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:c4970f5897fcf57c9ff20b94187a700c5f938120816209f91e5d3783189e3a95
+oid sha256:19a9fe212d947d8e0ef03220422ff01caeb1028072bdecbe12bb908c255f0d13
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a037f724fa60663ecfb7274a496d0e939440881e8527fd5e930982d2049e1a60
+oid sha256:397657c3251e929662cfc6f73971474fe29a5c096bcb7cde168a69ce35e81d49
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6925741665505bd0b03f4e190e8bf690ab75ef5253fd17bbffd0df49a5f81feb
+oid sha256:f7830cac7a2603f75479a012d46ca365959d36b0bf5a4437fdf84bf4690b0afc
 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": 3.114184617996216,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07326007326007326,
+  "best_metric": 3.0972774028778076,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.10989010989010989,
   "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": 39.873,
       "eval_steps_per_second": 10.055,
       "step": 20
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 1.0170722007751465,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.0695,
+      "step": 21
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 1.0976736545562744,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.0114,
+      "step": 24
+    },
+    {
+      "epoch": 0.09157509157509157,
+      "eval_loss": 3.104952573776245,
+      "eval_runtime": 5.845,
+      "eval_samples_per_second": 39.35,
+      "eval_steps_per_second": 9.923,
+      "step": 25
+    },
+    {
+      "epoch": 0.0989010989010989,
+      "grad_norm": 1.198337197303772,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.0233,
+      "step": 27
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "grad_norm": 1.2223875522613525,
+      "learning_rate": 0.0,
+      "loss": 3.0602,
+      "step": 30
+    },
+    {
+      "epoch": 0.10989010989010989,
+      "eval_loss": 3.0972774028778076,
+      "eval_runtime": 5.7846,
+      "eval_samples_per_second": 39.761,
+      "eval_steps_per_second": 10.027,
+      "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": 729966229585920.0,
+  "total_flos": 1090443379998720.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null