Training in progress, epoch 7, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e58c28154dffcb30f14b50844f6977937562e99cf1d10c140ff2f29744edc3
+oid sha256:3005f7130dea7c99e3a23fe693aca2f872a4909870b225fd381e552552cf3ab3
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d25fd32e37629b8a81718aa4981261247ecec1e7d3a8fba9275fad1fd079af7c
+oid sha256:b49e98b38a7667b6478792575464c5f70db060a96ad9bd23b60f51316b49032f
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b00198c0a76d2b134e58977666d57ae1f7de5e2dfe7b151a00fd2e5abad3451
+oid sha256:9b877278faa523a92a4cc98264dadc986c246d2d7704a09f27fad64a3fb519e0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136c120d5cb1bfe293fa4c534feee6054bd3200d5f744d350104a8b80432a125
+oid sha256:d54b3990ddc5c14708bc858361b93e000545e1cc595791b44c2db8c9f6c8ddbe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0030088424682617,
-  "best_model_checkpoint": "./opt_trained/checkpoint-1206",
-  "epoch": 6.0,
+  "best_metric": 0.9996200203895569,
+  "best_model_checkpoint": "./opt_trained/checkpoint-1407",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 1206,
+  "global_step": 1407,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -69,6 +69,14 @@
       "eval_samples_per_second": 37.172,
       "eval_steps_per_second": 9.293,
       "step": 1206
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.9996200203895569,
+      "eval_runtime": 77.0477,
+      "eval_samples_per_second": 37.068,
+      "eval_steps_per_second": 9.267,
+      "step": 1407
     }
   ],
   "logging_steps": 500,
@@ -88,7 +96,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.059810657792e+16,
+  "total_flos": 4.736445767424e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null