Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42342791e96e430e4263f565eb06e3c405aac168794630f9a285ce8365642b8b
+oid sha256:7e58a28c4bb0a66a102445721dec03c72ecdac71f99b2f17929e7d47d6fa4b02
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2ae8d1ee21a9d43016e79b18856557e3e79fda42bc2044f636231df47db5b51
+oid sha256:28b8b0dbca03cdb3cc020750887cd5aedcff6db66fc6eeb3cbe73b32817b72cd
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ac9ef8a8d750dd06f1b2f32aa7dc4ccd0792acf7e63e2006163d178a7597fee
+oid sha256:0a2ba38d61cd6275d77c5204447109dd9eddc38992e480ed671e0d925609356b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.013300895690918,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07428040854224698,
+  "best_metric": 3.917762517929077,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.11142061281337047,
   "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": 74.033,
       "eval_steps_per_second": 37.016,
       "step": 20
+    },
+    {
+      "epoch": 0.07799442896935933,
+      "grad_norm": 57.77225875854492,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 15.3251,
+      "step": 21
+    },
+    {
+      "epoch": 0.08913649025069638,
+      "grad_norm": 55.74565505981445,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 15.7606,
+      "step": 24
+    },
+    {
+      "epoch": 0.09285051067780872,
+      "eval_loss": 3.9420642852783203,
+      "eval_runtime": 1.5667,
+      "eval_samples_per_second": 72.763,
+      "eval_steps_per_second": 36.381,
+      "step": 25
+    },
+    {
+      "epoch": 0.10027855153203342,
+      "grad_norm": 47.04991912841797,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 15.861,
+      "step": 27
+    },
+    {
+      "epoch": 0.11142061281337047,
+      "grad_norm": 54.018978118896484,
+      "learning_rate": 0.0,
+      "loss": 15.701,
+      "step": 30
+    },
+    {
+      "epoch": 0.11142061281337047,
+      "eval_loss": 3.917762517929077,
+      "eval_runtime": 1.5431,
+      "eval_samples_per_second": 73.876,
+      "eval_steps_per_second": 36.938,
+      "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": 354006639575040.0,
+  "total_flos": 531009959362560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null