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:ab3c6c30be30d002c9bdb888b5b51dcd1032f1ed3600ae01f1dd544de2e99f52
+oid sha256:7857b1437a88ff9e1fdaa0b6c2e3c4daf6b6387ea38830b6e73c5c06033c3150
 size 4943178720

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b7deaad79314a2043c763969d6a803e98dc491daa862efa58a7f54a22f4410
+oid sha256:bd52fbfc22254e7e1622049afc0254da299acce2aa1340ae8381b441117fb64f
 size 4999819336

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4274c40f1493eb14129f4621c74c1fabcbc7e4e381228bc6a5f4cdee5547cdd5
+oid sha256:2d885d8c8c5995e84f01d8df318ab80138e6b735dd47ba729a289f2cd292dafe
 size 4540532728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f2ddc52625275a965f3a109531a19102ed2af5bf842fd054c81e4317fd46f90
+oid sha256:dcdf990af1fbeae7a7ccd40f7824862f8691ea0ac3ffde923eb0be58dca9f806
 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": 13.57,
       "eval_steps_per_second": 6.789,
       "step": 100
+    },
+    {
+      "epoch": 0.26066350710900477,
+      "grad_norm": 47.0,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 4.0304,
+      "step": 110
+    },
+    {
+      "epoch": 0.2843601895734597,
+      "grad_norm": 94.5,
+      "learning_rate": 0.000192,
+      "loss": 5.1359,
+      "step": 120
+    },
+    {
+      "epoch": 0.3080568720379147,
+      "grad_norm": 244.0,
+      "learning_rate": 0.0001999978128380225,
+      "loss": 5.2136,
+      "step": 130
+    },
+    {
+      "epoch": 0.33175355450236965,
+      "grad_norm": 74.0,
+      "learning_rate": 0.0001999803161162393,
+      "loss": 5.6738,
+      "step": 140
+    },
+    {
+      "epoch": 0.35545023696682465,
+      "grad_norm": 22.375,
+      "learning_rate": 0.00019994532573409262,
+      "loss": 5.4572,
+      "step": 150
+    },
+    {
+      "epoch": 0.35545023696682465,
+      "eval_loss": 5.4177703857421875,
+      "eval_runtime": 110.5332,
+      "eval_samples_per_second": 13.58,
+      "eval_steps_per_second": 6.794,
+      "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