Training in progress, step 200, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eec55da26257e6bdd7e6c8e36ecffb5a79021aeb51150dc5b63a96d4ddfa618
+oid sha256:126f178711fbc9dc02adb12aecf7c2e316048690bf9f666ebf5e533924ca5759
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5618717dfd829dd7d8596a68eaff8f83a9c2c913dcbefd2a76b79925f393192
+oid sha256:49a6a27ff45511a566f230b94929be575d47e80f94f11e46684241a9807432ad
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8ae689a4a2512f4173eeb1a100be1c1ac54ba038fbc329032c57fb26365379e
+oid sha256:a0c0971e1ca60fceb5fa43e0a83baf4624d8bf23bd31003292a1606de1c74861
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecefbb3f17bb76b6655eb0157c98b5287c17fa4b4c72a6b9068b0823ce9fd18d
+oid sha256:95b6047bd8cc6f4cdf7c46dea47edb8e542435510070c6cd1e0a7d9ccf5fd7da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d2b2a58cb1fef054c26ee40b50f34fb3a71e56ece66a18947891aede843123
+oid sha256:95d2a50364bc7f3078838455f012433d9b89075114f0547db53c7e328906dec9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.009369144284821987,
+  "epoch": 0.012492192379762648,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -145,6 +145,49 @@
       "eval_samples_per_second": 15.379,
       "eval_steps_per_second": 15.379,
       "step": 150
+    },
+    {
+      "epoch": 0.009993753903810118,
+      "grad_norm": 26.0,
+      "learning_rate": 0.04725712682570498,
+      "loss": 10.5338,
+      "step": 160
+    },
+    {
+      "epoch": 0.010618363522798251,
+      "grad_norm": 28.125,
+      "learning_rate": 0.046884695883873395,
+      "loss": 9.3137,
+      "step": 170
+    },
+    {
+      "epoch": 0.011242973141786383,
+      "grad_norm": 37.75,
+      "learning_rate": 0.04649022890837298,
+      "loss": 9.4597,
+      "step": 180
+    },
+    {
+      "epoch": 0.011867582760774516,
+      "grad_norm": 46.75,
+      "learning_rate": 0.046074123094010544,
+      "loss": 9.584,
+      "step": 190
+    },
+    {
+      "epoch": 0.012492192379762648,
+      "grad_norm": 48.25,
+      "learning_rate": 0.04563679742406935,
+      "loss": 9.6385,
+      "step": 200
+    },
+    {
+      "epoch": 0.012492192379762648,
+      "eval_loss": 9.662774085998535,
+      "eval_runtime": 53.0984,
+      "eval_samples_per_second": 15.876,
+      "eval_steps_per_second": 15.876,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -159,7 +202,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 3
+        "early_stopping_patience_counter": 4
       }
     },
     "TrainerControl": {
@@ -173,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6126932459520000.0,
+  "total_flos": 8169243279360000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null