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:de8870e3d1844d63b1d1ccf6c212323aba6916a9403d58c3f906cfe0571362a1
+oid sha256:87cd665d5194b58daf9f076f0d70da138f72bfb986db877d8c94f22a71986ac2
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12555ca2545543abe6e163790234b25afbd4d55b67b282832079d80ef92c60c4
+oid sha256:b027afa43f63b2c5b25975008932c91acea891890d801200412531e83645d762
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0648c05bcceba81aabdea1b34baac57c985681599db080ce43ad848e9f5bad60
+oid sha256:ec5cd6f4135325d74cbe93521ed6f759304f9780c6d6678a798b7bcfeb74b23f
 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": 1.9184151887893677,
-  "best_model_checkpoint": "./outputs/checkpoint-1200",
-  "epoch": 1.7045454545454546,
+  "best_metric": 1.905383586883545,
+  "best_model_checkpoint": "./outputs/checkpoint-1300",
+  "epoch": 1.8465909090909092,
   "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": 19.856,
       "eval_steps_per_second": 2.489,
       "step": 1200
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 0.0002,
+      "loss": 2.042,
+      "step": 1300
+    },
+    {
+      "epoch": 1.85,
+      "eval_loss": 1.905383586883545,
+      "eval_runtime": 75.0775,
+      "eval_samples_per_second": 19.873,
+      "eval_steps_per_second": 2.491,
+      "step": 1300
     }
   ],
   "logging_steps": 100,
@@ -182,7 +196,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.65226999975936e+16,
+  "total_flos": 3.957240059265024e+16,
   "trial_name": null,
   "trial_params": null
 }