Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85316f59b6316c507ed3d731f6adecc5a5764d348efeb342b48124c84e87d4f3
+oid sha256:28d1d81a55aaa268c5d94fea1fb72389b22e3c927e8e2a3ce3b6e3b3807cd75f
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a2e3cdb8b9e96b18d71684801614af6627c827dca5f21a81451ce21dedbef3
+oid sha256:0e9d1a68fa554641ca507725b21d1f3a050030de368158072ada08041a98d6e7
 size 13665274

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f23387d2ef34d1791447be278394c15128900e9096863778b0f682aeaf54bf9
+oid sha256:bd02a93821289e07916800eda516ec74965b8d8536586ecd1d4cfa4597dd47b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
+oid sha256:4677d15317405bcdd600dfdae9d04715d81517a0dbc7789a073149e371184d8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.427879810333252,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0032512395350727465,
+  "best_metric": 2.4247772693634033,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.004064049418840933,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 30.553,
       "eval_steps_per_second": 15.283,
       "step": 20
+    },
+    {
+      "epoch": 0.003413801511826384,
+      "grad_norm": 0.4734785258769989,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.427,
+      "step": 21
+    },
+    {
+      "epoch": 0.003576363488580021,
+      "grad_norm": 0.908765971660614,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.4109,
+      "step": 22
+    },
+    {
+      "epoch": 0.0037389254653336585,
+      "grad_norm": 0.9276166558265686,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.1517,
+      "step": 23
+    },
+    {
+      "epoch": 0.003901487442087296,
+      "grad_norm": 0.4119308292865753,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.4889,
+      "step": 24
+    },
+    {
+      "epoch": 0.004064049418840933,
+      "grad_norm": 0.4042227864265442,
+      "learning_rate": 0.0,
+      "loss": 2.3042,
+      "step": 25
+    },
+    {
+      "epoch": 0.004064049418840933,
+      "eval_loss": 2.4247772693634033,
+      "eval_runtime": 91.9005,
+      "eval_samples_per_second": 28.194,
+      "eval_steps_per_second": 14.102,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 116595011616768.0,
+  "total_flos": 144886448259072.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null