Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13f138ba6167106093aa397d7dded2d846b6f422673fe8fad30cac7880e1e4b5
+oid sha256:2ca316e3b7fb9cc71f88c5e7f9d6b50ef8602837f741059ed91d212515da9b65
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c36784fdbf48a98b761da6365177bc9bc38c0827a14eef6e03d8d78e71480d1
+oid sha256:9af828b9f11cf133960b996213e9ce2588f29152e3b65859a85fbc978847fb5f
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e2b5f8430e50053db1f0e53189e7ac7abc289b048f9d1df1b0464a7eebb1e9
+oid sha256:e2e3416f587b35a71d1b3778b5dfc773e3509866855d8726ac2a4de01c335195
 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": 1.8981908559799194,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.10922247252372176,
+  "best_metric": 1.8793390989303589,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.12287528158918698,
   "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": 25.154,
       "eval_steps_per_second": 6.288,
       "step": 400
+    },
+    {
+      "epoch": 0.1119530343368148,
+      "grad_norm": 11.885726928710938,
+      "learning_rate": 4.695790918802576e-05,
+      "loss": 7.2024,
+      "step": 410
+    },
+    {
+      "epoch": 0.11468359614990785,
+      "grad_norm": 11.538261413574219,
+      "learning_rate": 4.252125897855932e-05,
+      "loss": 7.3657,
+      "step": 420
+    },
+    {
+      "epoch": 0.11741415796300089,
+      "grad_norm": 12.95737075805664,
+      "learning_rate": 3.824753850538082e-05,
+      "loss": 7.6156,
+      "step": 430
+    },
+    {
+      "epoch": 0.12014471977609394,
+      "grad_norm": 13.987143516540527,
+      "learning_rate": 3.414886209349615e-05,
+      "loss": 7.5926,
+      "step": 440
+    },
+    {
+      "epoch": 0.12287528158918698,
+      "grad_norm": 17.603551864624023,
+      "learning_rate": 3.0236847886501542e-05,
+      "loss": 7.9609,
+      "step": 450
+    },
+    {
+      "epoch": 0.12287528158918698,
+      "eval_loss": 1.8793390989303589,
+      "eval_runtime": 244.4883,
+      "eval_samples_per_second": 25.228,
+      "eval_steps_per_second": 6.307,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.812517994725376e+17,
+  "total_flos": 3.164082744066048e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null