": null
 }