Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2ccb1201adc7ba3dce45c039a56a518750657ba48b9dc6407631be5a9ec0851
+oid sha256:9a594d700ae7ced351be9f9fa205e77a1c04484c30562fc301b8498ded4627f7
 size 1426462208

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a11c2381fc62f5a000590233a5f5371a956d9b0994b73d666ec134c93e250cb3
+oid sha256:2409b4f78e63edadb2a0bf9adfb64ff1e7e25ec40d11b7709030002d2cded2e1
 size 2853107898

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18651009765668713,
+  "epoch": 0.2797651464850307,
   "eval_steps": 500,
-  "global_step": 400000,
+  "global_step": 600000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,146 @@
       "learning_rate": 4.067789892644788e-05,
       "loss": 2.6014,
       "step": 400000
+    },
+    {
+      "epoch": 0.1911728500981043,
+      "grad_norm": 0.8321977257728577,
+      "learning_rate": 4.044485455942585e-05,
+      "loss": 2.5964,
+      "step": 410000
+    },
+    {
+      "epoch": 0.19583560253952148,
+      "grad_norm": 1.3375693559646606,
+      "learning_rate": 4.021178687864161e-05,
+      "loss": 2.5906,
+      "step": 420000
+    },
+    {
+      "epoch": 0.20049835498093868,
+      "grad_norm": 0.8211286067962646,
+      "learning_rate": 3.997874251161958e-05,
+      "loss": 2.5866,
+      "step": 430000
+    },
+    {
+      "epoch": 0.20516110742235585,
+      "grad_norm": 0.7890422940254211,
+      "learning_rate": 3.9745698144597546e-05,
+      "loss": 2.5817,
+      "step": 440000
+    },
+    {
+      "epoch": 0.20982385986377303,
+      "grad_norm": 1.0580294132232666,
+      "learning_rate": 3.951263046381331e-05,
+      "loss": 2.5776,
+      "step": 450000
+    },
+    {
+      "epoch": 0.2144866123051902,
+      "grad_norm": 1.0666168928146362,
+      "learning_rate": 3.927956278302907e-05,
+      "loss": 2.5729,
+      "step": 460000
+    },
+    {
+      "epoch": 0.21914936474660737,
+      "grad_norm": 1.0440067052841187,
+      "learning_rate": 3.904651841600704e-05,
+      "loss": 2.5748,
+      "step": 470000
+    },
+    {
+      "epoch": 0.22381211718802457,
+      "grad_norm": 0.8746099472045898,
+      "learning_rate": 3.88134507352228e-05,
+      "loss": 2.5704,
+      "step": 480000
+    },
+    {
+      "epoch": 0.22847486962944175,
+      "grad_norm": 0.882897675037384,
+      "learning_rate": 3.858040636820078e-05,
+      "loss": 2.5623,
+      "step": 490000
+    },
+    {
+      "epoch": 0.23313762207085892,
+      "grad_norm": 0.8458369970321655,
+      "learning_rate": 3.834740862870316e-05,
+      "loss": 2.5612,
+      "step": 500000
+    },
+    {
+      "epoch": 0.2378003745122761,
+      "grad_norm": 0.9579658508300781,
+      "learning_rate": 3.811434094791892e-05,
+      "loss": 2.5551,
+      "step": 510000
+    },
+    {
+      "epoch": 0.24246312695369326,
+      "grad_norm": 1.0498722791671753,
+      "learning_rate": 3.78813198946591e-05,
+      "loss": 2.5502,
+      "step": 520000
+    },
+    {
+      "epoch": 0.24712587939511046,
+      "grad_norm": 1.032334804534912,
+      "learning_rate": 3.764825221387486e-05,
+      "loss": 2.5534,
+      "step": 530000
+    },
+    {
+      "epoch": 0.2517886318365276,
+      "grad_norm": 0.9145790934562683,
+      "learning_rate": 3.7415184533090624e-05,
+      "loss": 2.547,
+      "step": 540000
+    },
+    {
+      "epoch": 0.2564513842779448,
+      "grad_norm": 1.0633904933929443,
+      "learning_rate": 3.71821634798308e-05,
+      "loss": 2.543,
+      "step": 550000
+    },
+    {
+      "epoch": 0.261114136719362,
+      "grad_norm": 0.9828123450279236,
+      "learning_rate": 3.694911911280877e-05,
+      "loss": 2.5398,
+      "step": 560000
+    },
+    {
+      "epoch": 0.2657768891607792,
+      "grad_norm": 0.8735861778259277,
+      "learning_rate": 3.671607474578674e-05,
+      "loss": 2.5345,
+      "step": 570000
+    },
+    {
+      "epoch": 0.27043964160219636,
+      "grad_norm": 1.1347264051437378,
+      "learning_rate": 3.6483053692526915e-05,
+      "loss": 2.5312,
+      "step": 580000
+    },
+    {
+      "epoch": 0.27510239404361353,
+      "grad_norm": 0.8275557160377502,
+      "learning_rate": 3.625000932550489e-05,
+      "loss": 2.5299,
+      "step": 590000
+    },
+    {
+      "epoch": 0.2797651464850307,
+      "grad_norm": 0.8891148567199707,
+      "learning_rate": 3.601696495848285e-05,
+      "loss": 2.5301,
+      "step": 600000
     }
   ],
   "logging_steps": 10000,
@@ -306,7 +446,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.86304678504589e+18,
+  "total_flos": 1.4794966500590223e+19,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null