Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc8014d8748e7dec7645ff75deb0b0111cb9c6f742c7a7131f58eb33ed12b568
+oid sha256:53b52583eb1f48727f95309ef024832b78fe092e4fdb89f913e7a9562c5c727d
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4e65de4b080779841194dd872c35a94659f1ffa84ba40bc11248589de15c96
+oid sha256:356ecbf982325373f6e4845cbb3779ad96c3c0f1219bc58fe38161b4ac5fc70c
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a692fca563f784c79b46a8c6beefa68d79b0f463147563be54c585f9c5445d8f
+oid sha256:1abd1b63763503d8e04dd5aa5f8b54aa0ede26a19fb30809aa8f80ca644485c3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec5ee53c096507164c256ff5ef50e9e03821f6656636c2034a53c87ba7c15a8
+oid sha256:bbef5529a1cc087d90a8b49ecf4b0da351977ee7c20f71a30cc90f519bb514b6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e89826b206d716fd97bcee65bdd2b08f50143c3dda0842ce4e2b37610f5ca831
+oid sha256:a37d6ce9351f9cc5e3275edf6256d5af50bf877e3de5a2e73e71f5f92b8051e5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34ae0937c61c26cef62b07d195d6a8702102333baf881f284e333252395994f5
+oid sha256:ac0ca82583bdc284453f024005180d0d7f7bc4ba349ebd9774fc26dc9287cc21
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9953327c201352be7b2c37fe2e8c427302b4ebf9dc7742a1697bb30527f231f0
+oid sha256:8f9b6cc7267db918b7309ff0cf09718043e45ea0b921e1903cd2a34a626202fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.775974452495575,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4900",
-  "epoch": 6.5595716198125835,
+  "best_metric": 0.7732182145118713,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5000",
+  "epoch": 6.693440428380187,
   "eval_steps": 100,
-  "global_step": 4900,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -742,6 +742,21 @@
       "eval_samples_per_second": 887.297,
       "eval_steps_per_second": 3.585,
       "step": 4900
+    },
+    {
+      "epoch": 6.693440428380187,
+      "grad_norm": 0.21073400974273682,
+      "learning_rate": 0.00033065595716198125,
+      "loss": 0.7166,
+      "step": 5000
+    },
+    {
+      "epoch": 6.693440428380187,
+      "eval_loss": 0.7732182145118713,
+      "eval_runtime": 6.3552,
+      "eval_samples_per_second": 895.647,
+      "eval_steps_per_second": 3.619,
+      "step": 5000
     }
   ],
   "logging_steps": 100,
@@ -770,7 +785,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.77930126753792e+17,
+  "total_flos": 1.815613538304e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null