Training in progress, step 48, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33b4844caefd469fc402ef51d94e4a7e03f93da8b31752639992a7762a880a8f
+oid sha256:e1cbff5d2dd655a43c655636c1f12011056f968d63edef65a78d2a9d7e3be60d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faffbce5868eeb6ddbc3cd65903a3be5ddb7763cc936364e13936bddd04132c3
+oid sha256:32fb54ec690956ca980ac389a6df0b97da27ec07177b45074e765cf24569836a
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c027f738a4dfd52c6913eec1699a4b97c1baecedcd1dcbe2a0d7d12892180c4
+oid sha256:da87e4c065bb443c099cfa52ab3a5635819290010328feda7944776129428914
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
+oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01857519788918206,
+  "epoch": 0.020263852242744063,
   "eval_steps": 4,
-  "global_step": 44,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -411,6 +411,42 @@
       "eval_samples_per_second": 8.393,
       "eval_steps_per_second": 8.393,
       "step": 44
+    },
+    {
+      "epoch": 0.01899736147757256,
+      "grad_norm": 3.1134109497070312,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.4219,
+      "step": 45
+    },
+    {
+      "epoch": 0.01941952506596306,
+      "grad_norm": 2.3598380088806152,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.3093,
+      "step": 46
+    },
+    {
+      "epoch": 0.01984168865435356,
+      "grad_norm": 2.2470579147338867,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.3218,
+      "step": 47
+    },
+    {
+      "epoch": 0.020263852242744063,
+      "grad_norm": 2.2850100994110107,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.3537,
+      "step": 48
+    },
+    {
+      "epoch": 0.020263852242744063,
+      "eval_loss": 0.26765426993370056,
+      "eval_runtime": 60.0554,
+      "eval_samples_per_second": 8.309,
+      "eval_steps_per_second": 8.309,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -430,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6321520238329856e+16,
+  "total_flos": 1.7805294805450752e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null