Training in progress, epoch 10, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f906cae71eeab352318738ca14756442ba163e636920c59a394a833c3dc856b
+oid sha256:f7885054e8acee224f47a6214787de54a8e17c44666a2e5e04f3e50bca0784d9
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8b25cc5f1a898ad72fef4fd30212846ab27173034c9792b0977650565a3991b
+oid sha256:eba41fe33bf5d3cc182639775a215fcb12d809754c66c097a8ecaa8b888aef54
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9fe00b64fad24a81305617574b1f144e0a203f88aad01c498c11972a75112b9
+oid sha256:a28e556a4b8cdf7354da0e380ee4ea62220dba2a79a4bfa40e71ebba35883c5a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93718a710ffbdf979db46548e4ac66f31c764b1a1991b166a6b3d69faeec3671
+oid sha256:aa7ea7d3411b48ce3a693531a3b9df8c7497b173d8cca394cb86cb6010b5fee6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9954783320426941,
-  "best_model_checkpoint": "./opt_trained/checkpoint-1809",
-  "epoch": 9.0,
+  "best_metric": 0.995110273361206,
+  "best_model_checkpoint": "./opt_trained/checkpoint-2010",
+  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 1809,
+  "global_step": 2010,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -100,6 +100,21 @@
       "eval_samples_per_second": 37.112,
       "eval_steps_per_second": 9.278,
       "step": 1809
+    },
+    {
+      "epoch": 9.951432129514322,
+      "grad_norm": 1.4501839876174927,
+      "learning_rate": 0.0002001,
+      "loss": 0.9774,
+      "step": 2000
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.995110273361206,
+      "eval_runtime": 77.0387,
+      "eval_samples_per_second": 37.072,
+      "eval_steps_per_second": 9.268,
+      "step": 2010
     }
   ],
   "logging_steps": 500,
@@ -119,7 +134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.089715986688e+16,
+  "total_flos": 6.76635109632e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null