Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2d8ecaa57543bdee3ee1bad27c90ea1de1d88f084c3b42b4b4cbe93400a79e0
+oid sha256:9533078a2e104afec6e080cccb1d02c00103abe39a263ee3fc27c9abf5d433a4
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c25ff65f86739f693b36da2af3da23bb86fcf28194abaa1e8f97f444bd4f05e
-size 509176980
+oid sha256:02d35001f66e6beb32c4d5c7ae92d49c0e1d38d1887a4bed98940b2c06a7690c
+size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a000cd4988714838a92a5d53ecd2bb75d51cf96346a5233df9c77ff43b456eef
+oid sha256:2ccd523d7f99090c16ae39b27ac1425ac9f46248c82709c8bdffb1a73da73cf5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb9254c45787266aeb2f2d77203ac5705f2dafc0eddb0332e9ac78a896bc3b27
+oid sha256:cf9d37d8ac9041b1174177f2abdfd03da05c909db05db7e02be2b5adefcdb593
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5060864686965942,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.0599592277251469,
+  "best_metric": 0.4862947463989258,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.07195107327017627,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 10.01,
       "eval_steps_per_second": 2.502,
       "step": 250
+    },
+    {
+      "epoch": 0.062357596834152776,
+      "grad_norm": 1.0596331357955933,
+      "learning_rate": 0.0001137664317165683,
+      "loss": 0.5781,
+      "step": 260
+    },
+    {
+      "epoch": 0.06475596594315865,
+      "grad_norm": 2.4672203063964844,
+      "learning_rate": 0.00010659464816035761,
+      "loss": 0.3945,
+      "step": 270
+    },
+    {
+      "epoch": 0.06715433505216453,
+      "grad_norm": 1.586638331413269,
+      "learning_rate": 9.940535183964242e-05,
+      "loss": 0.6164,
+      "step": 280
+    },
+    {
+      "epoch": 0.0695527041611704,
+      "grad_norm": 1.856692910194397,
+      "learning_rate": 9.22335682834317e-05,
+      "loss": 1.3025,
+      "step": 290
+    },
+    {
+      "epoch": 0.07195107327017627,
+      "grad_norm": 3.173532247543335,
+      "learning_rate": 8.511423770030617e-05,
+      "loss": 1.3479,
+      "step": 300
+    },
+    {
+      "epoch": 0.07195107327017627,
+      "eval_loss": 0.4862947463989258,
+      "eval_runtime": 175.2171,
+      "eval_samples_per_second": 10.022,
+      "eval_steps_per_second": 2.505,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.050147590144e+16,
+  "total_flos": 9.6601771081728e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null