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:ff83a0ddf7b50676b4192e9927e5202fafb132b8a2c04a6c3c3245ebc6162654
+oid sha256:58e232e37e71b1def8b7734831612df53b76ca0eb5a6465de95f788221533f5d
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f526ec102ae91fed65107bb1e2a4ab0cf6264a04e723c703aa7b2c0aa11adabd
+oid sha256:4d3785f15678c6f92e2a9a81246ac9f82a81d6748dc20474c2c78848780c1e2d
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef679fab5fb3c676adcc7a412c8bf7d1e59930c83568ce20eee25fb1d0fb261
+oid sha256:459b8ebc21da055bb58b68037491f81f6142db747d843dea15f6e43266294436
 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": 11.044090270996094,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007474539848640568,
+  "best_metric": 11.034719467163086,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.011211809772960851,
   "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": 190.938,
       "eval_steps_per_second": 95.554,
       "step": 20
+    },
+    {
+      "epoch": 0.007848266841072597,
+      "grad_norm": 1.3862786293029785,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 44.1421,
+      "step": 21
+    },
+    {
+      "epoch": 0.008969447818368682,
+      "grad_norm": 1.3453408479690552,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 44.173,
+      "step": 24
+    },
+    {
+      "epoch": 0.00934317481080071,
+      "eval_loss": 11.036252975463867,
+      "eval_runtime": 5.9901,
+      "eval_samples_per_second": 188.143,
+      "eval_steps_per_second": 94.155,
+      "step": 25
+    },
+    {
+      "epoch": 0.010090628795664768,
+      "grad_norm": 1.2414804697036743,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 44.1607,
+      "step": 27
+    },
+    {
+      "epoch": 0.011211809772960851,
+      "grad_norm": 1.4629985094070435,
+      "learning_rate": 0.0,
+      "loss": 44.1362,
+      "step": 30
+    },
+    {
+      "epoch": 0.011211809772960851,
+      "eval_loss": 11.034719467163086,
+      "eval_runtime": 5.941,
+      "eval_samples_per_second": 189.7,
+      "eval_steps_per_second": 94.934,
+      "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": 436790624256.0,
+  "total_flos": 655185936384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null