Training in progress, step 4200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58904a09d2c64b3af1fe77f00887cba4248f9483bd0ac2677c899654f1df66ed
+oid sha256:b2ed1408e2efdd98c7b559fc6298c728700c459403fc2ddc8b7970d6883b8151
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d399b620d3b044063e90c4a82c58a56992e901eda2495728359da6520d58da88
+oid sha256:6187567f5e91ca049754cdf7f8ffb52ba96c047d25df85f69a5200af3843250e
 size 268176506

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01228c358c1c5bd7e8d1e30fd7170ee7e7e01eaa5037c80171296afcca88fdbd
+oid sha256:cf8501dea4d10ea756923480c061d5728383aa62af8d35b092ebfbd3d967586c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd593900009094dac4848a91bffea810cd27abb68e41341848d2730ca4540832
+oid sha256:aadc5bf956670e67c41e56faeaa14475e61fa86563d6096803859a703c17b32f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4e118c022d36fb38d58d0d7f0e3edb67b05d2a137df1ba7684c820d27509268
+oid sha256:041f006de55d28fa25ff03374e6f3e91438a73a58213ec73d04709da0ca494b3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c260699388e534a54ab049ec860d4b3bec4fc81bbf3db000ead4ea6f2487ca
+oid sha256:a48b8a88d02d9f0ea814656ef0a0d2f282fcaee5f0c798e59f256612b22adb5a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09ac653d13867a7357fb216c15368c33da04027e0687353248f2f6a7723c2089
+oid sha256:67170579fb4c35acb5c0b3b0c2ce7debff2589cc4217ac3a9b76066d360d24bd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7832607626914978,
-  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4100",
-  "epoch": 5.4886211512717535,
+  "best_metric": 0.78049236536026,
+  "best_model_checkpoint": "mgh6/TCS_MLM/checkpoint-4200",
+  "epoch": 5.622489959839357,
   "eval_steps": 100,
-  "global_step": 4100,
+  "global_step": 4200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -622,6 +622,21 @@
       "eval_samples_per_second": 889.94,
       "eval_steps_per_second": 3.596,
       "step": 4100
+    },
+    {
+      "epoch": 5.622489959839357,
+      "grad_norm": 0.19276629388332367,
+      "learning_rate": 0.0004377510040160643,
+      "loss": 0.7411,
+      "step": 4200
+    },
+    {
+      "epoch": 5.622489959839357,
+      "eval_loss": 0.78049236536026,
+      "eval_runtime": 6.3726,
+      "eval_samples_per_second": 893.205,
+      "eval_steps_per_second": 3.609,
+      "step": 4200
     }
   ],
   "logging_steps": 100,
@@ -650,7 +665,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.48880310140928e+17,
+  "total_flos": 1.52511537217536e+17,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null