Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b87151ff71f3075240e1a34c1d0098091d99e65fb5ee1ad5622760cbbad1bf5
+oid sha256:7de312a8e99302e407350ebbec58756a087c45b23dc22ecd5cbaf2bf255638aa
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b6dcb58778735d168c93ef2df11cdd738a05ccdad1b675c9e835aa54a45d436
+oid sha256:76c4e7dd175d1171233199ac5270115297bfa975d16ffbc4bbc1e069e1c71096
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c118a7edf324ff6a1a38ff16f32a35eca90bf09908928dcd2cc8e742873a1ea2
+oid sha256:41665902630196f54d3bb1edfb2e49940aea6b83aae2e61e59c5648fef9e424c
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcdcbf7cad190cbb1eebcf5d3a7c6ead1c2f7214ab2b43c16f7e1860aaee06af
+oid sha256:7f2e88614aff46cd1ada70fbc3b2ec41b24cceb0ef1b4801de4a83c39b9b26bc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4174914360046387,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.05762028233938346,
+  "epoch": 0.08643042350907519,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 16.252,
       "eval_steps_per_second": 4.068,
       "step": 100
+    },
+    {
+      "epoch": 0.0633823105733218,
+      "grad_norm": 0.610034704208374,
+      "learning_rate": 0.00020570613669657956,
+      "loss": 1.7989,
+      "step": 110
+    },
+    {
+      "epoch": 0.06914433880726016,
+      "grad_norm": 0.7986786365509033,
+      "learning_rate": 0.00020241686623233464,
+      "loss": 1.5293,
+      "step": 120
+    },
+    {
+      "epoch": 0.0749063670411985,
+      "grad_norm": 0.9212441444396973,
+      "learning_rate": 0.00019866517033681577,
+      "loss": 1.2778,
+      "step": 130
+    },
+    {
+      "epoch": 0.08066839527513685,
+      "grad_norm": 0.9731055498123169,
+      "learning_rate": 0.00019446932689530684,
+      "loss": 1.0822,
+      "step": 140
+    },
+    {
+      "epoch": 0.08643042350907519,
+      "grad_norm": 1.488525390625,
+      "learning_rate": 0.0001898497776352901,
+      "loss": 0.8345,
+      "step": 150
+    },
+    {
+      "epoch": 0.08643042350907519,
+      "eval_loss": 1.5110596418380737,
+      "eval_runtime": 45.1761,
+      "eval_samples_per_second": 16.181,
+      "eval_steps_per_second": 4.051,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.808762618983219e+16,
+  "total_flos": 2.708774936641536e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null