Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96fd026ef624a6f84ad0ff89e5345ff688c41fbbc411568703eb3ec591d025ee
+oid sha256:f715e13ac1cf8f01095ad62f307817a62bca0dd70bb280eba55d38107fb9cfc1
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:868fe4d204b2c58b39cfd31e2bf2e2f33d3ac041fb6c22bfa23ceeb5ca721319
+oid sha256:3ae07a226eb08d1b539d76011be4858f74af576abcc8d78f1bda8b08492fe8c1
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f68bdd08ef8c010d640dbcb943bd224f2fe4d6bf3fd98664a4344e6b763f74fd
+oid sha256:1904e9631f3de0f38c36bf510b3348b6ef69cff731b4a358841188654a9146e7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e482854e4ff3c178dda878d03bf3633330934a775fc818e1843bd607d65d07
+oid sha256:6080dc3c4f31046c753abd07ed5f1a8449e11695e9772af37e8337628bc01d7f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4685615003108978,
-  "best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-500",
-  "epoch": 19.607843137254903,
+  "best_metric": 0.42764008045196533,
+  "best_model_checkpoint": "mikhail-panzo/ceb_b64_le5_s8000/checkpoint-1000",
+  "epoch": 39.21568627450981,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,84 @@
       "eval_samples_per_second": 28.192,
       "eval_steps_per_second": 3.602,
       "step": 500
+    },
+    {
+      "epoch": 21.568627450980394,
+      "grad_norm": 1.5475994348526,
+      "learning_rate": 2.7450000000000004e-06,
+      "loss": 0.5407,
+      "step": 550
+    },
+    {
+      "epoch": 23.529411764705884,
+      "grad_norm": 1.1005382537841797,
+      "learning_rate": 2.995e-06,
+      "loss": 0.5076,
+      "step": 600
+    },
+    {
+      "epoch": 25.49019607843137,
+      "grad_norm": 0.979748547077179,
+      "learning_rate": 3.2450000000000003e-06,
+      "loss": 0.5071,
+      "step": 650
+    },
+    {
+      "epoch": 27.45098039215686,
+      "grad_norm": 1.0884859561920166,
+      "learning_rate": 3.495e-06,
+      "loss": 0.4934,
+      "step": 700
+    },
+    {
+      "epoch": 29.41176470588235,
+      "grad_norm": 1.8463184833526611,
+      "learning_rate": 3.745e-06,
+      "loss": 0.4919,
+      "step": 750
+    },
+    {
+      "epoch": 31.372549019607842,
+      "grad_norm": 1.2262991666793823,
+      "learning_rate": 3.995000000000001e-06,
+      "loss": 0.4981,
+      "step": 800
+    },
+    {
+      "epoch": 33.333333333333336,
+      "grad_norm": 1.0878300666809082,
+      "learning_rate": 4.245e-06,
+      "loss": 0.4928,
+      "step": 850
+    },
+    {
+      "epoch": 35.294117647058826,
+      "grad_norm": 1.155561089515686,
+      "learning_rate": 4.495e-06,
+      "loss": 0.4848,
+      "step": 900
+    },
+    {
+      "epoch": 37.254901960784316,
+      "grad_norm": 1.4933425188064575,
+      "learning_rate": 4.745e-06,
+      "loss": 0.4754,
+      "step": 950
+    },
+    {
+      "epoch": 39.21568627450981,
+      "grad_norm": 1.239863634109497,
+      "learning_rate": 4.9950000000000005e-06,
+      "loss": 0.4756,
+      "step": 1000
+    },
+    {
+      "epoch": 39.21568627450981,
+      "eval_loss": 0.42764008045196533,
+      "eval_runtime": 6.3802,
+      "eval_samples_per_second": 28.212,
+      "eval_steps_per_second": 3.605,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -104,7 +182,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5442492972673152.0,
+  "total_flos": 1.088442385035588e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null