Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e187251073b3351e6580df36ed25fe4c968cdd63b5edbf05cf25fc402d5e61
+oid sha256:8aba30123b4dcd10b56b44969250423d49a2344c16d9ef1014cc640a36db368a
 size 402688040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad0ace38cb56f9ec0ee57f0c0f9dafabab7a9e502ed2c64f866c36dda9b9b48
+oid sha256:f7bfea603d53d961e86c38f46961c11d1480fda7c5b160fd509a6fbdd7b8c064
 size 204773972

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051026a9a89da9ad154cdff56d593da82bc617cc802089275f8d69463f4fd42b
+oid sha256:8fdf170ffdaff47ea36e8e2d34c14091e0093717e3ac6253a2fd93c559c89d35
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
+oid sha256:ddd16399db35d8a29f2ca6eadbdcd4462c58bf5886d5df4eb74f5a14652bb30c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.7833982706069946,
   "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.055699962866691426,
+  "epoch": 0.061888847629657136,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 21.508,
       "eval_steps_per_second": 5.38,
       "step": 450
+    },
+    {
+      "epoch": 0.056937739819284565,
+      "grad_norm": 0.4824948310852051,
+      "learning_rate": 3.990045318353154e-06,
+      "loss": 3.2513,
+      "step": 460
+    },
+    {
+      "epoch": 0.05817551677187771,
+      "grad_norm": 0.5319931507110596,
+      "learning_rate": 2.250797124418014e-06,
+      "loss": 3.4502,
+      "step": 470
+    },
+    {
+      "epoch": 0.05941329372447085,
+      "grad_norm": 0.6029831767082214,
+      "learning_rate": 1.0023889196182526e-06,
+      "loss": 3.6405,
+      "step": 480
+    },
+    {
+      "epoch": 0.060651070677063997,
+      "grad_norm": 0.634583592414856,
+      "learning_rate": 2.5090282323810766e-07,
+      "loss": 3.518,
+      "step": 490
+    },
+    {
+      "epoch": 0.061888847629657136,
+      "grad_norm": 1.1941403150558472,
+      "learning_rate": 0.0,
+      "loss": 3.8805,
+      "step": 500
+    },
+    {
+      "epoch": 0.061888847629657136,
+      "eval_loss": 1.7835521697998047,
+      "eval_runtime": 158.1315,
+      "eval_samples_per_second": 21.514,
+      "eval_steps_per_second": 5.382,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.064444069543936e+16,
+  "total_flos": 5.632902077349888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null