Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4a2e987f5fee613a4253c24d4cebfac621c959292090af881732a60c5e9b973
+oid sha256:c9095154cbae6284397a2dedb4aab4b465dcaff71b6633ff70bda59298a99523
 size 692169624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c193606aa2c18b13f8d90abfe7d3862170110ecf3033f8aaf3d0855ef5587da5
+oid sha256:c82b2cc0e87528de455f3edd5f5ecc9587f865f6534d7f1423650f47d2313774
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c983d111d3ec56de2891ca6e215fae2e56304160ac9beb5771ed74d82290b3
+oid sha256:e31a7020ce39d331a4f66b0aac8c3c27ff765a90a9909d8192a4ae0ee079f71a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03314917127071823,
+  "epoch": 0.04419889502762431,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 6.686,
       "eval_steps_per_second": 0.838,
       "step": 27
+    },
+    {
+      "epoch": 0.03683241252302026,
+      "grad_norm": 1.9543025493621826,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 2.5388,
+      "step": 30
+    },
+    {
+      "epoch": 0.040515653775322284,
+      "grad_norm": 2.1249802112579346,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 2.6073,
+      "step": 33
+    },
+    {
+      "epoch": 0.04419889502762431,
+      "grad_norm": 2.4751439094543457,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 2.5199,
+      "step": 36
+    },
+    {
+      "epoch": 0.04419889502762431,
+      "eval_loss": 0.6265907287597656,
+      "eval_runtime": 205.1795,
+      "eval_samples_per_second": 6.687,
+      "eval_steps_per_second": 0.838,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.593811631721677e+16,
+  "total_flos": 1.0125082175628902e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null