Training in progress, step 3500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa079d8f5f78ad05341ea236d2ade00e651277862b68a4130ace8f1920e4fc26
+oid sha256:08313b42957f67090aa115244b6a6aee90773239492ec422bd4cdc2a87eb25df
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:507a453e50f7a1b01e314911b48daf7d2393ad033c1524e967270d46aa02b89b
+oid sha256:fdc2214200b5403f71680f201b18760342827e59a59311c7e771aa14cee56c96
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83839fd075ba66694d3c368de69d75c341a9c5fab798f9cc50c55f617f5662ea
+oid sha256:98cfffb13124b787eca8198f34dff7a12f16b165a90f598871cb7e3ecca92324
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:653813692be3fe76058a72494d47dfbd3b6bbfee96ad09970fa4673fd2ea20e7
+oid sha256:c2986fa958ada5477ebe88ba8fc733f923510de4a8bd10bb9807ab03964f5f1d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6441076c1cbb565e8a73d1aab0642efd925e6b62088853107fb5868252f66a6f
+oid sha256:eb952e625e0c2be59a595bcc79e38c96d6dc8c431f14505091b0820a46236bd3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587dbaeb0068045023e24668350e32134b72575f93a986040a0358feb0532d23
+oid sha256:43c941a63238f94378bcb20909f17c5f59be9cb66d772ba3b2decb25abab3c48
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efdc531e420599f96dd87d66bd6a5df7ddb29f4c8764fef359b2917a85fb4260
+oid sha256:721310d2981547202484da70c2e17048502375ecff14f4280996b3b5ba67e562
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.805473268032074,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3200",
-  "epoch": 4.551539491298527,
+  "best_metric": 0.7966070771217346,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-3500",
+  "epoch": 4.685408299866131,
   "eval_steps": 100,
-  "global_step": 3400,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -517,6 +517,21 @@
       "eval_samples_per_second": 889.896,
       "eval_steps_per_second": 3.596,
       "step": 3400
+    },
+    {
+      "epoch": 4.685408299866131,
+      "grad_norm": 0.2070203423500061,
+      "learning_rate": 0.0005314591700133868,
+      "loss": 0.7658,
+      "step": 3500
+    },
+    {
+      "epoch": 4.685408299866131,
+      "eval_loss": 0.7966070771217346,
+      "eval_runtime": 6.3599,
+      "eval_samples_per_second": 894.984,
+      "eval_steps_per_second": 3.616,
+      "step": 3500
     }
   ],
   "logging_steps": 100,
@@ -531,7 +546,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -545,7 +560,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.23461720604672e+17,
+  "total_flos": 1.2709294768128e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null