Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128525095c9c4aa2360441c5622c7962547ed143337bfac52c83e3c618dc4e84
+oid sha256:15e78fa49fb00271ad118e01dad1e6674dfce4334a69cbe9e3cf1f3e76ece4a4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfbc3e8f45768fc4da85d1bfec94316cf2bc55ecb2cfaf6f30ff35e6567ace72
+oid sha256:6e12cf4a8339ad6e6ccc2e4a2b586e7d84e101d5a489f8144ee3b6d4413b9990
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8ec78ff15268c9da253ecb4b146058c0df0371aefad94e4b756060686ce26d
+oid sha256:5daf23a304609686c8d20bb6fce1b79761fd95eb6abbd30d197b1a5200625adb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06c69db2db6de56f38ba12b474a491d20087e27dc2893a95d6ac7716476ca645
+oid sha256:0aa0f75a1f3e346be25756b578158b09a68943f0b9f1cfe29f97939687f864ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08613728129205922,
+  "epoch": 0.09690444145356662,
   "eval_steps": 4,
-  "global_step": 32,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -303,6 +303,42 @@
       "eval_samples_per_second": 7.797,
       "eval_steps_per_second": 7.797,
       "step": 32
+    },
+    {
+      "epoch": 0.08882907133243607,
+      "grad_norm": 0.9806796312332153,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.3062,
+      "step": 33
+    },
+    {
+      "epoch": 0.09152086137281291,
+      "grad_norm": 1.1644279956817627,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.3511,
+      "step": 34
+    },
+    {
+      "epoch": 0.09421265141318977,
+      "grad_norm": 0.9300962090492249,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.2276,
+      "step": 35
+    },
+    {
+      "epoch": 0.09690444145356662,
+      "grad_norm": 0.9256501793861389,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.3099,
+      "step": 36
+    },
+    {
+      "epoch": 0.09690444145356662,
+      "eval_loss": 0.27339035272598267,
+      "eval_runtime": 10.1945,
+      "eval_samples_per_second": 7.749,
+      "eval_steps_per_second": 7.749,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -322,7 +358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3168499283197952e+16,
+  "total_flos": 1.4745009760763904e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null