Training in progress, step 1300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad81edbffb3ee917c43e9b387e7af768103587620ab9067cba3f0aed7aa5eb1c
+oid sha256:53a93aad74494e1da199a78d40cddc05b035544f04f6b1f54ae0d9518920ecda
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2360411f172c526aa92d4b4914fd540cc4ec865e5cf726b12c3e8eb4db95fa
+oid sha256:64fd34cf15527c9242ff55f7d79a57537a489b3a707e638c23d25fe290d76ef3
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79640f134089a5b6b53d3d1590ef6b452050436bae87c8a0c3b40ada6d34201d
+oid sha256:ac2be089e58af285b82a77df44ed8dc14c9f419db076cc74bf8b10029313b041
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
+oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0906414985656738,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.6,
+  "best_metric": 1.0867207050323486,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.7333333333333334,
   "eval_steps": 100,
-  "global_step": 1200,
+  "global_step": 1300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -175,6 +175,20 @@
       "eval_samples_per_second": 10.341,
       "eval_steps_per_second": 1.297,
       "step": 1200
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 0.0002,
+      "loss": 0.9411,
+      "step": 1300
+    },
+    {
+      "epoch": 1.73,
+      "eval_loss": 1.0867207050323486,
+      "eval_runtime": 186.79,
+      "eval_samples_per_second": 10.332,
+      "eval_steps_per_second": 1.296,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.696258635822121e+17,
+  "total_flos": 1.837764184871977e+17,
   "trial_name": null,
   "trial_params": null
 }