Training in progress, step 5100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b52583eb1f48727f95309ef024832b78fe092e4fdb89f913e7a9562c5c727d
+oid sha256:42f43a47f0498ebcc1fca1385aecf88d6754f5a79846a31ae5ffcc7a965bb762
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:356ecbf982325373f6e4845cbb3779ad96c3c0f1219bc58fe38161b4ac5fc70c
+oid sha256:7e7cc7f29707dd2ad6e0f596052b19567d73a72985f9f96e6051c98e7b68484e
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1abd1b63763503d8e04dd5aa5f8b54aa0ede26a19fb30809aa8f80ca644485c3
+oid sha256:da206a62ecb726d4d9d08b729122b498506d40bd61f1cf3b358d85abe26faff6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbef5529a1cc087d90a8b49ecf4b0da351977ee7c20f71a30cc90f519bb514b6
+oid sha256:740677f917cc0b44daacf55a4d0b688d702cbb84e375538956a299e232c2c525
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37d6ce9351f9cc5e3275edf6256d5af50bf877e3de5a2e73e71f5f92b8051e5
+oid sha256:a9239cd703fb2c09c1ae81a6126f897df0103303809825bcafdce13173d8bb27
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac0ca82583bdc284453f024005180d0d7f7bc4ba349ebd9774fc26dc9287cc21
+oid sha256:bcc83b43cba9115448342cd27740376c2eac2f3414497eb5ad5fa4bcc1e36d28
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f9b6cc7267db918b7309ff0cf09718043e45ea0b921e1903cd2a34a626202fd
+oid sha256:8a39c004fabb87004f6fa700ec70e32d89d41dc550ed41a4cdd9348c43c13c97
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7732182145118713,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5000",
-  "epoch": 6.693440428380187,
+  "best_metric": 0.7706419825553894,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-5100",
+  "epoch": 6.827309236947791,
   "eval_steps": 100,
-  "global_step": 5000,
+  "global_step": 5100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -757,6 +757,21 @@
       "eval_samples_per_second": 895.647,
       "eval_steps_per_second": 3.619,
       "step": 5000
+    },
+    {
+      "epoch": 6.827309236947791,
+      "grad_norm": 0.19911488890647888,
+      "learning_rate": 0.0003172690763052209,
+      "loss": 0.7113,
+      "step": 5100
+    },
+    {
+      "epoch": 6.827309236947791,
+      "eval_loss": 0.7706419825553894,
+      "eval_runtime": 6.3916,
+      "eval_samples_per_second": 890.547,
+      "eval_steps_per_second": 3.598,
+      "step": 5100
     }
   ],
   "logging_steps": 100,
@@ -785,7 +800,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.815613538304e+17,
+  "total_flos": 1.85192580907008e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null