Training in progress, step 150, checkpoint

last-checkpoint/model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c181850783b51fc1b54edd4fa27053218e7bd9412a9a06d8d85c03b4c0b31b6a
+oid sha256:3927460c5be93662d361e0652583a47649298ad5ffbd120a40a71773cd207aca
 size 4943178720

last-checkpoint/model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62ab75bdfa82032c63e0d69f29df189a216779f0cdc96d4e685ab22ee1e1415
+oid sha256:ff66447d15a6da7419c9fdaae48f2df66754bb12387f3096358548645c8277d0
 size 4999819336

last-checkpoint/model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1685fadb7da58fee532f9124714120dcf3943170b9ecefcae04d272e26d798d
+oid sha256:76dac0c69be005ed49e49458992a7fd3212ea772b71ced9d506db8a08caf089e
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b6cae90969af499a1a0e72b399ed2f5300b48f0f17bd9cf7dc83d7d82bed12
+oid sha256:3cd36532398aa526267b94731fe2352a0a0518b2a340bece982f3f2bd3518fba
 size 14710155092

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9420ac59722557c2d75561b7a80141668226ad32b0226580eab59c780161b06f
+oid sha256:6b1b9f0479324b9b6f1edd389fcd7b47638e6980c8cd3fbd0487a8e891e0040f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeada689887050f844873eed093c0e42e31037d558c794e13e2aaf05bbc18b5b
+oid sha256:2f2227e6ae47e426954edaad47574e1686726548477230bedd0b4f0bf3940388
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23696682464454977,
+  "epoch": 0.35545023696682465,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 13.612,
       "eval_steps_per_second": 6.811,
       "step": 100
+    },
+    {
+      "epoch": 0.26066350710900477,
+      "grad_norm": 87.5,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 4.4561,
+      "step": 110
+    },
+    {
+      "epoch": 0.2843601895734597,
+      "grad_norm": 137.0,
+      "learning_rate": 0.000192,
+      "loss": 4.4283,
+      "step": 120
+    },
+    {
+      "epoch": 0.3080568720379147,
+      "grad_norm": 344.0,
+      "learning_rate": 0.0001999978128380225,
+      "loss": 5.9584,
+      "step": 130
+    },
+    {
+      "epoch": 0.33175355450236965,
+      "grad_norm": 65.0,
+      "learning_rate": 0.0001999803161162393,
+      "loss": 6.4638,
+      "step": 140
+    },
+    {
+      "epoch": 0.35545023696682465,
+      "grad_norm": 114.5,
+      "learning_rate": 0.00019994532573409262,
+      "loss": 7.2027,
+      "step": 150
+    },
+    {
+      "epoch": 0.35545023696682465,
+      "eval_loss": 8.472414016723633,
+      "eval_runtime": 110.8104,
+      "eval_samples_per_second": 13.546,
+      "eval_steps_per_second": 6.777,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.74751783845888e+16,
+  "total_flos": 2.62127675768832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null