Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783f430e39c1a0a3580af314870f5a1fb5370147d2f31754c13f9b35e0af4fa6
+oid sha256:914e17c9232d999305e53c7195344bab00afb03e0dfa40b62493e4883bd527a1
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:086bb265e820ab945d1978839d90771e2c6752bae98469f227ac389f91deb03a
+oid sha256:377b11079887c815f3c172dd8c818e4d4535ef96a052ad53a1af6f99b9b0be24
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e045276e0937c8c5281651aa9ed8e933d9b3aa852e701288b0ef181f067313b3
+oid sha256:f065ae75e7b359cde6f6697daba7b031febbae786983fc3b48fcf1c17adec992
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e4a64d71eed58bad723d1496b310be4dbd45cd96d8ef2f7cd1e195fe59bff7c
+oid sha256:bc179f00b2227acaa3346fbc12b482f11319c504cfa09741eaad17d644154679
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.8749983310699463,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.011894142134998514,
+  "best_metric": 2.844726085662842,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.014867677668748141,
   "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": 47.495,
       "eval_steps_per_second": 11.874,
       "step": 200
+    },
+    {
+      "epoch": 0.012488849241748439,
+      "grad_norm": 0.6521171927452087,
+      "learning_rate": 0.0001488714136926695,
+      "loss": 2.9137,
+      "step": 210
+    },
+    {
+      "epoch": 0.013083556348498365,
+      "grad_norm": 0.7320899963378906,
+      "learning_rate": 0.0001422717824185469,
+      "loss": 2.8405,
+      "step": 220
+    },
+    {
+      "epoch": 0.01367826345524829,
+      "grad_norm": 0.8370326161384583,
+      "learning_rate": 0.00013548325891780705,
+      "loss": 2.8327,
+      "step": 230
+    },
+    {
+      "epoch": 0.014272970561998216,
+      "grad_norm": 1.010695219039917,
+      "learning_rate": 0.0001285389161945656,
+      "loss": 2.8228,
+      "step": 240
+    },
+    {
+      "epoch": 0.014867677668748141,
+      "grad_norm": 1.9595260620117188,
+      "learning_rate": 0.0001214725863885273,
+      "loss": 2.772,
+      "step": 250
+    },
+    {
+      "epoch": 0.014867677668748141,
+      "eval_loss": 2.844726085662842,
+      "eval_runtime": 150.3953,
+      "eval_samples_per_second": 47.076,
+      "eval_steps_per_second": 11.769,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2090767472394240.0,
+  "total_flos": 2622471269253120.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null