Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb43b5e8a5b1ddb020ebd66a1189c5c6b22b3ce382672e6d4261b2d2fcab1ed
+oid sha256:0c0dd60cfa9da17b782db65b8c8e3e3a1c850f72e9a9b220303b4ce989a55047
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8a0ceb741201f1cc69b3312ebd7f01c3bab93b1b3ce7da14ca4622a2b53007
+oid sha256:a2017a7e94d50b7991ad0512f6f9ef68549e37e3a603ef448567a455c5df8c50
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e7048c253e1c2ab61e63163424b1385b51f8d760e67dec41ed61f4ad7749f9e
+oid sha256:7df0ca3ad0a10b20e487b3c58626ef76f8524f36a4e67e15566b1577ef91441e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913ab8b0d366eeaae4f2a144c807ce2c591297e394af2372dd426dd4c3850119
+oid sha256:d6f907450757c510bc85cf5ba3c442a20b76731dbae558c5d4cdc37061b46d99
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2898170948028564,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.5521048999309869,
+  "best_metric": 1.241526484489441,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.6211180124223602,
   "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": 16.359,
       "eval_steps_per_second": 4.13,
       "step": 400
+    },
+    {
+      "epoch": 0.5659075224292616,
+      "grad_norm": 10.461315155029297,
+      "learning_rate": 1.976674108219295e-05,
+      "loss": 2.38,
+      "step": 410
+    },
+    {
+      "epoch": 0.5797101449275363,
+      "grad_norm": 12.781827926635742,
+      "learning_rate": 1.572702204780991e-05,
+      "loss": 2.5618,
+      "step": 420
+    },
+    {
+      "epoch": 0.5935127674258109,
+      "grad_norm": 12.61215877532959,
+      "learning_rate": 1.2114924139101056e-05,
+      "loss": 2.1771,
+      "step": 430
+    },
+    {
+      "epoch": 0.6073153899240856,
+      "grad_norm": 12.710418701171875,
+      "learning_rate": 8.948045133990798e-06,
+      "loss": 2.2393,
+      "step": 440
+    },
+    {
+      "epoch": 0.6211180124223602,
+      "grad_norm": 20.297300338745117,
+      "learning_rate": 6.241813748658489e-06,
+      "loss": 2.4048,
+      "step": 450
+    },
+    {
+      "epoch": 0.6211180124223602,
+      "eval_loss": 1.241526484489441,
+      "eval_runtime": 18.7361,
+      "eval_samples_per_second": 16.279,
+      "eval_steps_per_second": 4.11,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.15499407147008e+16,
+  "total_flos": 8.04936833040384e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null