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:b3467bbb771c27792973c3bb91cacc07bad38f226f51b57c7f0fb94057a64241
+oid sha256:6f480316a575e338d5af8265942ce374693b0167b595124cd72a9d2e2d5c733d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761d3d7fcb5f17e9ea1c4e0607535483bcac655556597b60cd615e79af634e7f
+oid sha256:4b1285f90a2f58e155d5c480f6110387a69e5846e254e2b3f76b4bae59c20754
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4f63aec6d8b3291c19fe2b4497f750eeddd6b87b84886cefc94a6bfc39de55
+oid sha256:d74b05f2720b311440022765a28fc8006a7374957aaca6aca1b5e6bc5db4cbaa
 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": 0.002443107270506266,
+  "epoch": 0.0032574763606750216,
   "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": 12.93,
       "eval_steps_per_second": 1.617,
       "step": 27
+    },
+    {
+      "epoch": 0.0027145636338958513,
+      "grad_norm": 3.188636541366577,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.4312,
+      "step": 30
+    },
+    {
+      "epoch": 0.0029860199972854364,
+      "grad_norm": 2.3065080642700195,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.6207,
+      "step": 33
+    },
+    {
+      "epoch": 0.0032574763606750216,
+      "grad_norm": 1.9325222969055176,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.5588,
+      "step": 36
+    },
+    {
+      "epoch": 0.0032574763606750216,
+      "eval_loss": 0.5455918908119202,
+      "eval_runtime": 1439.2701,
+      "eval_samples_per_second": 12.932,
+      "eval_steps_per_second": 1.617,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.899307929370624e+16,
+  "total_flos": 5.199077239160832e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null