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:f16aa187998241072446107657f3c91614d1da1feb6c38d800cf1987e00403af
+oid sha256:2632627ca7099116108c25a3471a552dd898c8d32f16dbc680a75b1f18b2b205
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9279b22d320b87b2af7f46b249a72f0922df650b5c59895884fd8af2a5d9d48
+oid sha256:9be818d4509413c742079991c6b5155b31a6e937db29eef03a4ad168a309706c
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:277940ae212e1e5a08e603a252f7fa28fd60fa0729a4ef3cb0e7b1749f3943e1
+oid sha256:dad5ca413a28a04500ccdf7fb740f3879efead86332719f7e40c744246e58702
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6691543459892273,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0024013207263995197,
+  "best_metric": 0.6558420062065125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0036019810895992796,
   "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": 10.629,
       "eval_steps_per_second": 5.316,
       "step": 20
+    },
+    {
+      "epoch": 0.0025213867627194957,
+      "grad_norm": 0.4009152352809906,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.6552,
+      "step": 21
+    },
+    {
+      "epoch": 0.0028815848716794235,
+      "grad_norm": 0.3772554099559784,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.633,
+      "step": 24
+    },
+    {
+      "epoch": 0.0030016509079994,
+      "eval_loss": 0.6581240296363831,
+      "eval_runtime": 330.2027,
+      "eval_samples_per_second": 10.621,
+      "eval_steps_per_second": 5.312,
+      "step": 25
+    },
+    {
+      "epoch": 0.0032417829806393518,
+      "grad_norm": 0.4186760485172272,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.6547,
+      "step": 27
+    },
+    {
+      "epoch": 0.0036019810895992796,
+      "grad_norm": 0.5794597864151001,
+      "learning_rate": 0.0,
+      "loss": 0.703,
+      "step": 30
+    },
+    {
+      "epoch": 0.0036019810895992796,
+      "eval_loss": 0.6558420062065125,
+      "eval_runtime": 329.7873,
+      "eval_samples_per_second": 10.634,
+      "eval_steps_per_second": 5.319,
+      "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": 8236125420257280.0,
+  "total_flos": 1.235418813038592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null