Training in progress, step 6100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2a6ed2418e724131a02e47f2c81ffc5df3416394ca54f70baceb70eac119db
+oid sha256:67c34ba597a5c81ced1d39b217a0c23c258e10ff6753c4df538802d18ce5e628
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35513a652aa9e0e95d1359291721041174bbb1ae68ab2503ceb7b5b5f399530f
+oid sha256:f6f899c00d47f39bb7388c3f058992fd87e8876c1cc3304647873a123f22ed96
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd3a153c7f4fc276e389e31eb4561038460cdb918add1c749f0812d48ee1437
+oid sha256:373381e1af0a7bd8f556a1461be5145a00f7ca5c3f9b98fdd6aa1a1866e01871
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c237aae9532ea0601345a50af5d3d3235dec36829be0cbcabbcf22b346088e11
+oid sha256:8054d9536c9328179ffe89e113671755f845d619eca4ba0428dce64587ae20ff
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a890d85cf3909fed97ba692f06a1c1bcd8034fc87a10bc42383393a95d82ff
+oid sha256:0b3efc810bd5e02520ea4047772206af56b66c4663e317c3c18bbf1aacf3ccf3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4170a8f5911ad67c847ff011b45564348bd028ac1db6fe944f3c5b069dd64eca
+oid sha256:80455bdd5f9d0849480e1ae2cd0f431ae5c19bbf0c5a630d843b2e838f480ce1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa89ea836ab8c5eee4c19423744e1df919c5d9e032dd5acf39a15943e43448e
+oid sha256:12bba307a2dbb51e1fe4a814ce6fd6fcd90ba49bffaa9b023d0750076d62c718
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7580859661102295,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-6000",
-  "epoch": 8.032128514056225,
+  "epoch": 8.165997322623829,
   "eval_steps": 100,
-  "global_step": 6000,
+  "global_step": 6100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -907,6 +907,21 @@
       "eval_samples_per_second": 889.346,
       "eval_steps_per_second": 3.594,
       "step": 6000
+    },
+    {
+      "epoch": 8.165997322623829,
+      "grad_norm": 0.2097356915473938,
+      "learning_rate": 0.00018340026773761714,
+      "loss": 0.6789,
+      "step": 6100
+    },
+    {
+      "epoch": 8.165997322623829,
+      "eval_loss": 0.7637941241264343,
+      "eval_runtime": 6.4327,
+      "eval_samples_per_second": 884.859,
+      "eval_steps_per_second": 3.576,
+      "step": 6100
     }
   ],
   "logging_steps": 100,
@@ -921,7 +936,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -935,7 +950,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1787362459648e+17,
+  "total_flos": 2.21504851673088e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null