Training in progress, step 2200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5aa044801096ba38aa92f3c53f63e3594612639b2f0a0f3e127c730420afec
+oid sha256:ee04b6f68182b087f7f27e1cf6f76d0faa0ed3d57cafc2725d1ca3855346159a
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:998470ae339ce2d1a1dbd90195389173b6be0d6c82752c4f94e20a6535bebcee
+oid sha256:ba8261c7433e4b1181ecb8102115396a5d6d0ea425ab1f2e0e02760511b39c4e
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c39f97aa75b72cdd45c6533229ea7444059209f60bb7244cde449b1b2a87c16
+oid sha256:a0b6050b6cd9166e4678f9efac6168fb5645843fe25e8f50be9ac899277f0249
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
+oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0696160793304443,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 1.069016456604004,
+  "best_model_checkpoint": "./outputs/checkpoint-2200",
+  "epoch": 2.9333333333333336,
   "eval_steps": 100,
-  "global_step": 2100,
+  "global_step": 2200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -301,6 +301,20 @@
       "eval_samples_per_second": 10.046,
       "eval_steps_per_second": 1.26,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 0.9177,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 1.069016456604004,
+      "eval_runtime": 197.4097,
+      "eval_samples_per_second": 9.777,
+      "eval_steps_per_second": 1.226,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.968788818327716e+17,
+  "total_flos": 3.110307163440169e+17,
   "trial_name": null,
   "trial_params": null
 }