Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c10e1024f75d1532fc1fb0ecee6581d07c99a877333b8804f1a7671c18ebfa7f
+oid sha256:d4986335a6d242c9992ec9398c217b707748ba7a3995524f5defb44d0337cf1d
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c9b9bcc89a9a003a6a3027797a7f6e54cbae9ccfc96a583da3a210939cedd6
+oid sha256:917ec3895b9dc995195a376f581f6e4388404ef6cc13f1de6520e4e6ce95c036
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa475f51346237b604de04dfb5849998c82ad8e092cda930a1bc5b8d1fca410b
+oid sha256:6de5eb04bac056357ebd53ed2c82a2e7d5a0037193fcc7faa1b95b0456b34b4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5212913155555725,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.09111617312072894,
+  "best_metric": 0.5042169094085693,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.1366742596810934,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.3,
       "eval_steps_per_second": 2.679,
       "step": 20
+    },
+    {
+      "epoch": 0.09567198177676538,
+      "grad_norm": 1.2766376733779907,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 2.1058,
+      "step": 21
+    },
+    {
+      "epoch": 0.10933940774487472,
+      "grad_norm": 0.9969152808189392,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 2.0709,
+      "step": 24
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "eval_loss": 0.5065757632255554,
+      "eval_runtime": 17.9141,
+      "eval_samples_per_second": 5.191,
+      "eval_steps_per_second": 2.624,
+      "step": 25
+    },
+    {
+      "epoch": 0.12300683371298406,
+      "grad_norm": 1.0334519147872925,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.9104,
+      "step": 27
+    },
+    {
+      "epoch": 0.1366742596810934,
+      "grad_norm": 0.7895696759223938,
+      "learning_rate": 0.0,
+      "loss": 1.8227,
+      "step": 30
+    },
+    {
+      "epoch": 0.1366742596810934,
+      "eval_loss": 0.5042169094085693,
+      "eval_runtime": 18.0605,
+      "eval_samples_per_second": 5.149,
+      "eval_steps_per_second": 2.602,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4467071907790848.0,
+  "total_flos": 6907843156377600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null