Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a073833fe27e1d30e14ff17db75651b68ad3e8a5848732a53ee25fda06078dcc
+oid sha256:3ee1a6461691368769afe9361838d60c5d9fd85bd7d2475feb945e099e128b04
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76b0cde71114fb1478bc1e2be364762451183f58258530575ed2e2b64cd6930c
+oid sha256:afcf5a4374bc9aadc1e2a6f417f4b9344ec32d0f180b2f3ea348d06053622aa4
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1806a9fe2950d45df5ae27410a4d3695e1b86f3fbe3c69545db0325af4115a2c
+oid sha256:fd25efae69fa90a9c45f55963c0cc4d7aa5965e1e67d432e91f378f100616c10
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.033337191804607015,
+  "epoch": 0.037504340780182895,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 24.819,
       "eval_steps_per_second": 3.104,
       "step": 72
+    },
+    {
+      "epoch": 0.03472624146313231,
+      "grad_norm": 0.47662776708602905,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 1.6413,
+      "step": 75
+    },
+    {
+      "epoch": 0.0361152911216576,
+      "grad_norm": 0.48989754915237427,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 1.6976,
+      "step": 78
+    },
+    {
+      "epoch": 0.037504340780182895,
+      "grad_norm": 0.5410365462303162,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 1.6951,
+      "step": 81
+    },
+    {
+      "epoch": 0.037504340780182895,
+      "eval_loss": 1.6343382596969604,
+      "eval_runtime": 146.6418,
+      "eval_samples_per_second": 24.809,
+      "eval_steps_per_second": 3.103,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.024573818096845e+16,
+  "total_flos": 4.52764554535895e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null