Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8fd5a7536117c9c062de23e712483ef97335539634fc37acbd2b48196af6f9
+oid sha256:e4c47c98706ac885a6c8437da9683a1593f1032ded7136cd6759c0419f916dc3
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc4f6740a3132d96407fcd57d951c890a713b0cea99fcd07cb7ea2d7143d7ef
+oid sha256:8ae9a8831bc8e209796beab3e8ad749ceb23d9e8eebbcd7dde9fe104ad3050ac
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49324b9e90e4a3300216fe09ec318d103f16e5de8c543c825c0b873b9acee835
+oid sha256:eaee9e6e7f084eb979a4fae1379973889d676dd05a81fe8ebfd03a9e10f90444
 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": 0.029258777633289986,
+  "epoch": 0.035110533159947985,
   "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": 11.046,
       "eval_steps_per_second": 1.381,
       "step": 45
+    },
+    {
+      "epoch": 0.031209362808842653,
+      "grad_norm": 1.0278661251068115,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 4.7762,
+      "step": 48
+    },
+    {
+      "epoch": 0.03315994798439532,
+      "grad_norm": 0.9808676838874817,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 4.5895,
+      "step": 51
+    },
+    {
+      "epoch": 0.035110533159947985,
+      "grad_norm": 0.8073239326477051,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 4.7345,
+      "step": 54
+    },
+    {
+      "epoch": 0.035110533159947985,
+      "eval_loss": 1.152621865272522,
+      "eval_runtime": 234.5525,
+      "eval_samples_per_second": 11.047,
+      "eval_steps_per_second": 1.381,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.881181799186432e+16,
+  "total_flos": 7.057418159023718e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null