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:f3d699ad02e6013c01b5b72cc16ad352c3668587f4e84c25aa9cf9246c9a15af
+oid sha256:586d2811c1c4f874ae3c902f6a98170c70240dfd391ea7e45359e2d50ca046c2
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e37e408105e2e2d7deb7fc472df65a26baed03ad989d967b66720f6d3b63477
+oid sha256:78428142cec7d47727f8f08d49e3a97dd027c94eba55f1a1bcad1a2ce1e5a08c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
+oid sha256:6bfe317d44b8f3bf2eb130aa26c2579199f2fbb7a32f4bcba4bfcd17b18d14b2
 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": 2.1560606956481934,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0009422517461102671,
+  "best_metric": 2.1497068405151367,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0014133776191654005,
   "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": 7.556,
       "eval_steps_per_second": 3.778,
       "step": 20
+    },
+    {
+      "epoch": 0.0009893643334157804,
+      "grad_norm": 0.5383328199386597,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.1533,
+      "step": 21
+    },
+    {
+      "epoch": 0.0011307020953323205,
+      "grad_norm": 0.4795800447463989,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.175,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011778146826378337,
+      "eval_loss": 2.150517463684082,
+      "eval_runtime": 1182.6083,
+      "eval_samples_per_second": 7.558,
+      "eval_steps_per_second": 3.779,
+      "step": 25
+    },
+    {
+      "epoch": 0.0012720398572488604,
+      "grad_norm": 0.48727738857269287,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.1221,
+      "step": 27
+    },
+    {
+      "epoch": 0.0014133776191654005,
+      "grad_norm": 0.46942269802093506,
+      "learning_rate": 0.0,
+      "loss": 2.1367,
+      "step": 30
+    },
+    {
+      "epoch": 0.0014133776191654005,
+      "eval_loss": 2.1497068405151367,
+      "eval_runtime": 1182.9742,
+      "eval_samples_per_second": 7.556,
+      "eval_steps_per_second": 3.778,
+      "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": 7418872835604480.0,
+  "total_flos": 1.1221045163851776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null