Training in progress, step 650, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad832a709ceb64a88d98817dcb75ad708bfacf1a4f40055fae54bcea8244ed97
+oid sha256:33b74a71409a6092147c8261e6079841b95b1b541653e7631df92b5ec093fb2d
 size 4995335576

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6af8410d351904bb32739cb663c37b7698ec1f70ff79e91a4a8d02f23e66cc06
+oid sha256:1f7a7b3a79538d29bd2b07f1f3ca7907aaf45286d1ffbe80362ca7ae98b8bb20
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5332c2221b81d3206827e2f3bda349a3e32e62b283b472331914261c4f8bf7d
+oid sha256:efbe7bd0bba081ddda6a51c290dec8b292cf8d17896f54b4481afd31df122aa1
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad578a43d11126d2531a957d968233fceac13bb258b4a43a2e2c3ad855ce9084
+oid sha256:c07c9483d2aaa0e0aa4859fa05bacc55a60e0f30ff9c95a3b76854e880483a96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a471a6ec9e3c58f40e439496906fe4d5cf4f1a004883d461acf006d0c949a038
+oid sha256:94df8b4b2d639d3f58ff36db997bdfab0ce18552982960aa949cca45016f5382
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.037476577139287946,
+  "epoch": 0.04059962523422861,
   "eval_steps": 50,
-  "global_step": 600,
+  "global_step": 650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -532,6 +532,49 @@
       "eval_samples_per_second": 16.071,
       "eval_steps_per_second": 16.071,
       "step": 600
+    },
+    {
+      "epoch": 0.038101186758276076,
+      "grad_norm": 56.75,
+      "learning_rate": 0.01689831185051374,
+      "loss": 8.3835,
+      "step": 610
+    },
+    {
+      "epoch": 0.03872579637726421,
+      "grad_norm": 864.0,
+      "learning_rate": 0.016151998149109708,
+      "loss": 7.9404,
+      "step": 620
+    },
+    {
+      "epoch": 0.03935040599625234,
+      "grad_norm": 458.0,
+      "learning_rate": 0.015414593635556518,
+      "loss": 8.7404,
+      "step": 630
+    },
+    {
+      "epoch": 0.03997501561524047,
+      "grad_norm": 412.0,
+      "learning_rate": 0.014686840813692224,
+      "loss": 7.7151,
+      "step": 640
+    },
+    {
+      "epoch": 0.04059962523422861,
+      "grad_norm": 95.5,
+      "learning_rate": 0.013969472468919462,
+      "loss": 7.7596,
+      "step": 650
+    },
+    {
+      "epoch": 0.04059962523422861,
+      "eval_loss": 7.7680439949035645,
+      "eval_runtime": 55.2903,
+      "eval_samples_per_second": 15.247,
+      "eval_steps_per_second": 15.247,
+      "step": 650
     }
   ],
   "logging_steps": 10,
@@ -546,7 +589,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 12
+        "early_stopping_patience_counter": 13
       }
     },
     "TrainerControl": {
@@ -560,7 +603,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.450772983808e+16,
+  "total_flos": 2.655004065792e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null