Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bd626e6dd33d7af38e6142a1fa31eba087ce2d597315db0de201d5a4b0ed4f
+oid sha256:024ec522820021456056770199a6e69a1cb16404da6a6ed85d5c57714746e440
 size 100690184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f4089cd98f6bb2db350bce6d1f10be1914caf5950f4a423b832f784a9f64c1
+oid sha256:6e59255bfba12a432921e4206413a16f99ffe14e24344f0840bd213a7846ddf2
 size 51345082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52755c482238068d89ef89ac9ac1f656e67ce9e17ba484d10897f188ef80c418
+oid sha256:2a8879ab1af878426e10fbad6694eb15cd02e8603536fc02026e1ffecbc8e901
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b43450b88475bcf098065f8f055f5a22625a79b35c329b2a2da0516bc5608f62
+oid sha256:ea278ffcc402f8731d694a21dbc5a96671a02299dc57c40b61a02431bc8aed26
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8851467370986938,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.19111323459149546,
+  "best_metric": 0.8364555239677429,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.21500238891543239,
   "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": 76.57,
       "eval_steps_per_second": 19.186,
       "step": 400
+    },
+    {
+      "epoch": 0.19589106545628285,
+      "grad_norm": 12.487257957458496,
+      "learning_rate": 2.0721656110318213e-05,
+      "loss": 1.1234,
+      "step": 410
+    },
+    {
+      "epoch": 0.20066889632107024,
+      "grad_norm": 12.503289222717285,
+      "learning_rate": 1.6486781567027783e-05,
+      "loss": 1.2566,
+      "step": 420
+    },
+    {
+      "epoch": 0.20544672718585763,
+      "grad_norm": 9.571052551269531,
+      "learning_rate": 1.2700186174806422e-05,
+      "loss": 1.6166,
+      "step": 430
+    },
+    {
+      "epoch": 0.210224558050645,
+      "grad_norm": 11.375801086425781,
+      "learning_rate": 9.380317845777794e-06,
+      "loss": 1.9494,
+      "step": 440
+    },
+    {
+      "epoch": 0.21500238891543239,
+      "grad_norm": 11.005843162536621,
+      "learning_rate": 6.543350644728947e-06,
+      "loss": 2.0351,
+      "step": 450
+    },
+    {
+      "epoch": 0.21500238891543239,
+      "eval_loss": 0.8364555239677429,
+      "eval_runtime": 11.4227,
+      "eval_samples_per_second": 77.215,
+      "eval_steps_per_second": 19.347,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3725608982937600.0,
+  "total_flos": 4191310105804800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null