Training in progress, epoch 65, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb235f09a86a71f72fd380ea86b3908259f2ca4810012eaddca9f063d4692311
+oid sha256:a2afb00543017d95fcea82ea27622d3f3f79457eb65c0d365f5f1fe2d3bd4a8d
 size 559424792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95be192bc29f614682b8e89d362747ab3b5fdd146c248b5059ca779f7f6f9b86
+oid sha256:b21a57ce3974826064dccd91bbe25ea1f2a0a4b8d96e8ea0d38cf8d3fa46a611
 size 1118926970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9acc0a3d1f86c8dd40605b2d8aed72f85514fb24f5ddb46e859465a7544823
+oid sha256:1a6be1c7dbbf2776066167d40e45e14b51de16e0238becf8ef04c2f6ba8a7876
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ffd78ebaa0111503a70087ed95e849e6a4d772a28d7757e415f68e7ca2fc52c
+oid sha256:df2983526d813d04879aeb1a0c630e99b09e4e6e5107a101d7cca553228cffdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 12.731040000915527,
   "best_model_checkpoint": "/kaggle/working/output/checkpoint-75690",
-  "epoch": 64.0,
+  "epoch": 65.0,
   "eval_steps": 500,
-  "global_step": 83520,
+  "global_step": 84825,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6364,6 +6364,105 @@
       "eval_samples_per_second": 29.56,
       "eval_steps_per_second": 3.715,
       "step": 83520
+    },
+    {
+      "epoch": 64.06130268199233,
+      "grad_norm": 1.2648850679397583,
+      "learning_rate": 9.977490421455939e-06,
+      "loss": 12.1,
+      "step": 83600
+    },
+    {
+      "epoch": 64.13793103448276,
+      "grad_norm": 1.115157961845398,
+      "learning_rate": 9.929597701149426e-06,
+      "loss": 11.798,
+      "step": 83700
+    },
+    {
+      "epoch": 64.21455938697318,
+      "grad_norm": 1.6352553367614746,
+      "learning_rate": 9.881704980842913e-06,
+      "loss": 11.9761,
+      "step": 83800
+    },
+    {
+      "epoch": 64.2911877394636,
+      "grad_norm": 1.2003965377807617,
+      "learning_rate": 9.833812260536398e-06,
+      "loss": 11.9813,
+      "step": 83900
+    },
+    {
+      "epoch": 64.36781609195403,
+      "grad_norm": 1.5004589557647705,
+      "learning_rate": 9.785919540229886e-06,
+      "loss": 11.7826,
+      "step": 84000
+    },
+    {
+      "epoch": 64.44444444444444,
+      "grad_norm": 1.3350985050201416,
+      "learning_rate": 9.738026819923372e-06,
+      "loss": 11.8015,
+      "step": 84100
+    },
+    {
+      "epoch": 64.52107279693486,
+      "grad_norm": 1.5985853672027588,
+      "learning_rate": 9.690134099616858e-06,
+      "loss": 11.6736,
+      "step": 84200
+    },
+    {
+      "epoch": 64.59770114942529,
+      "grad_norm": 2.1115546226501465,
+      "learning_rate": 9.642241379310345e-06,
+      "loss": 11.7572,
+      "step": 84300
+    },
+    {
+      "epoch": 64.67432950191571,
+      "grad_norm": 2.5769665241241455,
+      "learning_rate": 9.594348659003832e-06,
+      "loss": 11.8057,
+      "step": 84400
+    },
+    {
+      "epoch": 64.75095785440612,
+      "grad_norm": 3.2280073165893555,
+      "learning_rate": 9.546455938697319e-06,
+      "loss": 11.9184,
+      "step": 84500
+    },
+    {
+      "epoch": 64.82758620689656,
+      "grad_norm": 1.2311729192733765,
+      "learning_rate": 9.498563218390804e-06,
+      "loss": 11.9657,
+      "step": 84600
+    },
+    {
+      "epoch": 64.90421455938697,
+      "grad_norm": 1.6303430795669556,
+      "learning_rate": 9.450670498084293e-06,
+      "loss": 11.9864,
+      "step": 84700
+    },
+    {
+      "epoch": 64.98084291187739,
+      "grad_norm": 1.6421687602996826,
+      "learning_rate": 9.402777777777778e-06,
+      "loss": 11.8224,
+      "step": 84800
+    },
+    {
+      "epoch": 65.0,
+      "eval_loss": 12.752345085144043,
+      "eval_runtime": 44.1763,
+      "eval_samples_per_second": 29.541,
+      "eval_steps_per_second": 3.712,
+      "step": 84825
     }
   ],
   "logging_steps": 100,
@@ -6378,7 +6477,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 6
+        "early_stopping_patience_counter": 7
       }
     },
     "TrainerControl": {
@@ -6392,7 +6491,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.891383978456678e+16,
+  "total_flos": 3.952173748110797e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null