Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08847e4297a4f3580c24179e7fad59a879503daea5ad4e402c5ec291963f4d43
+oid sha256:f5fd1bc231ddaa08e3b126ff7e991a61f69316f262668798920494e1cfd3eb74
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22524d1ba9c27d3fbae4a488da1a28690e9bd087957706151576f3bc746fa27
+oid sha256:bb72dcf3db558b98338cf4438a4ae01dfa9fdb1e58f955536ef8ca0579409ec0
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e3d6ff809682f42a3de0e4608089e32d07b128d6b5ad5946f834559794b5091
+oid sha256:f3bee6e11761e71ad6005f6650cd86d99463f2e69e0f2e209868fa0b6569d716
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20243673851921273,
+  "epoch": 0.23617619493908154,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 34.685,
       "eval_steps_per_second": 4.393,
       "step": 54
+    },
+    {
+      "epoch": 0.21368322399250234,
+      "grad_norm": 0.20837906002998352,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 1.818,
+      "step": 57
+    },
+    {
+      "epoch": 0.22492970946579194,
+      "grad_norm": 0.22922676801681519,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 2.0037,
+      "step": 60
+    },
+    {
+      "epoch": 0.23617619493908154,
+      "grad_norm": 0.1948896199464798,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 1.8037,
+      "step": 63
+    },
+    {
+      "epoch": 0.23617619493908154,
+      "eval_loss": 1.9288066625595093,
+      "eval_runtime": 13.0065,
+      "eval_samples_per_second": 34.598,
+      "eval_steps_per_second": 4.382,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.761294214496256e+16,
+  "total_flos": 2.0575118778433536e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null