Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca2808b22a046cedf32118a5c1ed580c70b08ca00131af3cad76dd0c132ef24b
+oid sha256:7d8bd059b5a07147395db962efee1e0a409645eb6728f8c2b90e3ee61c90cce4
 size 17425352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b96d47e5e7fe7ffbe3fc00ec5febf40414638ad9ab43e2be8b8ac282366fe0f
+oid sha256:b22e887e199dad723e30012306c89bb121f35a85bc00a4f97ad662442f18912b
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78eaecaee821e1ec7f57e3cf3b6f1e7d10081600bd918c707846ea98564fc064
+oid sha256:364110e399b7f87a751563fc89811184979ad9e6b6dece51a29ad2258abb363f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.10465116279069768,
+  "epoch": 0.12558139534883722,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 69.743,
       "eval_steps_per_second": 8.766,
       "step": 45
+    },
+    {
+      "epoch": 0.11162790697674418,
+      "grad_norm": 1.4293689727783203,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 3.9897,
+      "step": 48
+    },
+    {
+      "epoch": 0.1186046511627907,
+      "grad_norm": 1.2574753761291504,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 4.0715,
+      "step": 51
+    },
+    {
+      "epoch": 0.12558139534883722,
+      "grad_norm": 1.068290114402771,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.8083,
+      "step": 54
+    },
+    {
+      "epoch": 0.12558139534883722,
+      "eval_loss": 3.9013290405273438,
+      "eval_runtime": 10.3754,
+      "eval_samples_per_second": 69.78,
+      "eval_steps_per_second": 8.771,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2822103996825600.0,
+  "total_flos": 3386524796190720.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null