Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:205262fab38c07f1dc88c7aa7db265281dff5fafafe8509e31c2a3749be2ff23
+oid sha256:560919ab2fd91b1c61ac728e157e326645901f81fcd3ac60af449f9d019068f3
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92fbb050cd8fb22eab395ef3df32770edc9a38b25f1eaceab147502e43d74a3
+oid sha256:74a7ba9cbcb6d4398be2dcce92eda63765c72458159f20293d1efec1b1fe8902
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6cd3d0e8561bd811bc21aa769d2d5dbb42316c067b88d062dc504cf60173516
+oid sha256:b43f5aa7c7de7f561307c3ffe1e145bef0d386677200b321eaa3c5d11bdd5724
 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": 1.507926106452942,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.049049662783568364,
+  "best_metric": 1.4945499897003174,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.07357449417535254,
   "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": 7.453,
       "eval_steps_per_second": 3.726,
       "step": 20
+    },
+    {
+      "epoch": 0.05150214592274678,
+      "grad_norm": 0.36523109674453735,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.4534,
+      "step": 21
+    },
+    {
+      "epoch": 0.05885959534028203,
+      "grad_norm": 0.3720594048500061,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.4564,
+      "step": 24
+    },
+    {
+      "epoch": 0.061312078479460456,
+      "eval_loss": 1.4964625835418701,
+      "eval_runtime": 23.1084,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.722,
+      "step": 25
+    },
+    {
+      "epoch": 0.06621704475781728,
+      "grad_norm": 0.3617859184741974,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.465,
+      "step": 27
+    },
+    {
+      "epoch": 0.07357449417535254,
+      "grad_norm": 0.3772672116756439,
+      "learning_rate": 0.0,
+      "loss": 1.4506,
+      "step": 30
+    },
+    {
+      "epoch": 0.07357449417535254,
+      "eval_loss": 1.4945499897003174,
+      "eval_runtime": 23.0939,
+      "eval_samples_per_second": 7.448,
+      "eval_steps_per_second": 3.724,
+      "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": 7024675670458368.0,
+  "total_flos": 1.0455331230449664e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null