Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00b3e4d14bfa2e93fb7b485f252d1a537d486247617da04e0d7a00869f3b466
+oid sha256:62a2d8d92b7aec96d9b14e81e189bc382a21f701046b64d2d6c1d3ef716d9aa7
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:467d667b0f7dbcb055a69972708269307511838923df8ff544a1486a01d1e192
+oid sha256:b441fb5dbf3019df142c9903ff4c022684a426738037ca9497630d406c1fa24e
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa924273901c1feaf439a41005e26ed218c16fdbbc3c727286f31e31d59848e
+oid sha256:bfa42d9ab242502b58d07b8b399771dd60f43b4e7a5af9c3ff254d71b99c0a81
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b775d676964eba957907c0ea3d5c5f814cabf4fc06c6838b05e1a89d80849d1
+oid sha256:ae2157ab127357b0e63187d087d7f205cbb57eef57e30a483bf9215a428c1446
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9f0e9fcb3fec99611921d8f34980406ad06f308daea00535e4da9839a46d96
+oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.846153846153847,
+  "epoch": 15.384615384615385,
   "eval_steps": 40,
-  "global_step": 180,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -173,6 +173,28 @@
       "learning_rate": 0.00016772815716257412,
       "loss": 9.597,
       "step": 180
+    },
+    {
+      "epoch": 14.615384615384615,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00016357237482099684,
+      "loss": 9.5534,
+      "step": 190
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00015922352526649803,
+      "loss": 9.5151,
+      "step": 200
+    },
+    {
+      "epoch": 15.384615384615385,
+      "eval_loss": 9.505026817321777,
+      "eval_runtime": 5.2791,
+      "eval_samples_per_second": 284.328,
+      "eval_steps_per_second": 4.546,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -192,7 +214,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 73648538910720.0,
+  "total_flos": 81831709900800.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null