Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad818c83ecada0ac38ac9925d364fe72c911bbfa7d0d92d3ba36f6a3ad0c67f7
+oid sha256:39780879b55af36d3fa91720510636d00c6e52a423e8f08e326a989983f210c7
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:302b8df31ea93fc8a26d7ae1c8ef10adf3233e1a216cdd840ba6ce88d7c18b73
+oid sha256:ae6db2f954da1f81b84ac81696b6881920d93a6c5ea5cc1763d5c384ef630497
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e7f674eb8e0d7b06038546beef4656bebd11a28fbd56de62105d83f601544a
+oid sha256:6e78c0407e9b9da7ed46812d33357290c89503de08bb3783c4c0def49e11abbf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0539993250084374,
+  "epoch": 0.060749240634492066,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 4.337,
       "eval_steps_per_second": 0.542,
       "step": 40
+    },
+    {
+      "epoch": 0.056699291258859266,
+      "grad_norm": 6.903482913970947,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.9028,
+      "step": 42
+    },
+    {
+      "epoch": 0.060749240634492066,
+      "grad_norm": 10.054128646850586,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.0095,
+      "step": 45
+    },
+    {
+      "epoch": 0.060749240634492066,
+      "eval_loss": 0.9632046222686768,
+      "eval_runtime": 287.8144,
+      "eval_samples_per_second": 4.336,
+      "eval_steps_per_second": 0.542,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0444492974430618e+17,
+  "total_flos": 1.1741738917114675e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null