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:c62ca606aaf3a5e391ab79efbdbd6f136ff872fffc76bb44f3f93cc16aa7ee48
+oid sha256:257f019123780b1c55e505466089f8e97774256b5162ff2a9dd9c53ad0981724
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c906645f5fa7e35290dbfc313513f00acb313f5a0c14568377f5e8a35a792e
+oid sha256:c55efb4794097377f43111558386aeebe7c8a2539fb41154eb47915789b79b92
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0770ff6204965e70605ce6b3d87c7de79ab315ff8e5a70f192ba4c9b0362a1ca
+oid sha256:828c793974c0f73b777262e329ad095566fad802fa73d655e45ae82e9eed4154
 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": 1.2948063611984253,
-  "best_model_checkpoint": "./outputs/checkpoint-2100",
-  "epoch": 2.8,
+  "best_metric": 1.2910176515579224,
+  "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": 30.492,
       "eval_steps_per_second": 3.825,
       "step": 2100
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 0.0002,
+      "loss": 1.3818,
+      "step": 2200
+    },
+    {
+      "epoch": 2.93,
+      "eval_loss": 1.2910176515579224,
+      "eval_runtime": 47.3703,
+      "eval_samples_per_second": 30.631,
+      "eval_steps_per_second": 3.842,
+      "step": 2200
     }
   ],
   "logging_steps": 100,
@@ -308,7 +322,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 7.041614616723456e+16,
+  "total_flos": 7.376989486841856e+16,
   "trial_name": null,
   "trial_params": null
 }