Training in progress, step 600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fbc31f895cb43b2fbf61441b4473d2cb8b833fec71ce0779fba7d0189727b7f
+oid sha256:2f884461b0966040f287943ef2ca62cd744cc3fb7ff6b2972e7dabf03eeb5fc8
 size 1235573136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5fb98da8a9f480baf5d2b95306b99d89e0e9d5228b7991cda12d800c4c375b
+oid sha256:ec055f970e5dfe7ce2d2ecc90396ffad38bf275b1d6a02844a1a9f3ac765ff13
 size 2471218763

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
+oid sha256:cb7fde5111803012042c93a73aa191336bb6e10b3ad44f6bd1d94fc7008a22b6
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12afa616253873716385d59b59f53f0a26b35b0747a1fa754d94617f51e7fa69
+oid sha256:b711533995c64c2cee501d3c0e16e1be76367e166e30293a3e9a77679128482b
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.125,
+  "epoch": 0.15,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -358,6 +358,76 @@
       "learning_rate": 0.0002693076923076923,
       "loss": 87.786767578125,
       "step": 500
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 12.950383186340332,
+      "learning_rate": 0.0002685384615384615,
+      "loss": 87.12896118164062,
+      "step": 510
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 12.832451820373535,
+      "learning_rate": 0.00026776923076923077,
+      "loss": 88.82958374023437,
+      "step": 520
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 14.343534469604492,
+      "learning_rate": 0.000267,
+      "loss": 87.53173217773437,
+      "step": 530
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 11.609414100646973,
+      "learning_rate": 0.0002662307692307692,
+      "loss": 86.57319946289063,
+      "step": 540
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 13.554574012756348,
+      "learning_rate": 0.00026546153846153847,
+      "loss": 87.31171264648438,
+      "step": 550
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 14.38441276550293,
+      "learning_rate": 0.0002646923076923077,
+      "loss": 85.79506225585938,
+      "step": 560
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 12.652528762817383,
+      "learning_rate": 0.0002639230769230769,
+      "loss": 86.28104248046876,
+      "step": 570
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 12.158783912658691,
+      "learning_rate": 0.0002631538461538461,
+      "loss": 85.13269653320313,
+      "step": 580
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 13.032898902893066,
+      "learning_rate": 0.00026238461538461534,
+      "loss": 85.8595458984375,
+      "step": 590
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 14.406429290771484,
+      "learning_rate": 0.0002616153846153846,
+      "loss": 86.73550415039062,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -377,7 +447,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8373582374722560.0,
+  "total_flos": 1.00712760885504e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null