Training in progress, step 9100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e631321de4a7f0edb9e4df608fffc1169a28c054004bb84d9c90bde1efd3eb
+oid sha256:72fe9633b02a51a49a2cfeadca1ee666fcf1b3fd25d1edaee5806d94baa42146
 size 136000488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d6bfa10fd72fa4552abbd126a8f73bf03087ddbbf0f406afd69187f481374aa
+oid sha256:1a87453f5493e54965bd9c6b74c8cccaf89bc199afc196a39a1776694b5725e8
 size 268176506

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf48ab9fa8bab1e3ff4f0f626fd9093b03562bae08edaf3a3a13235fa6b1ce3b
+oid sha256:a03dc33a206b870bac827b0d4553fe1f31612e46dc1d6df4c89c4f928ac98827
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f67e79141a1e8ab27edc1a44643202c30fbb22e5b9c3ef6241c285d6911e39
+oid sha256:297c2ad1be70bae81e3d823568324b3db1a2bdb9ff27011986573fdf4003489a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.0438764095306396,
   "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-8900",
-  "epoch": 2.6124818577648767,
+  "epoch": 2.641509433962264,
   "eval_steps": 100,
-  "global_step": 9000,
+  "global_step": 9100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1357,6 +1357,21 @@
       "eval_samples_per_second": 214.031,
       "eval_steps_per_second": 3.345,
       "step": 9000
+    },
+    {
+      "epoch": 2.641509433962264,
+      "grad_norm": 1.3446862697601318,
+      "learning_rate": 7.358490566037736e-05,
+      "loss": 1.9795,
+      "step": 9100
+    },
+    {
+      "epoch": 2.641509433962264,
+      "eval_loss": 1.0461750030517578,
+      "eval_runtime": 213.2022,
+      "eval_samples_per_second": 213.408,
+      "eval_steps_per_second": 3.335,
+      "step": 9100
     }
   ],
   "logging_steps": 100,
@@ -1371,7 +1386,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -1385,7 +1400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.003254005157069e+16,
+  "total_flos": 9.103292765936026e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null