Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36879b45c7de8297d7c2a2581689c90d44486db8e0579e66c17fdbea480830d5
+oid sha256:ab2c001f237ffca1cd839278a313f657af631af3ec6a76bc8b2eac4e50e3a25a
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0086cca069f0c748d38cf5898ee0f8a68f329511999200de0326b429e352be3d
+oid sha256:369f651983a45750392de2801cfc00489afdeea1f73debf56bd876311854ee9c
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a86f23dd80b1486d875fae815e5c4c0d268bef84bb0d514c5a7879f850beae
+oid sha256:3111302d79787eb2b7e881e82d970f10e7ab48daddfbf3a91d39b7ad609669ba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb28bb8cf2be6d829bc7d8d43fa28bbbd84fb8993a66e3e97cef2580889f0f5e
+oid sha256:317ba05605195c1d4e2040522f74e7ab98f17d7a309d9ff3aaeabe58a301e214
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6009775400161743,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.10875475802066341,
+  "best_metric": 0.39147135615348816,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.1631321370309951,
   "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": 17.003,
       "eval_steps_per_second": 4.251,
       "step": 100
+    },
+    {
+      "epoch": 0.11963023382272975,
+      "grad_norm": 0.9215604662895203,
+      "learning_rate": 0.0002009222730524731,
+      "loss": 0.2915,
+      "step": 110
+    },
+    {
+      "epoch": 0.13050570962479607,
+      "grad_norm": 0.9864150285720825,
+      "learning_rate": 0.00019770949725018733,
+      "loss": 0.2042,
+      "step": 120
+    },
+    {
+      "epoch": 0.14138118542686243,
+      "grad_norm": 1.3311983346939087,
+      "learning_rate": 0.00019404505009642473,
+      "loss": 0.1785,
+      "step": 130
+    },
+    {
+      "epoch": 0.15225666122892875,
+      "grad_norm": 2.455376386642456,
+      "learning_rate": 0.0001899467844093695,
+      "loss": 0.226,
+      "step": 140
+    },
+    {
+      "epoch": 0.1631321370309951,
+      "grad_norm": 5.563918113708496,
+      "learning_rate": 0.00018543466652749268,
+      "loss": 0.2853,
+      "step": 150
+    },
+    {
+      "epoch": 0.1631321370309951,
+      "eval_loss": 0.39147135615348816,
+      "eval_runtime": 22.7958,
+      "eval_samples_per_second": 17.021,
+      "eval_steps_per_second": 4.255,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.804021269528576e+16,
+  "total_flos": 2.701588502151168e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null