Training in progress, step 48, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:384ed821673440e0c55d6d023a0358c53debfa6ec642c549b2ca0d3a82345d68
+oid sha256:f967a6e912caa29dde25ca3288c033c52ad0f53515a483f7c8fa809fc65a3760
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e5353dd622bb5d97a3055c8b897729d053cfa74bade3e5c0db01e28a8e2f16
+oid sha256:92adf1fefefc8daad7c13159f188bf22733a5d0c335079f978687ad653fa5327
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c027f738a4dfd52c6913eec1699a4b97c1baecedcd1dcbe2a0d7d12892180c4
+oid sha256:da87e4c065bb443c099cfa52ab3a5635819290010328feda7944776129428914
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
+oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013174638820270979,
+  "epoch": 0.014372333258477431,
   "eval_steps": 4,
-  "global_step": 44,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -411,6 +411,42 @@
       "eval_samples_per_second": 8.45,
       "eval_steps_per_second": 8.45,
       "step": 44
+    },
+    {
+      "epoch": 0.013474062429822591,
+      "grad_norm": 34.80168151855469,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 4.7818,
+      "step": 45
+    },
+    {
+      "epoch": 0.013773486039374205,
+      "grad_norm": 25.594444274902344,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 3.0296,
+      "step": 46
+    },
+    {
+      "epoch": 0.014072909648925817,
+      "grad_norm": 39.9898567199707,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 1.9811,
+      "step": 47
+    },
+    {
+      "epoch": 0.014372333258477431,
+      "grad_norm": 58.41755294799805,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 2.8259,
+      "step": 48
+    },
+    {
+      "epoch": 0.014372333258477431,
+      "eval_loss": 3.2478675842285156,
+      "eval_runtime": 83.2404,
+      "eval_samples_per_second": 8.457,
+      "eval_steps_per_second": 8.457,
+      "step": 48
     }
   ],
   "logging_steps": 1,
@@ -430,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6321520238329856e+16,
+  "total_flos": 1.7805294805450752e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null