Training in progress, step 3400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81cfca91f074eb3fd1a57ab735cb0951f904b2c1043953b0e78d5f22cdb3b15f
+oid sha256:bc4e87ce60e95f334f9ec47b8fe54b1d82f5a5f7978130fdf8d944e15669723f
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca8a2716b512f448331946e4957a577a98bed9ca38b351798cd39e434f40157
+oid sha256:6ff5ecb883ad6d1eb389c5edac5865f629316fc50eededfe70d565ad326e30b3
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6fbad0ea34eece1c92d74863d52656aa2afa741f5a63409595d0576b937447
+oid sha256:19f1c1e4927fa3815539e897f0308722f491e1900ce9959e8f01c6f5809d166d
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9256a803964ffb87bb8f27450ef4542ffa862650dea6451971cd3526e89c291
+oid sha256:74901e7dfd1aad733e09f74ea6b7845fa91d24f912870eb55d586767f7c4065c
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4006284475326538,
-  "best_model_checkpoint": "./outputs/checkpoint-3300",
-  "epoch": 2.4043715846994536,
+  "best_metric": 1.3891088962554932,
+  "best_model_checkpoint": "./outputs/checkpoint-3400",
+  "epoch": 2.477231329690346,
   "eval_steps": 100,
-  "global_step": 3300,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -469,13 +469,27 @@
       "eval_samples_per_second": 43.687,
       "eval_steps_per_second": 5.466,
       "step": 3300
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 0.0002,
+      "loss": 1.3608,
+      "step": 3400
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 1.3891088962554932,
+      "eval_runtime": 143.6908,
+      "eval_samples_per_second": 43.663,
+      "eval_steps_per_second": 5.463,
+      "step": 3400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.964956353440809e+17,
+  "total_flos": 2.0244396170354688e+17,
   "trial_name": null,
   "trial_params": null
 }