Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15540cfa36234f25a067d39704854b76c3f5d925588adf9237e980d0831fcb6d
+oid sha256:704acbda212196abe32b0917069da059a8d16ff3c8da4bba242bb7d196aedb99
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c13befdc66e895338fc6cd3fb7d02853761b6fa621ac11dac6d8335b6514800c
+oid sha256:01a5c7efe72979b1344ed58a551e0ac819eb88a325f957f382bc36aa206dbcf8
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a15f8b7e107d1944aa714244b7981525070751630348b2f99259785cab9c85cb
+oid sha256:87951bd1d28cfc789427636c05788fc21db0e7e40be21589b4278413c44c66bd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007956856157722571,
+  "epoch": 0.009548227389267085,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 14.101,
       "eval_steps_per_second": 1.763,
       "step": 45
+    },
+    {
+      "epoch": 0.008487313234904075,
+      "grad_norm": 4.028677940368652,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.8459,
+      "step": 48
+    },
+    {
+      "epoch": 0.009017770312085581,
+      "grad_norm": 4.294224739074707,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.8475,
+      "step": 51
+    },
+    {
+      "epoch": 0.009548227389267085,
+      "grad_norm": 3.748793840408325,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.9537,
+      "step": 54
+    },
+    {
+      "epoch": 0.009548227389267085,
+      "eval_loss": 0.7180169224739075,
+      "eval_runtime": 675.8048,
+      "eval_samples_per_second": 14.094,
+      "eval_steps_per_second": 1.762,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.328172735889408e+16,
+  "total_flos": 7.59380728306729e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null