Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a813761d2224c7fb37055edee1acb2892f1fe7809f1b633af6e26c1ecb6e2c3
+oid sha256:f7633ad3e063cb428a0b8188912a6c200fed276f3ac3958cb073af61a7af3b6e
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:349c72b37487facceb08c3664d0a3316d3892e07bdec8bceb9f75eec3d979dc6
+oid sha256:27143edcddc7e4bb7d8afa4ad94874a2e2b960a13504529dd2d4838332938619
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0e8461d2cc9984524853d6378f6defe2c79278543800c1ccb0386f8a89ce6d
+oid sha256:778326eea75bceb231d76d4240266406ce58200b0ab03f90cf031acbe9d10c9b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b767aadc403b51acb4be7e5686ed9aca8849968f250eb8f6e6dc696912b18b1
+oid sha256:89c94a0c557709e37ca8b5be98f902c3c5b689c111517a992bd8c6198bc0a13b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f002a33fc2623a99598cc19e63b00d07a3a54d3a3e4e45012dcd97546e0cd2ee
+oid sha256:8441d9b4dfab33943d5c16fa962c16bea0a6d9e292d0fc439720612487ca5895
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32a4d787a67d4d08a9a13b95bd656f69f3f35d058ff8fc9b02991cf30e1a0681
+oid sha256:aa59e55205aedcec55695be0e324d9123d7e7aaffc98fdd62cc6a7fe21771b1f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c286a6a4668a022cb03a1323c141ebbb2973a90cff5b247a7f85ee65838a958
+oid sha256:8497e2283a464062b42ac5a931608c0c03aeed3224f849e0bfe9c9ea0a315a8f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1724227666854858,
   "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-300",
-  "epoch": 2.857142857142857,
+  "epoch": 3.8095238095238093,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,21 @@
       "eval_samples_per_second": 86.662,
       "eval_steps_per_second": 4.561,
       "step": 300
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "grad_norm": 0.17432411015033722,
+      "learning_rate": 0.0006190476190476191,
+      "loss": 1.2553,
+      "step": 400
+    },
+    {
+      "epoch": 3.8095238095238093,
+      "eval_loss": 1.1775765419006348,
+      "eval_runtime": 0.2186,
+      "eval_samples_per_second": 86.925,
+      "eval_steps_per_second": 4.575,
+      "step": 400
     }
   ],
   "logging_steps": 100,
@@ -66,7 +81,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -80,7 +95,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8795181683834880.0,
+  "total_flos": 1.172690891177984e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null