Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a99fa14e7ada8ff0c36834707b0c5d746e1c53941c99e77fed58b765d421cdd9
+oid sha256:ac19c7cad7a1b6bd5a53f3c8fd099c21a2f3a37b1c5abaa67131e148ccc20ec0
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd07d7efb7013759787ce26f571f42bc732d98613d169c2c735f705a0ace71c
+oid sha256:3432c5837af9fc3f28a7f115a414aa542c11527234bb3536fd7f0d6c4f7c56ae
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542da8d551e0c417e013011b8706e763ab5b1bc78b1362718ff9c733b64229b8
+oid sha256:34dd8fce3e6b1676652d98ecfdce8d505350e79db15ba965f80fca277ae52abc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a29a98d7724cf179d3beb2d49a34c568e23cf47a86cb77f3cd39efdcdbcc2de
+oid sha256:110c23ba7ac9436ac98f0e4bb88f393b7c16138e63fbbb47259fe31aa44af728
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1229233741760254,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.29027576197387517,
+  "best_metric": 2.0804994106292725,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.36284470246734396,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 11.69,
       "eval_steps_per_second": 2.943,
       "step": 200
+    },
+    {
+      "epoch": 0.3047895500725689,
+      "grad_norm": 1.1364762783050537,
+      "learning_rate": 0.00015318652713303674,
+      "loss": 2.144,
+      "step": 210
+    },
+    {
+      "epoch": 0.3193033381712627,
+      "grad_norm": 1.0806138515472412,
+      "learning_rate": 0.00014639560219879464,
+      "loss": 2.0368,
+      "step": 220
+    },
+    {
+      "epoch": 0.33381712626995647,
+      "grad_norm": 1.2863917350769043,
+      "learning_rate": 0.0001394103099009319,
+      "loss": 2.0586,
+      "step": 230
+    },
+    {
+      "epoch": 0.3483309143686502,
+      "grad_norm": 1.7007073163986206,
+      "learning_rate": 0.0001322646818813646,
+      "loss": 2.058,
+      "step": 240
+    },
+    {
+      "epoch": 0.36284470246734396,
+      "grad_norm": 2.966454029083252,
+      "learning_rate": 0.0001249935309215281,
+      "loss": 2.0311,
+      "step": 250
+    },
+    {
+      "epoch": 0.36284470246734396,
+      "eval_loss": 2.0804994106292725,
+      "eval_runtime": 24.4819,
+      "eval_samples_per_second": 11.845,
+      "eval_steps_per_second": 2.982,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.157230797337395e+16,
+  "total_flos": 6.467751968872858e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null