Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d71168ad9020ce7a453d84aa8f4be4bab8630b6df124228c3eb6142235daf0c
+oid sha256:c1074b2a9ea93bc62071db7f2563277af3f8412328b6c3fc8ed82da56efbf60b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366f7393a56d978bc10299f01762fc13729207344220c72ca833f46b995e66ec
+oid sha256:d90c0ec60df7b2988bc1d7af51dd0c321b4e1099609e54257a32f8ce767793a5
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c7e8c0f7bb988751ccd9907b573ddb354edc6c4d1478341caae7f6c4a40c442
+oid sha256:8e4d249624bc8de793916f023beebfa62202a9083f1d5be34ff57cd42f702095
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d403ac4d7711325e0c8bec676128002b741c5058ffa34f8bfc8e7d7e4547c436
+oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.34408602150537637,
+  "epoch": 0.5161290322580645,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 8.964,
       "eval_steps_per_second": 4.507,
       "step": 18
+    },
+    {
+      "epoch": 0.4014336917562724,
+      "grad_norm": 1.5562611818313599,
+      "learning_rate": 0.0001999229036240723,
+      "loss": 2.0297,
+      "step": 21
+    },
+    {
+      "epoch": 0.45878136200716846,
+      "grad_norm": 1.7431790828704834,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 1.861,
+      "step": 24
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 1.7667114734649658,
+      "learning_rate": 0.00019624552364536473,
+      "loss": 1.9087,
+      "step": 27
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "eval_loss": 1.8730906248092651,
+      "eval_runtime": 19.7448,
+      "eval_samples_per_second": 8.964,
+      "eval_steps_per_second": 4.508,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0742550511170355e+17,
+  "total_flos": 1.6113825766755533e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null