Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28a8a1ab613b04d4427ab81f4990b3cea9fcff1a0fd36a7d3c66fe3b240a6a16
+oid sha256:7b7050aacdc16edecc4768363e3345365b43cd39472ed7bb5e607ef139c0e1ef
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf74243e8750bd6dd69453fbbb0ad9504917688a6496e909eb95238a355fc40
+oid sha256:9d65778f4cd259510c03b00356fc54a7893f08bccce0c708cf52d56fe089f9b5
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f824b5aae8e7b3bed6b086664c12563def57f5d97a14f6faff99ac0b1708dd45
+oid sha256:e6fefa90ff71132e7bffa8e2bee23ca7b9972b4e44747e48c07a96239bd0db17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4919617176055908,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.001253466618617113,
+  "best_metric": 0.48363158106803894,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0018801999279256694,
   "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": 20.716,
       "eval_steps_per_second": 5.18,
       "step": 20
+    },
+    {
+      "epoch": 0.0013161399495479687,
+      "grad_norm": 1.4468401670455933,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.9005,
+      "step": 21
+    },
+    {
+      "epoch": 0.0015041599423405356,
+      "grad_norm": 1.8395060300827026,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.9538,
+      "step": 24
+    },
+    {
+      "epoch": 0.001566833273271391,
+      "eval_loss": 0.4840599298477173,
+      "eval_runtime": 649.5403,
+      "eval_samples_per_second": 20.687,
+      "eval_steps_per_second": 5.173,
+      "step": 25
+    },
+    {
+      "epoch": 0.0016921799351331025,
+      "grad_norm": 1.651307463645935,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.7949,
+      "step": 27
+    },
+    {
+      "epoch": 0.0018801999279256694,
+      "grad_norm": 2.069519281387329,
+      "learning_rate": 0.0,
+      "loss": 1.8733,
+      "step": 30
+    },
+    {
+      "epoch": 0.0018801999279256694,
+      "eval_loss": 0.48363158106803894,
+      "eval_runtime": 648.3451,
+      "eval_samples_per_second": 20.725,
+      "eval_steps_per_second": 5.182,
+      "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": 1.3232659048169472e+16,
+  "total_flos": 1.976730549170995e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null