Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25c40d550cd8eff09586b66453ca7839fa2d21f5839f8017c0ee8d58cf507837
+oid sha256:9ad0ad1ec2f4a0da722ab81dde3ad69159dcf0742edcfe57e4cca789fba06a15
 size 912336848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10418c209b4dbd59557ff6d549f691a2a8c29b6dc46a68bbc562d4ef894e2ed
+oid sha256:0f6535423f77c0223cf0058ca521b61ee1ef5b8c074ffbdf38738c36c1ddf9ed
 size 463916756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9784b068ef086ea718f8e30bb8ba6d00897bd2c4d3c7a6df020d03382ae08d81
+oid sha256:7d102f8af972e5368c3c047932602bbc8ed67bfe8ec1625e8b5f385ef88afe38
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0c9560ea4ec378bff0927b20fa3ef4645adc76e93a49024ae06865cbf33e40
+oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.339497447013855,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.350109409190372,
+  "best_metric": 0.32358914613723755,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.3938730853391685,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 6.526,
       "eval_steps_per_second": 1.642,
       "step": 400
+    },
+    {
+      "epoch": 0.3588621444201313,
+      "grad_norm": 1.2920477390289307,
+      "learning_rate": 1.9193792065317794e-05,
+      "loss": 1.4396,
+      "step": 410
+    },
+    {
+      "epoch": 0.3676148796498906,
+      "grad_norm": 0.0026803743094205856,
+      "learning_rate": 1.5271166336279193e-05,
+      "loss": 1.1564,
+      "step": 420
+    },
+    {
+      "epoch": 0.37636761487964987,
+      "grad_norm": 0.006616776809096336,
+      "learning_rate": 1.1763766917677837e-05,
+      "loss": 0.2591,
+      "step": 430
+    },
+    {
+      "epoch": 0.3851203501094092,
+      "grad_norm": 0.02039826288819313,
+      "learning_rate": 8.688681506918602e-06,
+      "loss": 0.0429,
+      "step": 440
+    },
+    {
+      "epoch": 0.3938730853391685,
+      "grad_norm": 0.0405426099896431,
+      "learning_rate": 6.060891611016215e-06,
+      "loss": 0.0019,
+      "step": 450
+    },
+    {
+      "epoch": 0.3938730853391685,
+      "eval_loss": 0.32358914613723755,
+      "eval_runtime": 74.0818,
+      "eval_samples_per_second": 6.493,
+      "eval_steps_per_second": 1.633,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1656992047169536e+17,
+  "total_flos": 2.4355049998123008e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null