Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dca466cd745146a4892c25b064185d56ccd8a718909812cc29b77d32e7cabd5
+oid sha256:89bbf1d00d7f73d8f9aa0028ddade81b9d7f1dfc1db4669491c4658a3913098c
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6113d479c60c8b8bfca33e994f87404a12d90f4c0fae485fe797feb08d5c1939
+oid sha256:40fa07f3b19137ff625210794ca652c71fa282c338003d77871c3404f0c4fc27
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f99c3423a1a837c0044fd54e06d7d82d98d4715055617568b6a0802f4f5619
+oid sha256:4b00502da5feba7cd8100a8570af5fac37e5c8c267a539c58346d380c13e441c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eafb059b24c048fdb576d0c24ef98dd629ed0a08dffd4d0840cb64cb9bf7cb3e
+oid sha256:7a6520d631a97505ffb9672b2c4a6bcc41f32ff1759145d7010e14811b31feed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5292332172393799,
   "best_model_checkpoint": "./opt_trained3/checkpoint-30",
-  "epoch": 9.0,
+  "epoch": 9.353982300884956,
   "eval_steps": 500,
-  "global_step": 135,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,14 @@
       "eval_samples_per_second": 50.133,
       "eval_steps_per_second": 12.533,
       "step": 135
+    },
+    {
+      "epoch": 9.353982300884956,
+      "eval_loss": 0.5451804399490356,
+      "eval_runtime": 6.0344,
+      "eval_samples_per_second": 49.715,
+      "eval_steps_per_second": 12.429,
+      "step": 140
     }
   ],
   "logging_steps": 500,
@@ -93,12 +101,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5009450520960000.0,
+  "total_flos": 5207869157760000.0,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null