Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:302b1e49506cf8a2f6be7df9eb914a5a22181a7f48998aea098da889929fe70b
+oid sha256:f1b49c5cf8c9904f530d5b551cd50a7010480cbc526f3202d75c1189c3d22353
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782e2d2a139a42c65b5869d28871ff2018b39607a728c43f4593938ed277e3b4
+oid sha256:db130831adb61cd9765c63395fb567a08dfe0d4be9c5bcc6ab77250c3fe1a40b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16dbd92b02a89cf372eb0be8faed673d0065b4c507cdb24698df320c511fb2f
+oid sha256:63d2c99dbd46a20a48c294132ab2d17f45afe77fd0e7fd574cf93295fea8e744
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
+oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.167008638381958,
-  "best_model_checkpoint": "./outputs/checkpoint-2900",
-  "epoch": 2.1129326047358834,
+  "best_metric": 2.1564178466796875,
+  "best_model_checkpoint": "./outputs/checkpoint-3000",
+  "epoch": 2.185792349726776,
   "eval_steps": 100,
-  "global_step": 2900,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -413,13 +413,27 @@
       "eval_samples_per_second": 30.623,
       "eval_steps_per_second": 3.831,
       "step": 2900
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0002,
+      "loss": 2.1284,
+      "step": 3000
+    },
+    {
+      "epoch": 2.19,
+      "eval_loss": 2.1564178466796875,
+      "eval_runtime": 205.2562,
+      "eval_samples_per_second": 30.567,
+      "eval_steps_per_second": 3.824,
+      "step": 3000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.255440339421184e+16,
+  "total_flos": 8.542105612314624e+16,
   "trial_name": null,
   "trial_params": null
 }