Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b83195d21b6b2db80d21d66897a32786856ff6cab713cc9fb50a7218a25b8b0
+oid sha256:47e1147544a530bb9b8865b89f7abba07b82f5604ba6a7521dfb0f3004b47001
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17e424ce26416c7231018c5ad6ae9de79a5aabe166485512f1576a674256cfc1
+oid sha256:9aa188749df7b1e981e2afd8916a9f92f2ce4dac662e7d255722e60f44f6963e
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a083a129159440f3f40c21dbf044f9db32e87979479354f79b35c86bfc3bdd
+oid sha256:d8874dd5e607118e18f489ed9ad8aaab7c3de4c272a2acaa47fb9a2cd05a480a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e33da60be502927a2afa2046e81eb3da1ce22fa49e674a279bab92f8b0f7cf7
+oid sha256:605d23f463d574da26fdafa2a2fc396d0b00160053ea75ca175c5c8e6f2990e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004992589125516811,
+  "epoch": 0.009985178251033622,
   "eval_steps": 8,
-  "global_step": 8,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 9.397,
       "eval_steps_per_second": 4.699,
       "step": 8
+    },
+    {
+      "epoch": 0.005616662766206412,
+      "grad_norm": 2.2846736907958984,
+      "learning_rate": 9e-05,
+      "loss": 1.6608,
+      "step": 9
+    },
+    {
+      "epoch": 0.007488883688275216,
+      "grad_norm": 1.0156153440475464,
+      "learning_rate": 0.00012,
+      "loss": 1.1555,
+      "step": 12
+    },
+    {
+      "epoch": 0.00936110461034402,
+      "grad_norm": 0.878858208656311,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.9501,
+      "step": 15
+    },
+    {
+      "epoch": 0.009985178251033622,
+      "eval_loss": 0.856473982334137,
+      "eval_runtime": 574.4848,
+      "eval_samples_per_second": 9.396,
+      "eval_steps_per_second": 4.698,
+      "step": 16
     }
   ],
   "logging_steps": 3,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.256153676546048e+16,
+  "total_flos": 8.512307353092096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null