Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2767e1a9696d3fc22d045d15b5be281656eafc9c5e7a1f72b729cae1e8e681c9
+oid sha256:6383a994356d2d5807ca12d4ac064319e6dceecb77f7545dd8de5f9dd85bf414
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30c5060550e6f184b17b91286b39a72e6dc03b925bda255bd2d080d5cf953d4a
+oid sha256:13223e3411fc2b15d19a767fdaea673c867083b3932de3662b372c127602ef6c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375821e39d2967b7ee28fa23c79e88e8d298ace5c697b299efe87ae74b6d7087
+oid sha256:fd8d600d482e23e3ca867dd9393eea90ad7988cda5e7fe71bdb3e78ed1ae286c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0869265263884098,
+  "epoch": 0.09934460158675405,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 7.138,
       "eval_steps_per_second": 0.894,
       "step": 63
+    },
+    {
+      "epoch": 0.09106588478785788,
+      "grad_norm": 2.911757230758667,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.528,
+      "step": 66
+    },
+    {
+      "epoch": 0.09520524318730597,
+      "grad_norm": 3.0450966358184814,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 0.651,
+      "step": 69
+    },
+    {
+      "epoch": 0.09934460158675405,
+      "grad_norm": 3.033231019973755,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.5592,
+      "step": 72
+    },
+    {
+      "epoch": 0.09934460158675405,
+      "eval_loss": 0.16376812756061554,
+      "eval_runtime": 171.1546,
+      "eval_samples_per_second": 7.134,
+      "eval_steps_per_second": 0.894,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.771886336676987e+17,
+  "total_flos": 2.0250129562022707e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null