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:c10cd879656c14f6c67706e5ef6a6ed5392b7455783b83226008557ab6c1c197
+oid sha256:7173f2095eaefc6173f2296bc5ca0608b2758d7af43d3295f6d0b0fa07c89c2f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727c0144258ef51a1f515989e494415a1427822d9138284e64c8b3c60045bfff
+oid sha256:fe914b1d9853545e2ace71d2ea9f0c4da3dfd1c4d91fbd902fd559e493e92959
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc78d73481e3ba72a3d6fb04344d343a7f6ed3f4dbca1980cc2dfd7e0b74a18a
+oid sha256:ed20cb1e030baf9351dd9705735eda93875b2582f4380baf52cb1cb6e628a469
 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": 0.00958155550565162,
+  "epoch": 0.010779249943858073,
   "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": 8.439,
       "eval_steps_per_second": 8.439,
       "step": 32
+    },
+    {
+      "epoch": 0.009880979115203234,
+      "grad_norm": 41.4135627746582,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 3.9928,
+      "step": 33
+    },
+    {
+      "epoch": 0.010180402724754846,
+      "grad_norm": 29.63922882080078,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.1258,
+      "step": 34
+    },
+    {
+      "epoch": 0.01047982633430646,
+      "grad_norm": 34.11370086669922,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.8219,
+      "step": 35
+    },
+    {
+      "epoch": 0.010779249943858073,
+      "grad_norm": 19.921571731567383,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 4.0769,
+      "step": 36
+    },
+    {
+      "epoch": 0.010779249943858073,
+      "eval_loss": 3.3533554077148438,
+      "eval_runtime": 83.2266,
+      "eval_samples_per_second": 8.459,
+      "eval_steps_per_second": 8.459,
+      "step": 36
     }
   ],
   "logging_steps": 1,
@@ -322,7 +358,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1870196536967168e+16,
+  "total_flos": 1.3353971104088064e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null