Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a46920ac10c8a512b7e00064c95cbc9a73e50858492e3178bb7be0c3b7f2ab78
+oid sha256:90e5772404c246f879a51f9fbc160d928bbd3292efdde08e067e3557a32f2cff
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4490e81b8795df6bf3551ca1f326e85f71984b26bd1ab60a19676d3634f72aaa
+oid sha256:55562a4bb595b9c937a47e2b592ca9b4209134c55e5b2eb1dc1166e4c4932136
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea5e46d94cda4a436a8f88b993239000b927f7e588da79b712e5c0bff773aae
+oid sha256:978adf3ea0400b68da2de3bc98072490751633d1be6e1827474e23d2c7f34414
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96aa36799c943a9bfefa20f32f650908880b1404c454cf725bf5d9ee2c75343e
+oid sha256:126a95bf1277ff34f610ecef71ab3da4221c5fdf57145767d775e04c91223794
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.1364036649465561,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.08161044613710555,
+  "epoch": 0.1088139281828074,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 5.811,
       "eval_steps_per_second": 1.456,
       "step": 150
+    },
+    {
+      "epoch": 0.08705114254624592,
+      "grad_norm": 0.26904261112213135,
+      "learning_rate": 0.0001813903489357277,
+      "loss": 0.234,
+      "step": 160
+    },
+    {
+      "epoch": 0.09249183895538629,
+      "grad_norm": 0.448312371969223,
+      "learning_rate": 0.00017609327897085954,
+      "loss": 0.2675,
+      "step": 170
+    },
+    {
+      "epoch": 0.09793253536452666,
+      "grad_norm": 0.6152125000953674,
+      "learning_rate": 0.00017045228564685694,
+      "loss": 0.3036,
+      "step": 180
+    },
+    {
+      "epoch": 0.10337323177366703,
+      "grad_norm": 0.39368465542793274,
+      "learning_rate": 0.0001644948513161638,
+      "loss": 0.3332,
+      "step": 190
+    },
+    {
+      "epoch": 0.1088139281828074,
+      "grad_norm": 1.3323695659637451,
+      "learning_rate": 0.00015825,
+      "loss": 0.4591,
+      "step": 200
+    },
+    {
+      "epoch": 0.1088139281828074,
+      "eval_loss": 0.14527782797813416,
+      "eval_runtime": 66.1265,
+      "eval_samples_per_second": 5.852,
+      "eval_steps_per_second": 1.467,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.2263274848256e+16,
+  "total_flos": 5.216495638413312e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null