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:e25a34169bf69f684ab29af2083c0b0d3394199dbd3d4f8742a76bee13624092
+oid sha256:f4e4c3e431397affb0b53a175f1d739e123a548290e92aa64fcfafdab4741baa
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffdb2007df072481443c9b669f6145cb9673a5da7b023032498921ab48c5d0ec
+oid sha256:c437b4883ae346b7f4da009a3b6066984851ff7b629fd190c3180636fa144ec5
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832c2c442cbf71daf394540d727b118ab5b6db1652a2abe4106d73ca87deac6e
+oid sha256:330796178c89f0a970539182417e271745b4e562e5f628fb3ab81d04129143f0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913ab8b0d366eeaae4f2a144c807ce2c591297e394af2372dd426dd4c3850119
+oid sha256:d6f907450757c510bc85cf5ba3c442a20b76731dbae558c5d4cdc37061b46d99
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9605308771133423,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.5805515239477503,
+  "best_metric": 1.946034550666809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.6531204644412192,
   "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": 11.897,
       "eval_steps_per_second": 2.995,
       "step": 400
+    },
+    {
+      "epoch": 0.5950653120464441,
+      "grad_norm": 0.927768886089325,
+      "learning_rate": 1.976674108219295e-05,
+      "loss": 1.9795,
+      "step": 410
+    },
+    {
+      "epoch": 0.6095791001451378,
+      "grad_norm": 0.8885520696640015,
+      "learning_rate": 1.572702204780991e-05,
+      "loss": 1.9164,
+      "step": 420
+    },
+    {
+      "epoch": 0.6240928882438317,
+      "grad_norm": 1.0483330488204956,
+      "learning_rate": 1.2114924139101056e-05,
+      "loss": 1.9517,
+      "step": 430
+    },
+    {
+      "epoch": 0.6386066763425254,
+      "grad_norm": 1.1401947736740112,
+      "learning_rate": 8.948045133990798e-06,
+      "loss": 1.9481,
+      "step": 440
+    },
+    {
+      "epoch": 0.6531204644412192,
+      "grad_norm": 3.351959705352783,
+      "learning_rate": 6.241813748658489e-06,
+      "loss": 1.8876,
+      "step": 450
+    },
+    {
+      "epoch": 0.6531204644412192,
+      "eval_loss": 1.946034550666809,
+      "eval_runtime": 24.5405,
+      "eval_samples_per_second": 11.817,
+      "eval_steps_per_second": 2.975,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0333318014409114e+17,
+  "total_flos": 1.1634410976077414e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null