Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60dd3854bf6d29a499964e4f11098e6810ae98c6bb0e872b79a72f6fa033c8c4
+oid sha256:62532d5f8e21eb02dc93bec707dc21d939ae8d4751f4be929d9a7303a2dbfa3c
 size 247936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb03c27b6f613e4ad09ed2d22c9aaee953dea497b1d6d962401a302e0756f3c
+oid sha256:f7afdaa4aa3fd94db2282fab43e0da35f8dcc2e7065253cbea7e606c7806065a
 size 263024

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:add90063e1e616d6ac6be40dd95ded3a73a340bb31303d1ec63f0b2f30524740
+oid sha256:87e3e3253b1e11d5b911b90c9d12eee8f8449ea7e8df10ad506caaaaa9049447
 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": 0.05115089514066496,
+  "epoch": 0.061381074168797956,
   "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": 155.4,
       "eval_steps_per_second": 39.007,
       "step": 45
+    },
+    {
+      "epoch": 0.05456095481670929,
+      "grad_norm": 1.0063976049423218,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 43.9744,
+      "step": 48
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 1.0805094242095947,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 43.7906,
+      "step": 51
+    },
+    {
+      "epoch": 0.061381074168797956,
+      "grad_norm": 1.041139841079712,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 43.8027,
+      "step": 54
+    },
+    {
+      "epoch": 0.061381074168797956,
+      "eval_loss": 10.949912071228027,
+      "eval_runtime": 4.7641,
+      "eval_samples_per_second": 155.537,
+      "eval_steps_per_second": 39.042,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 397116702720.0,
+  "total_flos": 481917665280.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null