Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f39ff5e6a7c7396010dc085133725848362b179f4abf610d68799ae35d51bb3
+oid sha256:7ad560950c30ee361bd6e56e76dd7ae3fd01a32e5b336f872a1f88cce5a9878e
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d2c2f65295658588aa56c07b522f2f8be70741c8a3cfbe7820efe3613200ac
+oid sha256:0ab3ea18d7ba145a72a83a961c286a4452f07c9d4e23da8071a0e1c9fdd13c44
 size 91850618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86c50309d9afc9a45e9cec60e2bbd6cc0fa89899b185f912525ec2d33c4d1f1
+oid sha256:673d714655f2ba834946cb072196c6921336a9e8f589e820a8194fa31d869878
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aefa5c0989fb1076f44dee5ec81119730caab480902e567590e4c3defecd81d
+oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2891488075256348,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.05784167906131218,
+  "best_metric": 2.2623276710510254,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.06610477607007106,
   "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": 58.345,
       "eval_steps_per_second": 14.586,
       "step": 350
+    },
+    {
+      "epoch": 0.059494298463063956,
+      "grad_norm": 1.9254217147827148,
+      "learning_rate": 4.804797352168861e-05,
+      "loss": 2.1897,
+      "step": 360
+    },
+    {
+      "epoch": 0.061146917864815735,
+      "grad_norm": 2.3489015102386475,
+      "learning_rate": 4.189289918950325e-05,
+      "loss": 2.2346,
+      "step": 370
+    },
+    {
+      "epoch": 0.0627995372665675,
+      "grad_norm": 3.7030725479125977,
+      "learning_rate": 3.606476390688449e-05,
+      "loss": 2.2318,
+      "step": 380
+    },
+    {
+      "epoch": 0.06445215666831929,
+      "grad_norm": 5.087347507476807,
+      "learning_rate": 3.0591961763087043e-05,
+      "loss": 2.2742,
+      "step": 390
+    },
+    {
+      "epoch": 0.06610477607007106,
+      "grad_norm": 16.04279899597168,
+      "learning_rate": 2.550115570003141e-05,
+      "loss": 2.5913,
+      "step": 400
+    },
+    {
+      "epoch": 0.06610477607007106,
+      "eval_loss": 2.2623276710510254,
+      "eval_runtime": 43.6913,
+      "eval_samples_per_second": 58.318,
+      "eval_steps_per_second": 14.58,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8808497424629760.0,
+  "total_flos": 1.00722165153792e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null