Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a9805601b3a37da5eec4036f7883ac9e977fd04b2444e642d86d6341973a73
+oid sha256:170286993f7b49d72fdee6d346a125dbb799daacf9f219184c02dbfd0d3d9c8a
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80bac36c8d7e69d9c9785885c7a6cb29ee5f919f3648e7a04fb8500db72430f6
+oid sha256:d98b83f136c5aab861e4451520fcd964f2e40059376f226d745963a1f3701924
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a40fa307c8c591dcfc24aaa28b94acee940e8d4d3469093ca4b746bc04e8cce
+oid sha256:c2c4941eb02fc8c6c8c7070e24abe93ba6cf66b464693b925666db7822fc778e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
+oid sha256:90c455b2a7603e9003556345290fd0185bd6c6017de2b595e3f9c6216f721e5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.15055163204669952,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.23771790808240886,
+  "best_metric": 0.14917609095573425,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.31695721077654515,
   "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": 10.937,
       "eval_steps_per_second": 2.748,
       "step": 150
+    },
+    {
+      "epoch": 0.25356576862123614,
+      "grad_norm": 1.835580825805664,
+      "learning_rate": 2.2644444444444443e-06,
+      "loss": 0.1311,
+      "step": 160
+    },
+    {
+      "epoch": 0.2694136291600634,
+      "grad_norm": 1.0110487937927246,
+      "learning_rate": 1.6983333333333333e-06,
+      "loss": 0.1496,
+      "step": 170
+    },
+    {
+      "epoch": 0.28526148969889065,
+      "grad_norm": 5.238423824310303,
+      "learning_rate": 1.1322222222222221e-06,
+      "loss": 0.162,
+      "step": 180
+    },
+    {
+      "epoch": 0.3011093502377179,
+      "grad_norm": 0.5642182230949402,
+      "learning_rate": 5.661111111111111e-07,
+      "loss": 0.1568,
+      "step": 190
+    },
+    {
+      "epoch": 0.31695721077654515,
+      "grad_norm": 1.1575543880462646,
+      "learning_rate": 0.0,
+      "loss": 0.1739,
+      "step": 200
+    },
+    {
+      "epoch": 0.31695721077654515,
+      "eval_loss": 0.14917609095573425,
+      "eval_runtime": 18.2576,
+      "eval_samples_per_second": 10.9,
+      "eval_steps_per_second": 2.739,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.19631105835008e+16,
+  "total_flos": 5.59508141113344e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null