Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff95c29d1750d92a3787e765189a9e7f0c7161de50fd9b17b1461c9ee081338
+oid sha256:0ce65fe5efb6992c37767cc647a3c029a01aea16ffea7857be16a9901fd52044
 size 1157746040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e978b1f869052d53aeb288937e36ccf34d3742d19c7a52bd2cba36af35bcac61
+oid sha256:a7b53f159ef1f9c4e7bd20a321ce56f1c9f0351711488fab70880cd2e72e306f
 size 588699796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3b126f4b4e5c2909be5eb79075beb49bba1c2edf89b512969d055a9d65fcfad
+oid sha256:c84a67128ae6918b79c3715f16531616a7fd438c0472b14975d8be4f346d1720
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a7c1078eb5a1a7c3016e3bc1b27b5075c61ea30d4750bf448abc31716e92a9c
+oid sha256:1164ae497156bc73ad6aea2c09c8b9bf103d80abc111b82a8d3df6753edffe06
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.7171608209609985,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.04263180332528066,
+  "epoch": 0.05684240443370755,
   "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": 9.03,
       "eval_steps_per_second": 2.267,
       "step": 150
+    },
+    {
+      "epoch": 0.045473923546966034,
+      "grad_norm": 1.6705387830734253,
+      "learning_rate": 0.00017709199943488106,
+      "loss": 1.806,
+      "step": 160
+    },
+    {
+      "epoch": 0.048316043768651416,
+      "grad_norm": 2.3406643867492676,
+      "learning_rate": 0.00017192045245496238,
+      "loss": 1.5212,
+      "step": 170
+    },
+    {
+      "epoch": 0.05115816399033679,
+      "grad_norm": 3.6276838779449463,
+      "learning_rate": 0.00016641313195854277,
+      "loss": 1.5071,
+      "step": 180
+    },
+    {
+      "epoch": 0.054000284212022166,
+      "grad_norm": 7.468491077423096,
+      "learning_rate": 0.0001605968690574869,
+      "loss": 1.0868,
+      "step": 190
+    },
+    {
+      "epoch": 0.05684240443370755,
+      "grad_norm": 19.19157600402832,
+      "learning_rate": 0.0001545,
+      "loss": 1.503,
+      "step": 200
+    },
+    {
+      "epoch": 0.05684240443370755,
+      "eval_loss": 2.506401300430298,
+      "eval_runtime": 81.7213,
+      "eval_samples_per_second": 9.067,
+      "eval_steps_per_second": 2.276,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,7 +201,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.657292947501875e+16,
+  "total_flos": 3.482539204490035e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null