Training in progress, step 8000

last-checkpoint/mlm/pytorch_adapter.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb454b3d4f9b6534bcc880cd89323f184febad64180dc7f1ee3d7bb5070a927
+oid sha256:16c5c5057a64b3cad8a47f86160a30bb8bbb08c6534d9f02efeede6644c3b90e
 size 3595045

last-checkpoint/mlm/pytorch_model_head.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15660b0a4b1439094aff78fe900f7dcc3f0d00ebbc09b9c0875ab35cfaa31ecb
+oid sha256:6c3a8b2289b4e893871c232a10646122eb944ca6489f63a56bf01bbb4b28fef7
 size 771377007

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ef07dbae6fdb7f4cb89114e9251a6c0a6505ea88dfa5d082e03a3dbdaf5c837
+oid sha256:f7a59e648b0340d2080a6bec4eba1c97d57ffe17e05103c1d20ed110891cbb39
 size 13924549

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:217de0e1fa7492d3e277c1b5a85ecf7e60bd5aab5a2353feb199a9f524d7b6a7
+oid sha256:8686bc61a3c5779e57a5993953e53b100dad817b5e9ce496938eff2e300e3d6a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f54256afd68a22ff4075495f654d677e4d7320c8b00180c7c41d9e33fff51696
+oid sha256:782ae62eac3562dae1bb53fc15debb42f186572902673da6c3f3cc67f1f329ea
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 2.0270919799804688,
   "best_model_checkpoint": "./test-mlm/checkpoint-7000",
-  "epoch": 5.547337278106509,
-  "global_step": 7500,
+  "epoch": 5.9171597633136095,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,11 +231,26 @@
       "eval_samples_per_second": 10.502,
       "eval_steps_per_second": 2.103,
       "step": 7500
+    },
+    {
+      "epoch": 5.92,
+      "learning_rate": 2.6035502958579882e-05,
+      "loss": 2.1762,
+      "step": 8000
+    },
+    {
+      "epoch": 5.92,
+      "eval_accuracy": 0.5788765296492829,
+      "eval_loss": 2.0379111766815186,
+      "eval_runtime": 82.6272,
+      "eval_samples_per_second": 10.517,
+      "eval_steps_per_second": 2.106,
+      "step": 8000
     }
   ],
   "max_steps": 10816,
   "num_train_epochs": 8,
-  "total_flos": 9993181660692480.0,
+  "total_flos": 1.065974927413248e+16,
   "trial_name": null,
   "trial_params": null
 }

runs/Mar10_16-33-29_9eaed4381315/events.out.tfevents.1678466242.9eaed4381315.3748.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13fa9616bbeaab603b382fdb4a23f625da352c5c321fe94140b1ff8d542fa2d8
-size 12215
+oid sha256:4551f925e4d38ddc90b3be747397008ca2eb3b16f0883deff61ff26301d30c8a
+size 12695