Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2958ef7928d42d39f72ee023b6e28ef4769c1b49583d5ff6aab778b434f8d174
+oid sha256:787f2551b6ac8583af6eea1cb71af383da2ce2104f41d2230e2a07da90e5d21c
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ed1481e5abb077d9b40483275d6d09b48248b205ccf6eb7d0e0f30b37264fe8
-size 37134420
+oid sha256:1f7a6512e6cf7cc15a8a708ef1e3cc6ec2b4bf938b14afef26cc69ace80971c5
+size 37134740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc836fc73d9e93b435db16205a92787f798fa2d8d53f4ff715f4c6c6f3cc1719
+oid sha256:19e2e3b1a3fb431d188c6e72e3cee4c7684c54ae7e071aa6381813d0d35eaabc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e4a8d9505ab5e0891e71b89f41010a5997ec96d8f1c5ec4c12ce973f5bf2fa
+oid sha256:a8d9346c4fcc90fb1ec8546736583b76a4fae6bc25cb93181337c187d15da94a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2301549911499023,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.16323865491348352,
+  "best_metric": 1.2161424160003662,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.1958863858961802,
   "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": 61.439,
       "eval_steps_per_second": 15.366,
       "step": 250
+    },
+    {
+      "epoch": 0.16976820111002286,
+      "grad_norm": 0.05828835442662239,
+      "learning_rate": 0.0001237326699871115,
+      "loss": 1.1586,
+      "step": 260
+    },
+    {
+      "epoch": 0.1762977473065622,
+      "grad_norm": 0.09446071833372116,
+      "learning_rate": 0.00011852887240871145,
+      "loss": 1.2516,
+      "step": 270
+    },
+    {
+      "epoch": 0.18282729350310153,
+      "grad_norm": 0.15607990324497223,
+      "learning_rate": 0.00011327255272837221,
+      "loss": 1.2933,
+      "step": 280
+    },
+    {
+      "epoch": 0.18935683969964087,
+      "grad_norm": 0.35059285163879395,
+      "learning_rate": 0.00010797861055530831,
+      "loss": 1.2938,
+      "step": 290
+    },
+    {
+      "epoch": 0.1958863858961802,
+      "grad_norm": 1.048234462738037,
+      "learning_rate": 0.00010266205214377748,
+      "loss": 1.1819,
+      "step": 300
+    },
+    {
+      "epoch": 0.1958863858961802,
+      "eval_loss": 1.2161424160003662,
+      "eval_runtime": 42.3336,
+      "eval_samples_per_second": 60.921,
+      "eval_steps_per_second": 15.236,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.066988458927718e+16,
+  "total_flos": 4.875582621037363e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null