Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:506f8ace0b66b066b1cb32f1d21957707da08ba16a463c5399f3f40d378da3c3
+oid sha256:0a813761d2224c7fb37055edee1acb2892f1fe7809f1b633af6e26c1ecb6e2c3
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0afce708c736beaf7f4f34f21ad39779f9ddd67099a7adf0ab23d01a883538d
+oid sha256:349c72b37487facceb08c3664d0a3316d3892e07bdec8bceb9f75eec3d979dc6
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d64835eb19f46a9b22f6aa58bb2f3f1dc3002d1bc5be3f3bc276dc53687563b0
+oid sha256:4b0e8461d2cc9984524853d6378f6defe2c79278543800c1ccb0386f8a89ce6d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3093efecbd6e27a65d810e2de233c67bdd05d5cf4c80744604fe7b0b3a4572
+oid sha256:9b767aadc403b51acb4be7e5686ed9aca8849968f250eb8f6e6dc696912b18b1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:867fe0ea87c80e44b60860e2807e83aa43f5e41a0cbfbcfc1a71131022813998
+oid sha256:f002a33fc2623a99598cc19e63b00d07a3a54d3a3e4e45012dcd97546e0cd2ee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ecbe193d41c269d7e2ce8215b2dea9bbdfc768d928e2f8d4cf4684fdf034d2
+oid sha256:32a4d787a67d4d08a9a13b95bd656f69f3f35d058ff8fc9b02991cf30e1a0681
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f234c0b485586aa78088ec64e6ba5f29d51e09fcb17f9fa5ddd33f7056bf45e0
+oid sha256:8c286a6a4668a022cb03a1323c141ebbb2973a90cff5b247a7f85ee65838a958
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1765815019607544,
-  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-200",
-  "epoch": 1.9047619047619047,
+  "best_metric": 1.1724227666854858,
+  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-300",
+  "epoch": 2.857142857142857,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,21 @@
       "eval_samples_per_second": 87.116,
       "eval_steps_per_second": 4.585,
       "step": 200
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.16163380444049835,
+      "learning_rate": 0.0007142857142857143,
+      "loss": 1.2854,
+      "step": 300
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_loss": 1.1724227666854858,
+      "eval_runtime": 0.2192,
+      "eval_samples_per_second": 86.662,
+      "eval_steps_per_second": 4.561,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -65,7 +80,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5863454455889920.0,
+  "total_flos": 8795181683834880.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null