Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db757bc3775ce2b22261275c3c067a5f29c74aa7c3fe5bbd75b4ae2cd72d5701
+oid sha256:05bdb81ea9fd3fb7fee69363543e0abb627618d494a437b729ea47c50157ca52
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae2a3833b0f0747b6d7320f475c3dc27198cfa0bb3cb5b818b178baded93b48
+oid sha256:9e0de4cc64561a2e127a5c5a576cfa4877018690c45b21294691e3aa497459b8
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6242d91b23d26aaf36eff89477251a99db12b884840e91018a4334bd9fde5610
+oid sha256:6c36ff10dd2a06f64abe8c50f0195373fd0ff96ab73fe93f86c0fc6019aa6cd7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e22b2a2843ce706fbf823b6124dbe8ac9013ba578730467f535c1093539a53
+oid sha256:8d74e9d8e3d06c40a9ac96856348569834b8994791b3d5aae1e2e971c3d36f89
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b82fcc60f09c292335cf857fb27c07cde649312ad30b4eb7d0dce1131d1d5e
+oid sha256:55f3a3269c586457d190d66e9d2716fd5f503d02f41c3c15109c31faad2d4e0c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73784ba49228f3808b2d8c3413a07d9f0d06397abba4a302454586636be59647
+oid sha256:c00c02e75f0b8ba3dec9f97bfdfaa0f162c32f2f42503a061b77c04f924bbab3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c409ef2722f271c561931fe81937589049d3a4d4409ff868699b6a54fced761c
+oid sha256:87c5c7a464f7359a51f160c6e7acb947388efd776aacc4351ee16aea191aa1f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0809524059295654,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-200",
-  "epoch": 0.2677376171352075,
+  "best_metric": 1.0328294038772583,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-300",
+  "epoch": 0.40160642570281124,
   "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": 895.204,
       "eval_steps_per_second": 3.617,
       "step": 200
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "grad_norm": 0.2209886759519577,
+      "learning_rate": 0.0009598393574297188,
+      "loss": 1.124,
+      "step": 300
+    },
+    {
+      "epoch": 0.40160642570281124,
+      "eval_loss": 1.0328294038772583,
+      "eval_runtime": 6.3831,
+      "eval_samples_per_second": 891.734,
+      "eval_steps_per_second": 3.603,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -65,7 +80,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7262454153216000.0,
+  "total_flos": 1.0893681229824e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null