Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:946d32d985173c18f5383f6f021285eac930e8b15bf01e32bdc289a3d1d064b0
+oid sha256:968e03ae03f33689ee8bf0de5450ffc0dd78b0a4a9a4154f817c34ab4c0000cd
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae12cb034dee1ace326afc842d9d042204bc073559045bafb6193deba3066dd3
+oid sha256:776694f290b9de0755e58f47f93532e51b16152bcc2a447db53e896be1864ffb
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef77511580e35acadedd0521b40f2b82d4303a9ddf4d4b6b9df9f3ea88463acd
+oid sha256:adda167bf4ac7f6ad5f7c7ab1e731ef248010db34ac4f0c8817dee1b730768a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6da36b358afefa2fe6fe8e3889efc77dfb89ac577ed7bb55c631123a9ebe149
+oid sha256:56e06160672e234a504b2a9f8fb3d80ed8c221e80fde36a5548d37e259bd5bc6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0845487117767334,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.010239606799098914,
+  "best_metric": 2.076117515563965,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.01365280906546522,
   "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": 18.975,
       "eval_steps_per_second": 4.744,
       "step": 150
+    },
+    {
+      "epoch": 0.010922247252372175,
+      "grad_norm": 9.40384578704834,
+      "learning_rate": 2.2444444444444445e-06,
+      "loss": 2.0879,
+      "step": 160
+    },
+    {
+      "epoch": 0.011604887705645437,
+      "grad_norm": 15.089966773986816,
+      "learning_rate": 1.6833333333333332e-06,
+      "loss": 2.0984,
+      "step": 170
+    },
+    {
+      "epoch": 0.012287528158918698,
+      "grad_norm": 20.971054077148438,
+      "learning_rate": 1.1222222222222222e-06,
+      "loss": 2.1849,
+      "step": 180
+    },
+    {
+      "epoch": 0.01297016861219196,
+      "grad_norm": 17.864702224731445,
+      "learning_rate": 5.611111111111111e-07,
+      "loss": 2.1495,
+      "step": 190
+    },
+    {
+      "epoch": 0.01365280906546522,
+      "grad_norm": 58.980403900146484,
+      "learning_rate": 0.0,
+      "loss": 2.2493,
+      "step": 200
+    },
+    {
+      "epoch": 0.01365280906546522,
+      "eval_loss": 2.076117515563965,
+      "eval_runtime": 324.174,
+      "eval_samples_per_second": 19.027,
+      "eval_steps_per_second": 4.757,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.36624253370368e+16,
+  "total_flos": 7.15499004493824e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null