Training in progress, step 65000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfbbbdf5e0f7e1e75984b8a87f3e00820c6720f8b58391005c381702a07c4655
+oid sha256:cd99d22f631d655bafa0ef921825bcac2b2df42c1345f4f9a951d158bf615583
 size 891644712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec27daf70b494d2ff8c64e8643c93445ac61cf57d9539ca709da5a21408ca147
+oid sha256:724bb64220f2c161eb3405e2f9cd8e66607b6d55bd8fd225e7c8e74e6dbcc62b
 size 1783444357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb6e27605cfbdbbe56fb86eafa8a4f9c8afa89179aa209cea4a2aad4a0e0629b
+oid sha256:87df364b8a2ed1fef782c858fba27ed776a184876aa3b66d329ff8aa75bd7a24
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cbd243928a750e8ab80bcce9d0d6e45db7cd8c8e143e8c4373b48e856fd52e7
+oid sha256:1452c3e81c52ae774720bef3063ad9b20552f8d2905fb135042cced0dd4241c8
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3904,
+  "epoch": 0.416,
   "eval_steps": 500,
-  "global_step": 61000,
+  "global_step": 65000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -861,6 +861,62 @@
       "learning_rate": 4.024352e-05,
       "loss": 0.3265,
       "step": 61000
+    },
+    {
+      "epoch": 0.3936,
+      "grad_norm": 0.6397412419319153,
+      "learning_rate": 4.0163520000000004e-05,
+      "loss": 0.3268,
+      "step": 61500
+    },
+    {
+      "epoch": 0.3968,
+      "grad_norm": 0.7801005840301514,
+      "learning_rate": 4.0083520000000005e-05,
+      "loss": 0.3314,
+      "step": 62000
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.6966884136199951,
+      "learning_rate": 4.000352e-05,
+      "loss": 0.3263,
+      "step": 62500
+    },
+    {
+      "epoch": 0.4032,
+      "grad_norm": 0.7413304448127747,
+      "learning_rate": 3.9923520000000006e-05,
+      "loss": 0.3284,
+      "step": 63000
+    },
+    {
+      "epoch": 0.4064,
+      "grad_norm": 0.7089780569076538,
+      "learning_rate": 3.984352e-05,
+      "loss": 0.3252,
+      "step": 63500
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 0.6669878959655762,
+      "learning_rate": 3.976352e-05,
+      "loss": 0.3239,
+      "step": 64000
+    },
+    {
+      "epoch": 0.4128,
+      "grad_norm": 0.7352403998374939,
+      "learning_rate": 3.968368e-05,
+      "loss": 0.3226,
+      "step": 64500
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 0.6916635036468506,
+      "learning_rate": 3.9603840000000005e-05,
+      "loss": 0.3234,
+      "step": 65000
     }
   ],
   "logging_steps": 500,
@@ -880,7 +936,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9717145059328e+17,
+  "total_flos": 3.166581030912e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null