Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642e058e21c5f82c79e2d455586fc35de9d3bbede3f1b245857c145ade12ae4c
+oid sha256:c8443f95975ed048c1e0c6439b048d73def3589de1b85658dedc1194ff2ceec2
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a5a9e2ead50a62876cb41854412c361ba13570d118e10d53d9e0f12fb7d6622
+oid sha256:d5b6a52199cf5dec8b8d08e594f5982f4f45118f3079c0f3af9bd6119f9c1e53
 size 67216698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7892406e2a5f44bebfb08110f3f3b9ce30dc4f1519a5ed481caed1cba73b43b6
+oid sha256:7e3499c9219ff63ac9dc89d615db02459233dedff9eb247616c2961ba422d443
 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": 1.7598811388015747,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0017981568891885817,
+  "best_metric": 1.685139536857605,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0026972353337828725,
   "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": 15.277,
       "eval_steps_per_second": 3.82,
       "step": 20
+    },
+    {
+      "epoch": 0.001888064733648011,
+      "grad_norm": 2.2444121837615967,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 7.217,
+      "step": 21
+    },
+    {
+      "epoch": 0.002157788267026298,
+      "grad_norm": 2.5647079944610596,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 6.9141,
+      "step": 24
+    },
+    {
+      "epoch": 0.0022476961114857273,
+      "eval_loss": 1.6970316171646118,
+      "eval_runtime": 612.7583,
+      "eval_samples_per_second": 15.287,
+      "eval_steps_per_second": 3.822,
+      "step": 25
+    },
+    {
+      "epoch": 0.0024275118004045853,
+      "grad_norm": 2.836585521697998,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 7.0266,
+      "step": 27
+    },
+    {
+      "epoch": 0.0026972353337828725,
+      "grad_norm": 2.9823758602142334,
+      "learning_rate": 0.0,
+      "loss": 7.2442,
+      "step": 30
+    },
+    {
+      "epoch": 0.0026972353337828725,
+      "eval_loss": 1.685139536857605,
+      "eval_runtime": 599.685,
+      "eval_samples_per_second": 15.62,
+      "eval_steps_per_second": 3.905,
+      "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": 2389220983308288.0,
+  "total_flos": 3290813807198208.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null