Training in progress, step 3200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:279352a17ba807341e217afb26a693fced5c5c19e29613658f3fe885384b9f15
+oid sha256:510639ec914275029ce699b8f395cc1a6104b0efcbf3b0fa6c29af9eeec05cd7
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e50071ac450b1ec9a4dcfcc89b7b00e9ae30e9d87ad938bab50ff4303cf96655
+oid sha256:cb7ac333324ae4365bb9df7cc6216cbba49db9a5c9da60f712ec88bdc7d18afe
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4506919beed58b19c98839e1c17c26b50151b11f50ca31c7cc7f1e5618071106
+oid sha256:d230beeb15f5cac449e9697519a96908c6060afb660e731e7a80310a803abc98
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ecb8491adb59de1678c7683adb025d787487869e6e77014d8400715c3801f7
+oid sha256:4b29cdb3cbf6e4e08e2f27c0eb794c687591cebafa7e8eb23b1335d0cbe8631d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4254179000854492,
-  "best_model_checkpoint": "./outputs/checkpoint-3100",
-  "epoch": 2.2586520947176685,
+  "best_metric": 1.414027214050293,
+  "best_model_checkpoint": "./outputs/checkpoint-3200",
+  "epoch": 2.3315118397085612,
   "eval_steps": 100,
-  "global_step": 3100,
+  "global_step": 3200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -441,13 +441,27 @@
       "eval_samples_per_second": 43.744,
       "eval_steps_per_second": 5.473,
       "step": 3100
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.0002,
+      "loss": 1.4013,
+      "step": 3200
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 1.414027214050293,
+      "eval_runtime": 143.518,
+      "eval_samples_per_second": 43.716,
+      "eval_steps_per_second": 5.47,
+      "step": 3200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.845992464012247e+17,
+  "total_flos": 1.9054273686596813e+17,
   "trial_name": null,
   "trial_params": null
 }