Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06de54356caf5134697b9305c6fb3dbe1d42165a3514f8dbf5f04d529013ca0b
+oid sha256:f0cb17255184785b2ba3df5819549de3498e4d0e7f5e4a2729e64f86ed29de26
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acad3bd5185f15d2083dbdab2a7ea9174efe0e27e14ae7a2665f11b26cfcac49
+oid sha256:79cb07b7152ff3d568067d45b91b044799060a8b3ac1266a4369878feec01534
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d76ee5db35896feed2f2eab6eefd5e502a2071ac89e16365d614e1d552bdd4a
+oid sha256:94e42ef0c0957b2a7ec805704d6efb2633584722c7af0bcea1764796bb5bf281
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31d5c232261bd3cfa0ddb7ee08c20b1a70b99fd9b31a96f2f369934ab1735b0
+oid sha256:db89a18915ddabc34d8708a039b979f64d5e4cc545f23f1fce000552d7bc042d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f027b9a18c6943dd85fd54dee70977cf85ff24387e584dc2a20aadf01d7b7c1
+oid sha256:bae1cf896f870000f671d939a3f1578d4d9fe08093081f10392f661f08c70d15
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29fbc76816745a073373ce20100a5effea96b1be67d91768816fa7688e1f2c77
+oid sha256:5af89e3e6ffd392e6a4fda5011e523226c849189f0277976c34d1b371ff1023d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78b880d8dec1a7eab2c20e06be9bdfae0e6b593eeea278d2bbbae39b7c6102cb
+oid sha256:4405150630b4301b5298e1c0d4cb42b626ca737cad764049dcb8e7d48dbfef79
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9178469181060791,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-900",
-  "epoch": 1.2048192771084336,
+  "best_metric": 0.9004408717155457,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-1000",
+  "epoch": 1.3386880856760375,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -142,6 +142,21 @@
       "eval_samples_per_second": 894.095,
       "eval_steps_per_second": 3.613,
       "step": 900
+    },
+    {
+      "epoch": 1.3386880856760375,
+      "grad_norm": 0.18636095523834229,
+      "learning_rate": 0.0008661311914323963,
+      "loss": 0.9389,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3386880856760375,
+      "eval_loss": 0.9004408717155457,
+      "eval_runtime": 6.385,
+      "eval_samples_per_second": 891.467,
+      "eval_steps_per_second": 3.602,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -170,7 +185,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2681043689472e+16,
+  "total_flos": 3.631227076608e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null