Training in progress, epoch 11, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:738193b43a1ddc49a6b37452f390cf37e63f0bef9a1c61e386a5e2b6d138eecd
+oid sha256:3bf7f54b64df93ce0f2fcb68fc7e653d2405f54ec2007bc21b1dbbf171b3b035
 size 2682482800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57b4d51a5d8639db9ae6b325a825cf66ee6d51be8a39f945da91642215c31c2
+oid sha256:9be947d954b496169e373878044be7308c4f2c478c1251870839f1a7cb47be36
 size 5365108834

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c88d52cdd8bfc63870ec8c6cfb4399bc14947ba93e051c849375243bf4017226
+oid sha256:2322f66ff1c6e187e3a28e99424d0d727cfb601d8182c3cf171308f1229edf01
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b14b4e9c95c66720db6c6a64c68b170bafb8648830648375f2c99f07c4ff19a
+oid sha256:fc4fd1f16fcb95d9548ef1b42dd4a5a37d5b3e9dd4348574c75fdb00d7912893
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9511386752128601,
-  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-2570",
-  "epoch": 10.0,
+  "best_metric": 0.9429148435592651,
+  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-2827",
+  "epoch": 11.0,
   "eval_steps": 500,
-  "global_step": 2570,
+  "global_step": 2827,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,6 +157,21 @@
       "eval_samples_per_second": 46.579,
       "eval_steps_per_second": 5.822,
       "step": 2570
+    },
+    {
+      "epoch": 11.0,
+      "grad_norm": 0.5148940682411194,
+      "learning_rate": 8.159505208333334e-05,
+      "loss": 0.7466,
+      "step": 2827
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.9429148435592651,
+      "eval_runtime": 9.2986,
+      "eval_samples_per_second": 46.459,
+      "eval_steps_per_second": 5.807,
+      "step": 2827
     }
   ],
   "logging_steps": 500,
@@ -185,7 +200,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.693286615993549e+17,
+  "total_flos": 4.062615277592904e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null