Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5995830eb1febee676b7330cea0c4b733dc043a73a573c3a086dda9eb7b126a9
+oid sha256:79cada4a810e67c91e5d93b0f36a2576d561b79240d7e333d8eabae22f8be629
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04cfb4b5ff1b186f7b62cc6bbd2939066d1400df652651dc54a369795c1b8c38
+oid sha256:5c6ba999aaf4fb05fb45d72622893e9d9c3a9d23c1a59f681a011a00495cc156
 size 39357829

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bea0b80d96d23f3f961d11718afa3bd11f3aaf4fdfcb59d7ee8fe5190f75ff3
+oid sha256:5710b632f596fa570df2f2575c76e26fe0b3fdacd4ac49afac18b353777ba28e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9620557427406311,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.8666666666666667,
+  "best_metric": 0.9571696519851685,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 2.0,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,20 @@
       "eval_samples_per_second": 2.653,
       "eval_steps_per_second": 0.333,
       "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 0.7863,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9571696519851685,
+      "eval_runtime": 726.583,
+      "eval_samples_per_second": 2.656,
+      "eval_steps_per_second": 0.333,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.627481660202189e+17,
+  "total_flos": 3.884951923281101e+17,
   "trial_name": null,
   "trial_params": null
 }