Training in progress, epoch 11, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7885054e8acee224f47a6214787de54a8e17c44666a2e5e04f3e50bca0784d9
+oid sha256:507e45593144bb2cf41c0598515e2ea5832f9e83502a991e35ca1fd8897d4b7b
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eba41fe33bf5d3cc182639775a215fcb12d809754c66c097a8ecaa8b888aef54
+oid sha256:08bee2e0984bbf63dd98e3afe5ce279648b51a871ad71dbaa9c855446f016deb
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a28e556a4b8cdf7354da0e380ee4ea62220dba2a79a4bfa40e71ebba35883c5a
+oid sha256:2816efc9f4c1de5a16c78e02f2554b79cf809e4fff588f530d63512ba1508099
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7ea7d3411b48ce3a693531a3b9df8c7497b173d8cca394cb86cb6010b5fee6
+oid sha256:667845ec98850da2da09c9709aecd8f85bd67e83fe7c6e52d5a2e2d27bb40110
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.995110273361206,
-  "best_model_checkpoint": "./opt_trained/checkpoint-2010",
-  "epoch": 10.0,
+  "best_metric": 0.9924370050430298,
+  "best_model_checkpoint": "./opt_trained/checkpoint-2211",
+  "epoch": 11.0,
   "eval_steps": 500,
-  "global_step": 2010,
+  "global_step": 2211,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -115,6 +115,14 @@
       "eval_samples_per_second": 37.072,
       "eval_steps_per_second": 9.268,
       "step": 2010
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 0.9924370050430298,
+      "eval_runtime": 77.2049,
+      "eval_samples_per_second": 36.992,
+      "eval_steps_per_second": 9.248,
+      "step": 2211
     }
   ],
   "logging_steps": 500,
@@ -134,7 +142,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.76635109632e+16,
+  "total_flos": 7.442986205952e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null