Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d6bb3e27013db77751ae42990ca25f2a9e2839f5613cee28ea3239bb7eb378
+oid sha256:590cc07a5971e0c9b5a120a7bf1ab31dacb17b8e613468c7da3945788c20a68a
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25626d303f532dbc82735d9979fcb89d91ea06847267438f8c249605e06f806
+oid sha256:f911d2970d860a82d3517e9eb7d0c2728b18b778c7f6864f1152c87840fce80e
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 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": 11.929913520812988,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.020335536349771224,
+  "best_metric": 11.929757118225098,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.030503304524656837,
   "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": 34.385,
       "eval_steps_per_second": 17.234,
       "step": 20
+    },
+    {
+      "epoch": 0.021352313167259787,
+      "grad_norm": 0.03248075395822525,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.9307,
+      "step": 21
+    },
+    {
+      "epoch": 0.02440264361972547,
+      "grad_norm": 0.023889845237135887,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 11.9311,
+      "step": 24
+    },
+    {
+      "epoch": 0.02541942043721403,
+      "eval_loss": 11.929779052734375,
+      "eval_runtime": 12.1206,
+      "eval_samples_per_second": 34.239,
+      "eval_steps_per_second": 17.161,
+      "step": 25
+    },
+    {
+      "epoch": 0.027452974072191154,
+      "grad_norm": 0.03272699564695358,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.9295,
+      "step": 27
+    },
+    {
+      "epoch": 0.030503304524656837,
+      "grad_norm": 0.023512979969382286,
+      "learning_rate": 0.0,
+      "loss": 11.9302,
+      "step": 30
+    },
+    {
+      "epoch": 0.030503304524656837,
+      "eval_loss": 11.929757118225098,
+      "eval_runtime": 12.1269,
+      "eval_samples_per_second": 34.221,
+      "eval_steps_per_second": 17.152,
+      "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": 11616780288.0,
+  "total_flos": 16956751872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null