Training in progress, step 4300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ed1408e2efdd98c7b559fc6298c728700c459403fc2ddc8b7970d6883b8151
+oid sha256:d23141409bbb36a38c3ce6252dcd54c440951d823323c077f592e6f354d33732
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6187567f5e91ca049754cdf7f8ffb52ba96c047d25df85f69a5200af3843250e
+oid sha256:6d8a3a5334ea620d0b1aa7d05f74d5b2e45113047721b4d09e02ce2e2caca40f
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf8501dea4d10ea756923480c061d5728383aa62af8d35b092ebfbd3d967586c
+oid sha256:38679a2b5c2a15bfaedda45a175bd9dc69ff598a51cb53b08d2ee68a513aad2a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadc5bf956670e67c41e56faeaa14475e61fa86563d6096803859a703c17b32f
+oid sha256:e1470c935f1f6cd56241e6cdca8ba23824c7931ab218970a075485e3692d413b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041f006de55d28fa25ff03374e6f3e91438a73a58213ec73d04709da0ca494b3
+oid sha256:8a3afd79a56cf15dde135418a9cc05bad23ce2f4495ba4281f7957156612fd22
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48b8a88d02d9f0ea814656ef0a0d2f282fcaee5f0c798e59f256612b22adb5a
+oid sha256:e6248feb49b80cbe7da84d4d5a5df02cdfd3c071ecca50d38f674563e33ad624
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67170579fb4c35acb5c0b3b0c2ce7debff2589cc4217ac3a9b76066d360d24bd
+oid sha256:9db256387c89b824cc8694ccbc88b87e90fb06a8490ffefcb4a7211239aa0c26
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.78049236536026,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4200",
-  "epoch": 5.622489959839357,
+  "epoch": 5.756358768406961,
   "eval_steps": 100,
-  "global_step": 4200,
+  "global_step": 4300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -637,6 +637,21 @@
       "eval_samples_per_second": 893.205,
       "eval_steps_per_second": 3.609,
       "step": 4200
+    },
+    {
+      "epoch": 5.756358768406961,
+      "grad_norm": 0.19334332644939423,
+      "learning_rate": 0.00042436412315930387,
+      "loss": 0.7389,
+      "step": 4300
+    },
+    {
+      "epoch": 5.756358768406961,
+      "eval_loss": 0.7910569906234741,
+      "eval_runtime": 6.3418,
+      "eval_samples_per_second": 897.535,
+      "eval_steps_per_second": 3.627,
+      "step": 4300
     }
   ],
   "logging_steps": 100,
@@ -651,7 +666,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -665,7 +680,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.52511537217536e+17,
+  "total_flos": 1.56142764294144e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null