Training in progress, step 2400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d727907d193aef09e2a9d80365acb6f2462a20c6a4bbe793bc592fe7653384
+oid sha256:0e70d948b14eeb2738c622c9062216d0b8e2a32126d68081cae366880231148b
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14db266b84b7a4fd9c6961d6cbddc96684ca7a5facf6bbc70686999fceb9b40f
+oid sha256:7ce78e97c8ae69598891ec67aee3926e6b331920bcd79fa081e823d88bd33450
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee07e8dcd8ba9e44bfd4964110f49118b76a8cef649358084a25ac12aea38df8
+oid sha256:0a930774a621d4d5d809c7d64a221ff6bd07ed23f3ed097b50736aabef7637e5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef8ba89520738b13bda5df191bb09dcdf29a49633395376036fac6c7c910b7e
+oid sha256:0e3d5b90f1e82706bb6a590340582d4016e7c5e4792a715e2f622fe917104775
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:982c6813cdea3b949eb3e7af3ec5f20a06ee4f7d374e292b05a8b646d098fd83
+oid sha256:953299768136249cbeaf35052c07f5beaddf92b3ed6807401fc342d1f3ce8a19
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba15cb4748b341969934bf30614b73106ba62fd6173231a4135f3d41ad085f55
+oid sha256:605e0299f66122c6d4f906277dccc7352e4b84e55889db022b63c776ad810b8b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c45ce9ebd2e6f751801c4dc4b8d6cab111bdc01864bb53ac8fcc86dd2f2927
+oid sha256:33272a1400e7968fc81a41e0dd087f4d4d92e5236ea466e9bc96e6973620ac72
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8286001682281494,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2300",
-  "epoch": 3.0789825970548863,
+  "best_metric": 0.8264986872673035,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-2400",
+  "epoch": 3.21285140562249,
   "eval_steps": 100,
-  "global_step": 2300,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -352,6 +352,21 @@
       "eval_samples_per_second": 882.942,
       "eval_steps_per_second": 3.568,
       "step": 2300
+    },
+    {
+      "epoch": 3.21285140562249,
+      "grad_norm": 0.1851571649312973,
+      "learning_rate": 0.000678714859437751,
+      "loss": 0.8181,
+      "step": 2400
+    },
+    {
+      "epoch": 3.21285140562249,
+      "eval_loss": 0.8264986872673035,
+      "eval_runtime": 6.3671,
+      "eval_samples_per_second": 893.972,
+      "eval_steps_per_second": 3.612,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
@@ -380,7 +395,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.3518222761984e+16,
+  "total_flos": 8.7149449838592e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null