Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac6d465212671f645f0c5c05ebf728f1d70d12d7ce543038e72cf8f653cb838
+oid sha256:6cf2d746cf9c1bcb2d13ea94c2632bccb5f2b274e91f8cac38e63024aae99092
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923793c3226af58b708818fdf54ec6644050e5ff369f5d3e7bf667b6fd94bb04
+oid sha256:30cf4209b1ecb2af9a25148698df44405d1d3663d9c64fbc4517055affd85545
 size 51418452

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:436e3f26d21c67fae4787bf3356ab50f12b0bd9b8481bf84f7755722eb0ab42a
+oid sha256:18c7bf7a082fa3558d497f2e3ffae21e2ac8e74eeecff79cda5124ee33566210
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0a47cc675a5d4ba5fe8c0d42564476e1fe842799977ab67bf2a8317adef53f
+oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7500874400138855,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.47072668431891734,
+  "best_metric": 0.7452362179756165,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.529567519858782,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 22.085,
       "eval_steps_per_second": 5.521,
       "step": 400
+    },
+    {
+      "epoch": 0.48249485142689025,
+      "grad_norm": 0.8447908759117126,
+      "learning_rate": 4.695790918802576e-05,
+      "loss": 5.6785,
+      "step": 410
+    },
+    {
+      "epoch": 0.4942630185348632,
+      "grad_norm": 0.8665351867675781,
+      "learning_rate": 4.252125897855932e-05,
+      "loss": 4.643,
+      "step": 420
+    },
+    {
+      "epoch": 0.5060311856428361,
+      "grad_norm": 0.7426034808158875,
+      "learning_rate": 3.824753850538082e-05,
+      "loss": 2.7279,
+      "step": 430
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.9415715932846069,
+      "learning_rate": 3.414886209349615e-05,
+      "loss": 1.2065,
+      "step": 440
+    },
+    {
+      "epoch": 0.529567519858782,
+      "grad_norm": 1.705180048942566,
+      "learning_rate": 3.0236847886501542e-05,
+      "loss": 1.3062,
+      "step": 450
+    },
+    {
+      "epoch": 0.529567519858782,
+      "eval_loss": 0.7452362179756165,
+      "eval_runtime": 64.9352,
+      "eval_samples_per_second": 22.053,
+      "eval_steps_per_second": 5.513,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6931377852330803e+17,
+  "total_flos": 3.030240531264307e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null