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:aee6ed3c05428b44110e484c5d881e7899a865aa805b08a623e67ef8441824e6
+oid sha256:308f33ad8053cbcc02d0227051ea3026c078a62bb037b7e5abbf349a89bd9491
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59271043586c4698f23841d46c3d037e7aaef955ddd49c140067880e1a67514a
+oid sha256:960c1541f35e135fd47853f2b869eee8cd36968913f6f5238c0c06fc7be12af7
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6565a983eb60a1ab2039221a989689679339010c7128893817127967f2ed54
+oid sha256:85beaa8ab06d8b11f3c93d6d561d3d052e57d6c7eebec9bffaf3e9025adb2a43
 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": 1.5370266437530518,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.3006872852233677,
+  "best_metric": 1.5103766918182373,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.3436426116838488,
   "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": 17.763,
       "eval_steps_per_second": 4.459,
       "step": 350
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 0.7905786037445068,
+      "learning_rate": 4.804797352168861e-05,
+      "loss": 1.7401,
+      "step": 360
+    },
+    {
+      "epoch": 0.3178694158075601,
+      "grad_norm": 0.8707358241081238,
+      "learning_rate": 4.189289918950325e-05,
+      "loss": 1.5886,
+      "step": 370
+    },
+    {
+      "epoch": 0.32646048109965636,
+      "grad_norm": 1.027565360069275,
+      "learning_rate": 3.606476390688449e-05,
+      "loss": 1.5207,
+      "step": 380
+    },
+    {
+      "epoch": 0.33505154639175255,
+      "grad_norm": 1.4600329399108887,
+      "learning_rate": 3.0591961763087043e-05,
+      "loss": 1.4404,
+      "step": 390
+    },
+    {
+      "epoch": 0.3436426116838488,
+      "grad_norm": 3.2995972633361816,
+      "learning_rate": 2.550115570003141e-05,
+      "loss": 1.1546,
+      "step": 400
+    },
+    {
+      "epoch": 0.3436426116838488,
+      "eval_loss": 1.5103766918182373,
+      "eval_runtime": 27.585,
+      "eval_samples_per_second": 17.763,
+      "eval_steps_per_second": 4.459,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.2207629983744e+16,
+  "total_flos": 7.1094434267136e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null