Training in progress, step 5900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:464259aa1160c21d7be7d0281cf5d9e24fa2ada0adb8b181a451a8b08e20d13a
+oid sha256:820135006e8f542b62482eb19ee364b94abab136b7b8a4413fc390b6f62b73c3
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fcc17b2a1b6bebaaa880feed9123eafc604829151cc6d7c8506bc692c9ba19c
+oid sha256:a9dab2d80004b8909d4d8fd752bfb96ad4dce2d7c56df286126417e073abad01
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8861626d2974eea65d9e9d45679068c8468bbcff28731312236b82396fdd1501
+oid sha256:9a7ca6d811655d83037346c9acab1bd1021739307d82d202ff63fbbb1ceea038
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff113b6e3a7af36c2fa1001fea1da9e7ab58959e64621c09fad4213aef23972
+oid sha256:fc61214d825fc5f544783bf7e53e491231850f7439142c284518609f7838f7b3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0531f0416eb655e0b86503bc22b77c870301e0053657cda1907014a7fdb5de
+oid sha256:d30e70950b56357ecf556fa58da2ddb5dde5c9a8f7271bce7669a1e8dfcbe777
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4113b73e69e160af28faa2b395f060414c8473ba52fec1a536387e609ddc76fd
+oid sha256:d04322e2e747379ff005ccb5528da0279e78c7e5a0e7a749a19a62353195571f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dc30c4a8e7f8b01c931fefb09d74e5e8b79704150bb29deb3b3753ae05e1017
+oid sha256:26846a794e568be1028d1d62c40f80fee62c5e08ae6707128928f5668ddc009f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7648805975914001,
   "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5700",
-  "epoch": 7.764390896921017,
+  "epoch": 7.898259705488621,
   "eval_steps": 100,
-  "global_step": 5800,
+  "global_step": 5900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -877,6 +877,21 @@
       "eval_samples_per_second": 891.102,
       "eval_steps_per_second": 3.601,
       "step": 5800
+    },
+    {
+      "epoch": 7.898259705488621,
+      "grad_norm": 0.20442116260528564,
+      "learning_rate": 0.00021017402945113788,
+      "loss": 0.6876,
+      "step": 5900
+    },
+    {
+      "epoch": 7.898259705488621,
+      "eval_loss": 0.7717822790145874,
+      "eval_runtime": 6.3521,
+      "eval_samples_per_second": 896.089,
+      "eval_steps_per_second": 3.621,
+      "step": 5900
     }
   ],
   "logging_steps": 100,
@@ -891,7 +906,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -905,7 +920,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.10611170443264e+17,
+  "total_flos": 2.14242397519872e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null