Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab238c54681852ccb1c5c00174c26c4f2c36da6485b98ea14382b8bf2fc8048
+oid sha256:5551226ab5bfd745eb7fe17a5b3fedce124382a60d2d20795b113e9b18b68f3a
 size 267906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99819392c7083c86785e1d940108a695ea641c8437f6b1679f95cdf1aa0797ae
+oid sha256:0fd363e983824f4c78cdeaa33c76213afd91356b0873865a270bd9ff5269b840
 size 535874874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c02ce3f3054c39adc876693c7f59df2fda4f57fab4ab6cbb2fa38e83b9f448d
+oid sha256:ef95a9514ae37e8f2eb4eaddbe787b2be90d77d4dceafab5d7aeaa43ee4fe036
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be1267363922e30a42a625671aeb53c185a218217e9e479f52c207df2bead2ff
+oid sha256:b962cc92831cf1304b89840743bc274ff678cb5e5537496acffd72095de51d51
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0108377933502197,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-4000",
-  "epoch": 0.3116964076989013,
+  "best_metric": 0.9227759838104248,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-6000",
+  "epoch": 0.4675446115483519,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -95,6 +95,50 @@
       "eval_samples_per_second": 103.744,
       "eval_steps_per_second": 0.818,
       "step": 4000
+    },
+    {
+      "epoch": 0.35065845866126394,
+      "grad_norm": 3.7277610301971436,
+      "learning_rate": 6.493415413387362e-05,
+      "loss": 0.5422,
+      "step": 4500
+    },
+    {
+      "epoch": 0.3896205096236266,
+      "grad_norm": 4.281050205230713,
+      "learning_rate": 6.103794903763734e-05,
+      "loss": 0.5257,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3896205096236266,
+      "eval_loss": 0.9513921737670898,
+      "eval_runtime": 50.1094,
+      "eval_samples_per_second": 103.773,
+      "eval_steps_per_second": 0.818,
+      "step": 5000
+    },
+    {
+      "epoch": 0.42858256058598926,
+      "grad_norm": 3.6584441661834717,
+      "learning_rate": 5.7141743941401084e-05,
+      "loss": 0.5195,
+      "step": 5500
+    },
+    {
+      "epoch": 0.4675446115483519,
+      "grad_norm": 5.238151550292969,
+      "learning_rate": 5.3245538845164814e-05,
+      "loss": 0.5106,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4675446115483519,
+      "eval_loss": 0.9227759838104248,
+      "eval_runtime": 49.9608,
+      "eval_samples_per_second": 104.082,
+      "eval_steps_per_second": 0.821,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -114,7 +158,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6963084222464e+16,
+  "total_flos": 2.5444626333696e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null