Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0600860070dced4e9a1ac14d5c0d0c0a306341d1f7fc3a833518da321be2ca0
+oid sha256:80e34d71116f5d53311f8563d56a4b2a8ae8922d47f01a6478ca680c5ff0226b
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb960441cce8834648edffebcce8f9638a322a69f4c1ea17d3102f53b4e6b94
+oid sha256:c080b252798c977ddf50c71f9c984dc311955998348163bea5508e48fdb17582
 size 71878996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c65e98e5d3f07914004955bea2ba490007914966234c8478b7ee57e6db7fcdc8
+oid sha256:c0a47ffee245dfaa06d6600e46c3920bab53b5c0fb7a226fcdbcd88e4859ad27
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c15c93e093cba090b2f3583592294b602741c9988a1980b16636e603079f25
+oid sha256:2c0c9560ea4ec378bff0927b20fa3ef4645adc76e93a49024ae06865cbf33e40
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.405674695968628,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.12343502027861047,
+  "best_metric": 2.38608717918396,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.14106859460412627,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 46.151,
       "eval_steps_per_second": 11.557,
       "step": 350
+    },
+    {
+      "epoch": 0.12696173514371364,
+      "grad_norm": 1.2822436094284058,
+      "learning_rate": 4.430111320118996e-05,
+      "loss": 1.6962,
+      "step": 360
+    },
+    {
+      "epoch": 0.1304884500088168,
+      "grad_norm": 2.262040853500366,
+      "learning_rate": 3.862602172977134e-05,
+      "loss": 2.0943,
+      "step": 370
+    },
+    {
+      "epoch": 0.13401516487391996,
+      "grad_norm": 3.736957550048828,
+      "learning_rate": 3.325237406093478e-05,
+      "loss": 2.6009,
+      "step": 380
+    },
+    {
+      "epoch": 0.1375418797390231,
+      "grad_norm": 4.0212321281433105,
+      "learning_rate": 2.820635006596558e-05,
+      "loss": 2.7693,
+      "step": 390
+    },
+    {
+      "epoch": 0.14106859460412627,
+      "grad_norm": 14.131185531616211,
+      "learning_rate": 2.351253346654272e-05,
+      "loss": 3.0325,
+      "step": 400
+    },
+    {
+      "epoch": 0.14106859460412627,
+      "eval_loss": 2.38608717918396,
+      "eval_runtime": 25.8049,
+      "eval_samples_per_second": 46.27,
+      "eval_steps_per_second": 11.587,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3516459506466816.0,
+  "total_flos": 4018810864533504.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null