Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b5a502fe2912e547b3587aa7130918c57e01be8c57f6e1cb2a5b8b828748d72
+oid sha256:ce5ee95e06177970efe3c81f38c0e450a3056c458412289eb8b337dc8f92b2f8
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11472b17789b8da64c6c4f6ee24288794b69156872a806498e0e9050a6585482
+oid sha256:545fe6baf339b186bb782a916c966886881a543e22c399ebe19a020de1c4f110
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124625e167eb28acbfc793cfcb3e8a08b32e7fea06501462bc9e420a5e1beb2a
+oid sha256:30af866df24edce708e1eb20700878b402fa05707fa9bc5f332496baf440dbbb
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9772b1095a18bdc0dac6da07c88a52ebb0235e5a005dde3b5ccb9399535eb49d
+oid sha256:da8c069932bbe17678ad03a8f86ba70ed86e66ece4d5449de499aa9836bd050a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05,
+  "epoch": 0.075,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,76 @@
       "learning_rate": 0.00029238461538461536,
       "loss": 104.3275146484375,
       "step": 200
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 13.086603164672852,
+      "learning_rate": 0.00029161538461538463,
+      "loss": 105.60206298828125,
+      "step": 210
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 17.55739402770996,
+      "learning_rate": 0.0002908461538461538,
+      "loss": 102.73480224609375,
+      "step": 220
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 18.34480094909668,
+      "learning_rate": 0.00029007692307692306,
+      "loss": 100.7387939453125,
+      "step": 230
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 13.852744102478027,
+      "learning_rate": 0.0002893076923076923,
+      "loss": 101.04940795898438,
+      "step": 240
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 13.510031700134277,
+      "learning_rate": 0.0002885384615384615,
+      "loss": 101.42539672851562,
+      "step": 250
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 15.467084884643555,
+      "learning_rate": 0.00028776923076923077,
+      "loss": 99.12225341796875,
+      "step": 260
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 15.127578735351562,
+      "learning_rate": 0.000287,
+      "loss": 96.99212646484375,
+      "step": 270
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 13.582677841186523,
+      "learning_rate": 0.0002862307692307692,
+      "loss": 99.32898559570313,
+      "step": 280
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 14.728398323059082,
+      "learning_rate": 0.0002854615384615384,
+      "loss": 97.85962524414063,
+      "step": 290
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 14.059552192687988,
+      "learning_rate": 0.0002846923076923077,
+      "loss": 97.9947509765625,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -167,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3395460080586240.0,
+  "total_flos": 5059232948390400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null