Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55d9137c72c4a4b12bb5c63cf090f1541ef029e09f00091887b860978d532cc9
+oid sha256:4994d483f9785dc0bde6ccbfb3120d5bfabdb973e7f9f830d964085711981e0d
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63ff8f1b33013b0b7c62688949dac6ee9415ba236119c61ab9a531a0c03256c
+oid sha256:5b1791423eb620649f3992e17cc9bcf7179df7f2e283690b43a17f7bc25c59c8
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0bb62c383dd93bb7277f2f4f3ecc51f45d7c7b1a6c0012d26a10c5589360f2
+oid sha256:6122816c42780a868d77d7c48cf66d125e516c03075f49e683bda8693a41f3d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.038338658146964855,
+  "epoch": 0.07667731629392971,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 36.265,
       "eval_steps_per_second": 4.59,
       "step": 9
+    },
+    {
+      "epoch": 0.051118210862619806,
+      "grad_norm": 1.2419706583023071,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 1.017,
+      "step": 12
+    },
+    {
+      "epoch": 0.06389776357827476,
+      "grad_norm": 0.8883413672447205,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.9621,
+      "step": 15
+    },
+    {
+      "epoch": 0.07667731629392971,
+      "grad_norm": 1.3165100812911987,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.7864,
+      "step": 18
+    },
+    {
+      "epoch": 0.07667731629392971,
+      "eval_loss": 0.7199711799621582,
+      "eval_runtime": 10.8865,
+      "eval_samples_per_second": 36.284,
+      "eval_steps_per_second": 4.593,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2351283906281472.0,
+  "total_flos": 4702567812562944.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null