Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:820135006e8f542b62482eb19ee364b94abab136b7b8a4413fc390b6f62b73c3
+oid sha256:bb2a6ed2418e724131a02e47f2c81ffc5df3416394ca54f70baceb70eac119db
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9dab2d80004b8909d4d8fd752bfb96ad4dce2d7c56df286126417e073abad01
+oid sha256:35513a652aa9e0e95d1359291721041174bbb1ae68ab2503ceb7b5b5f399530f
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7ca6d811655d83037346c9acab1bd1021739307d82d202ff63fbbb1ceea038
+oid sha256:9fd3a153c7f4fc276e389e31eb4561038460cdb918add1c749f0812d48ee1437
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc61214d825fc5f544783bf7e53e491231850f7439142c284518609f7838f7b3
+oid sha256:c237aae9532ea0601345a50af5d3d3235dec36829be0cbcabbcf22b346088e11
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d30e70950b56357ecf556fa58da2ddb5dde5c9a8f7271bce7669a1e8dfcbe777
+oid sha256:96a890d85cf3909fed97ba692f06a1c1bcd8034fc87a10bc42383393a95d82ff
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04322e2e747379ff005ccb5528da0279e78c7e5a0e7a749a19a62353195571f
+oid sha256:4170a8f5911ad67c847ff011b45564348bd028ac1db6fe944f3c5b069dd64eca
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26846a794e568be1028d1d62c40f80fee62c5e08ae6707128928f5668ddc009f
+oid sha256:daa89ea836ab8c5eee4c19423744e1df919c5d9e032dd5acf39a15943e43448e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7648805975914001,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5700",
-  "epoch": 7.898259705488621,
+  "best_metric": 0.7580859661102295,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6000",
+  "epoch": 8.032128514056225,
   "eval_steps": 100,
-  "global_step": 5900,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -892,6 +892,21 @@
       "eval_samples_per_second": 896.089,
       "eval_steps_per_second": 3.621,
       "step": 5900
+    },
+    {
+      "epoch": 8.032128514056225,
+      "grad_norm": 0.21449404954910278,
+      "learning_rate": 0.00019678714859437752,
+      "loss": 0.6838,
+      "step": 6000
+    },
+    {
+      "epoch": 8.032128514056225,
+      "eval_loss": 0.7580859661102295,
+      "eval_runtime": 6.4002,
+      "eval_samples_per_second": 889.346,
+      "eval_steps_per_second": 3.594,
+      "step": 6000
     }
   ],
   "logging_steps": 100,
@@ -906,7 +921,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -920,7 +935,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.14242397519872e+17,
+  "total_flos": 2.1787362459648e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null