Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a53818166c997a5f044919047269de5637df30c7f3e35e43de5a49620a745bac
+oid sha256:c36e0e6e72d331231c75519120e36a9242a8bff07537a0f65827a336f1b79a44
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28dd6e6307fa015e692b6b556932fde5666659c25197be0bf989d11c190341f1
+oid sha256:99f20a54dee8d027bcc9bbaea42ff161e8cbba806bb3f35869be2a2f744d29fc
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6371144a111a3072f591f746239d824c555a871e29310d8421824db33cb69d80
+oid sha256:7b9a2678740824fb589a72819ef8a2601a1af7909330828a265812e5b5ff9c95
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc12850c9ff9801525024d9966df4799da11201038cba4971a720ddadfcd7ec
+oid sha256:db973c8a6e8032795aca2e0edfd5e46b92aea774c79981d12eef1bcb25c3d7d4
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb0e11d33e42a9adcc5c976e37e059307e91eb6ae74c969ff1b3eb2f755782d6
+oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.538461538461538,
+  "epoch": 15.384615384615385,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 284.626,
       "eval_steps_per_second": 4.551,
       "step": 150
+    },
+    {
+      "epoch": 12.307692307692308,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00017541066097768963,
+      "loss": 9.688,
+      "step": 160
+    },
+    {
+      "epoch": 13.076923076923077,
+      "grad_norm": 0.3671875,
+      "learning_rate": 0.00017167825131684513,
+      "loss": 9.6416,
+      "step": 170
+    },
+    {
+      "epoch": 13.846153846153847,
+      "grad_norm": 0.375,
+      "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": 9.504176139831543,
+      "eval_runtime": 5.2799,
+      "eval_samples_per_second": 284.283,
+      "eval_steps_per_second": 4.545,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -163,7 +206,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 61373782425600.0,
+  "total_flos": 81831709900800.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null