Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6a10b4dbb6c1fffa0a2b2a0b0be2f00c64691c0722eccb5e2d988681d3a240
+oid sha256:3440c86b8b88cc2da5a2e39e27a46b84d667a99c438c256f77d8a0f7875ef23f
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba21b2f5464f9d4b5e71ac132d21c159afbd589928948ba470bdaa3f3750bb1a
+oid sha256:0a25fff4450dd8b61ff947bafb3cff0998b05ff9798895f247c6776ab2fc3889
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed69e948ee4038df38169a6e64fa720197cdd09c4278ff7465da67fe5ea3faa8
+oid sha256:3863cb9fe532bc088238dc1cb8b728c9cabe47e45da05252cff3a64c0873df03
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4176307916641235,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007108457287057277,
+  "best_metric": 1.1148810386657715,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0014216914574114554,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 3.219,
       "eval_steps_per_second": 1.609,
       "step": 10
+    },
+    {
+      "epoch": 0.0008530148744468731,
+      "grad_norm": 2.932966947555542,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 5.9641,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010662685930585914,
+      "grad_norm": 2.8447232246398926,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.2347,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010662685930585914,
+      "eval_loss": 1.2026777267456055,
+      "eval_runtime": 1839.866,
+      "eval_samples_per_second": 3.22,
+      "eval_steps_per_second": 1.61,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012795223116703097,
+      "grad_norm": 3.2762951850891113,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 4.6009,
+      "step": 18
+    },
+    {
+      "epoch": 0.0014216914574114554,
+      "eval_loss": 1.1148810386657715,
+      "eval_runtime": 1839.4766,
+      "eval_samples_per_second": 3.22,
+      "eval_steps_per_second": 1.61,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347789697024000.0,
+  "total_flos": 1.2695579394048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null