Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0966bc0bb80c3905d69063096e9f7955661648577c5ec5ff0c6044bdb354f1a
+oid sha256:c994ed763ffdf01a4ace29018f755540d0176eb8ed228a7cac3e6bac0439a59b
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892335271b766fb75c06967443fa873223ad0ac3b87038638b89cdc8c74328a3
-size 147359892
+oid sha256:03ca68ebd84761490f58e0f451dc0d547e94878bd68d5cd963bd4dc96f8ed280
+size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a20fef20f0244883d637fb24a7cd0b45eda6e51d951c7f1c0c4000b7e8d6c7c
+oid sha256:25d7a045d89bd8ceaab7d1045abc7faefdff2f720a23807664708ea64c4a5995
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c025e03e0d8ded968e4f23b186aaafce8f23c2a50b134c4f77cea95627049ac8
+oid sha256:09bf653dc25e0c029a8db4ba507ae3589e41445bb2b0fcc38f99c09150129f49
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2070493698120117,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.14208581983518045,
+  "best_metric": 1.1927704811096191,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.17050298380221654,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 35.53,
       "eval_steps_per_second": 8.918,
       "step": 250
+    },
+    {
+      "epoch": 0.14776925262858767,
+      "grad_norm": 0.2006831169128418,
+      "learning_rate": 0.00011597548864310363,
+      "loss": 1.1851,
+      "step": 260
+    },
+    {
+      "epoch": 0.1534526854219949,
+      "grad_norm": 0.28160572052001953,
+      "learning_rate": 0.00010866444715376263,
+      "loss": 1.1084,
+      "step": 270
+    },
+    {
+      "epoch": 0.1591361182154021,
+      "grad_norm": 0.35404494404792786,
+      "learning_rate": 0.00010133555284623744,
+      "loss": 1.1729,
+      "step": 280
+    },
+    {
+      "epoch": 0.16481955100880932,
+      "grad_norm": 0.8237364292144775,
+      "learning_rate": 9.402451135689641e-05,
+      "loss": 1.1748,
+      "step": 290
+    },
+    {
+      "epoch": 0.17050298380221654,
+      "grad_norm": 1.429248571395874,
+      "learning_rate": 8.676694134497232e-05,
+      "loss": 1.3167,
+      "step": 300
+    },
+    {
+      "epoch": 0.17050298380221654,
+      "eval_loss": 1.1927704811096191,
+      "eval_runtime": 20.9276,
+      "eval_samples_per_second": 35.408,
+      "eval_steps_per_second": 8.888,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2119359384190976e+16,
+  "total_flos": 1.4539094960898048e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null