Training in progress, step 900, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f449ecaea05023856701cc6a7482fc4575a7d78905c0579ac3cd784669119041
+oid sha256:06de54356caf5134697b9305c6fb3dbe1d42165a3514f8dbf5f04d529013ca0b
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64c3cdc6de437bb4cd73d82d3785754a70052aee12cbfbea25694372cfbd99cf
+oid sha256:acad3bd5185f15d2083dbdab2a7ea9174efe0e27e14ae7a2665f11b26cfcac49
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2f28005ae080d5f74ee78733fad5c069f8b08635360a4876733f9e12e33dea
+oid sha256:6d76ee5db35896feed2f2eab6eefd5e502a2071ac89e16365d614e1d552bdd4a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb645dc2e4148818e3b8abafb0475d084098a031401b3762383d7bb8284eea3a
+oid sha256:a31d5c232261bd3cfa0ddb7ee08c20b1a70b99fd9b31a96f2f369934ab1735b0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb042206d9d129a5489fd88e856b87f650944ac6e30a8e680a63423187eafd8
+oid sha256:1f027b9a18c6943dd85fd54dee70977cf85ff24387e584dc2a20aadf01d7b7c1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38e70ba9ff6e871b9d42454856b4698e04796c285cbeeab7718443e202a72c0d
+oid sha256:29fbc76816745a073373ce20100a5effea96b1be67d91768816fa7688e1f2c77
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f77b738f0f28a29c728f4c7ce2972e380af6a14dc67f95a2dd3348d64628be
+oid sha256:78b880d8dec1a7eab2c20e06be9bdfae0e6b593eeea278d2bbbae39b7c6102cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9347544312477112,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-800",
-  "epoch": 1.07095046854083,
+  "best_metric": 0.9178469181060791,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-900",
+  "epoch": 1.2048192771084336,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,21 @@
       "eval_samples_per_second": 889.412,
       "eval_steps_per_second": 3.594,
       "step": 800
+    },
+    {
+      "epoch": 1.2048192771084336,
+      "grad_norm": 0.19168391823768616,
+      "learning_rate": 0.0008795180722891566,
+      "loss": 0.956,
+      "step": 900
+    },
+    {
+      "epoch": 1.2048192771084336,
+      "eval_loss": 0.9178469181060791,
+      "eval_runtime": 6.3662,
+      "eval_samples_per_second": 894.095,
+      "eval_steps_per_second": 3.613,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -155,7 +170,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.9049816612864e+16,
+  "total_flos": 3.2681043689472e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null