Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2697b0103f3e9a84d56d702845b9ab9e0674b90e040a7763cbd8a01bbeb3aa78
+oid sha256:c5a8ef6f3d2457ec19ccdda34f7787f6509a5d603bfe308c434d9d17b294666f
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c6f5fb498cfcc23a8591ef372f36052fe34ce1134acce53126104d8962bd9a
+oid sha256:f07b15cc0b1d0c1233bd60337f752d90931d6e5ecc980f195deeafbcbda1964c
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f108ec767e229a767e3d8a697ef9ce2b2a773115cacb416ea44871e02516790e
+oid sha256:8861ce7e5b4b02a8488133165a43c601c061bcd41ee0e57ed3ac50ce78e47089
 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": 1.9199856519699097,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.04756242568370987,
+  "best_metric": 1.8473726511001587,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0713436385255648,
   "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": 37.573,
       "eval_steps_per_second": 18.786,
       "step": 20
+    },
+    {
+      "epoch": 0.04994054696789536,
+      "grad_norm": 2.961555242538452,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.9746,
+      "step": 21
+    },
+    {
+      "epoch": 0.057074910820451845,
+      "grad_norm": 2.0701985359191895,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.9017,
+      "step": 24
+    },
+    {
+      "epoch": 0.059453032104637336,
+      "eval_loss": 1.8603113889694214,
+      "eval_runtime": 4.8901,
+      "eval_samples_per_second": 36.4,
+      "eval_steps_per_second": 18.2,
+      "step": 25
+    },
+    {
+      "epoch": 0.06420927467300833,
+      "grad_norm": 2.001005172729492,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.8412,
+      "step": 27
+    },
+    {
+      "epoch": 0.0713436385255648,
+      "grad_norm": 2.62384033203125,
+      "learning_rate": 0.0,
+      "loss": 1.7613,
+      "step": 30
+    },
+    {
+      "epoch": 0.0713436385255648,
+      "eval_loss": 1.8473726511001587,
+      "eval_runtime": 4.7303,
+      "eval_samples_per_second": 37.629,
+      "eval_steps_per_second": 18.815,
+      "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": 360477150412800.0,
+  "total_flos": 540715725619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null