Training in progress, step 2400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9a2709e81636435aba8f3bb7327af7f9417368c1e69b5f7f4dafc5ef83b42e
+oid sha256:7b81ed46ebdb73fd60c8215b609715c54bcfe893e61ff2be90363782866d9e6c
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d142de881369afb81fa782a9f7cb9303e9766b0a36b592265358e0bd252ab8
+oid sha256:6de2015aa68212071f7c3b91dcfb7b66def0e2afa315439b5c6b549df235e69d
 size 107046

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e17b31b606cecc714a35646778bd910aae92f0dd75e92266ee6b7a50d23e26
+oid sha256:89aa5d01ec6e12a5fc14cff311e1bf214e0afce816e4ca5554bee6c16bbad85d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc5c1fa9a33b222473458ad5e1d3c347079ca2b75bd1df6dfe3400031423b431
+oid sha256:3dee3877c8ca490cbca3fe12b55636d1fec9ddfd94e751ac0ae51b2d185b582e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.899188995361328,
-  "best_model_checkpoint": "miner_id_24/checkpoint-2250",
-  "epoch": 18.71101871101871,
+  "best_metric": 11.899084091186523,
+  "best_model_checkpoint": "miner_id_24/checkpoint-2400",
+  "epoch": 19.95841995841996,
   "eval_steps": 150,
-  "global_step": 2250,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -450,6 +450,35 @@
       "eval_samples_per_second": 225.183,
       "eval_steps_per_second": 57.4,
       "step": 2250
+    },
+    {
+      "epoch": 19.126819126819125,
+      "grad_norm": 0.056740619242191315,
+      "learning_rate": 6.222931005539701e-05,
+      "loss": 12.0697,
+      "step": 2300
+    },
+    {
+      "epoch": 19.542619542619544,
+      "grad_norm": 0.04759081080555916,
+      "learning_rate": 6.138996138996139e-05,
+      "loss": 11.8947,
+      "step": 2350
+    },
+    {
+      "epoch": 19.95841995841996,
+      "grad_norm": 0.07817522436380386,
+      "learning_rate": 6.055061272452577e-05,
+      "loss": 11.9002,
+      "step": 2400
+    },
+    {
+      "epoch": 19.95841995841996,
+      "eval_loss": 11.899084091186523,
+      "eval_runtime": 0.4537,
+      "eval_samples_per_second": 224.815,
+      "eval_steps_per_second": 57.306,
+      "step": 2400
     }
   ],
   "logging_steps": 50,
@@ -478,7 +507,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2929083088896.0,
+  "total_flos": 3124387872768.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null