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:f2d6dab5ca8181fc1dc29cb32054fda81f93d4a4abf035af49cad17f24bfd615
+oid sha256:6ed77c781c860f0282373d2f387f026d09f31f943b1cd69a70580346a39aaafd
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3ea8c2af77eb8239d0d4cd7d1de10fb477c2dd2185487719d60614572e08d0
+oid sha256:f9f7ea7eaf9b07a11acb5a17675c713194b4593df91913e17e9e6c2745c11506
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594921cbcd5de3c8898f7cd0fa8dd16876c5eca785fcbff50acd710b7c77341c
+oid sha256:bc484119e6874e66923f2eac6e486d85d5e0864cd7ab861e7b98f962924ce1c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6f907450757c510bc85cf5ba3c442a20b76731dbae558c5d4cdc37061b46d99
+oid sha256:9d42e03a0a3d94b2b0007a43190dd2041868878539beefabe7cf790df6d1d4f7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1731915473937988,
   "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.2557544757033248,
+  "epoch": 0.2841716396703609,
   "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": 35.548,
       "eval_steps_per_second": 8.923,
       "step": 450
+    },
+    {
+      "epoch": 0.26143790849673204,
+      "grad_norm": 0.19075030088424683,
+      "learning_rate": 4.009414470383994e-06,
+      "loss": 1.1471,
+      "step": 460
+    },
+    {
+      "epoch": 0.26712134129013926,
+      "grad_norm": 0.2625552713871002,
+      "learning_rate": 2.261723324051111e-06,
+      "loss": 1.1226,
+      "step": 470
+    },
+    {
+      "epoch": 0.2728047740835465,
+      "grad_norm": 0.3403363525867462,
+      "learning_rate": 1.0072548852474675e-06,
+      "loss": 1.0545,
+      "step": 480
+    },
+    {
+      "epoch": 0.2784882068769537,
+      "grad_norm": 0.5292404294013977,
+      "learning_rate": 2.5212079810819554e-07,
+      "loss": 1.2098,
+      "step": 490
+    },
+    {
+      "epoch": 0.2841716396703609,
+      "grad_norm": 1.3367726802825928,
+      "learning_rate": 0.0,
+      "loss": 1.2654,
+      "step": 500
+    },
+    {
+      "epoch": 0.2841716396703609,
+      "eval_loss": 1.1794259548187256,
+      "eval_runtime": 20.8245,
+      "eval_samples_per_second": 35.583,
+      "eval_steps_per_second": 8.932,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -416,7 +459,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "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": 2.165353118642995e+16,
+  "total_flos": 2.4011222261170176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null