Training in progress, step 27, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fd693e6ff375d02b620f26b32b599b5d1e4169fd83778fa25461beaa297299
+oid sha256:b3467bbb771c27792973c3bb91cacc07bad38f226f51b57c7f0fb94057a64241
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:787b784a4a6dd4e5c7e961f2510701b0001417d07c97fa1315af87db5dc03e92
+oid sha256:761d3d7fcb5f17e9ea1c4e0607535483bcac655556597b60cd615e79af634e7f
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
+oid sha256:2b4f63aec6d8b3291c19fe2b4497f750eeddd6b87b84886cefc94a6bfc39de55
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
+oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0016287381803375108,
+  "epoch": 0.002443107270506266,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 12.935,
       "eval_steps_per_second": 1.617,
       "step": 18
+    },
+    {
+      "epoch": 0.001900194543727096,
+      "grad_norm": 2.2299928665161133,
+      "learning_rate": 4.817959636416969e-05,
+      "loss": 0.5779,
+      "step": 21
+    },
+    {
+      "epoch": 0.002171650907116681,
+      "grad_norm": 3.2380049228668213,
+      "learning_rate": 4.707368982147318e-05,
+      "loss": 0.6919,
+      "step": 24
+    },
+    {
+      "epoch": 0.002443107270506266,
+      "grad_norm": 2.030574321746826,
+      "learning_rate": 4.572593931387604e-05,
+      "loss": 0.4923,
+      "step": 27
+    },
+    {
+      "epoch": 0.002443107270506266,
+      "eval_loss": 0.5967397689819336,
+      "eval_runtime": 1439.4951,
+      "eval_samples_per_second": 12.93,
+      "eval_steps_per_second": 1.617,
+      "step": 27
     }
   ],
   "logging_steps": 3,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.599538619580416e+16,
+  "total_flos": 3.899307929370624e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null