Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1074b2a9ea93bc62071db7f2563277af3f8412328b6c3fc8ed82da56efbf60b
+oid sha256:84d348b33b833d7118abd3f100d70b7d313a866228f2cf4973c56e51eb2c58a5
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d90c0ec60df7b2988bc1d7af51dd0c321b4e1099609e54257a32f8ce767793a5
+oid sha256:92614455d6b4f9fea1720ef0d7522eb53064139c2983b463ad81c13613377dc3
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e4d249624bc8de793916f023beebfa62202a9083f1d5be34ff57cd42f702095
+oid sha256:884ce308a4b9046b63daa8471de316c7b3c332361554edb94ea15c1aef43590c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014898519bf1f31fef4a7ab39caf2eaa1ff4fbc5662e969211f7676259067ad2
+oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5161290322580645,
+  "epoch": 0.6881720430107527,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 8.964,
       "eval_steps_per_second": 4.508,
       "step": 27
+    },
+    {
+      "epoch": 0.5734767025089605,
+      "grad_norm": 1.5921707153320312,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 1.8208,
+      "step": 30
+    },
+    {
+      "epoch": 0.6308243727598566,
+      "grad_norm": 1.4759997129440308,
+      "learning_rate": 0.00018724960070727972,
+      "loss": 1.9535,
+      "step": 33
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 1.3630574941635132,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.8836,
+      "step": 36
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "eval_loss": 1.8447675704956055,
+      "eval_runtime": 19.7508,
+      "eval_samples_per_second": 8.962,
+      "eval_steps_per_second": 4.506,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6113825766755533e+17,
+  "total_flos": 2.148510102234071e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null