Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1019f64c8b0eead118129c935f4115736c38cd10518de1788c926aadce9bc4
+oid sha256:3880b7fbd04701276dc3b811a1180a8ace690b5a18ef55884d9ef8b429c54e5b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f900bf56433149b0488645dbcdbffa1945104d5372cd826591675ecda329d2d
+oid sha256:74a1403b45f05e1ce4c5c2c597ed0eae24e05809d13e26e11bd19cd0e30bedf2
 size 43122580

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": 0.05193306405077899,
+  "epoch": 0.06231967686093479,
   "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": 13.965,
       "eval_steps_per_second": 1.75,
       "step": 45
+    },
+    {
+      "epoch": 0.05539526832083093,
+      "grad_norm": 4.322741508483887,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 7.5892,
+      "step": 48
+    },
+    {
+      "epoch": 0.058857472590882864,
+      "grad_norm": 3.949061870574951,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 7.5119,
+      "step": 51
+    },
+    {
+      "epoch": 0.06231967686093479,
+      "grad_norm": 4.710406303405762,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 7.8128,
+      "step": 54
+    },
+    {
+      "epoch": 0.06231967686093479,
+      "eval_loss": 1.9215248823165894,
+      "eval_runtime": 104.5083,
+      "eval_samples_per_second": 13.97,
+      "eval_steps_per_second": 1.751,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.309618477170688e+16,
+  "total_flos": 7.571542172604826e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null