Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d29b52c4177a1c2e4929eb83c5071c7f64b8f574e791441801cb4dde0967dd
+oid sha256:1b87151ff71f3075240e1a34c1d0098091d99e65fb5ee1ad5622760cbbad1bf5
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a6b0ba624f3c9925accb42a6a143ff47375ae85fd06617b4ddb9c99678a45f9
+oid sha256:1b6dcb58778735d168c93ef2df11cdd738a05ccdad1b675c9e835aa54a45d436
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d80bce9e6234687b4a21fae9f2fa835d59a237b42a5723abfbb81e6515d06634
+oid sha256:c118a7edf324ff6a1a38ff16f32a35eca90bf09908928dcd2cc8e742873a1ea2
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a6f5371cad36fe4f88646b9681959924f9f12b9fe1fb69172cecf5eda55557
+oid sha256:dcdcbf7cad190cbb1eebcf5d3a7c6ead1c2f7214ab2b43c16f7e1860aaee06af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4174914360046387,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.02881014116969173,
+  "epoch": 0.05762028233938346,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 16.347,
       "eval_steps_per_second": 4.092,
       "step": 50
+    },
+    {
+      "epoch": 0.03457216940363008,
+      "grad_norm": 0.6755384802818298,
+      "learning_rate": 0.0002147381354029311,
+      "loss": 1.8599,
+      "step": 60
+    },
+    {
+      "epoch": 0.040334197637568424,
+      "grad_norm": 0.9027474522590637,
+      "learning_rate": 0.0002139538173897188,
+      "loss": 1.5252,
+      "step": 70
+    },
+    {
+      "epoch": 0.04609622587150677,
+      "grad_norm": 1.0059105157852173,
+      "learning_rate": 0.0002126508670788841,
+      "loss": 1.2772,
+      "step": 80
+    },
+    {
+      "epoch": 0.05185825410544512,
+      "grad_norm": 0.9736582636833191,
+      "learning_rate": 0.00021083563231336926,
+      "loss": 1.0586,
+      "step": 90
+    },
+    {
+      "epoch": 0.05762028233938346,
+      "grad_norm": 1.0923612117767334,
+      "learning_rate": 0.00020851695673448515,
+      "loss": 0.7892,
+      "step": 100
+    },
+    {
+      "epoch": 0.05762028233938346,
+      "eval_loss": 1.486754298210144,
+      "eval_runtime": 44.9804,
+      "eval_samples_per_second": 16.252,
+      "eval_steps_per_second": 4.068,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9087503013249024.0,
+  "total_flos": 1.808762618983219e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null