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:dc43e3f4958106b99d77a6abfb255211c1873a7450e2ce03818e5a706e1ead22
+oid sha256:7ee54646a8d8e086da73ea4ea766d37f331724745da6db8860da669060ea0ad3
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6613b5f4d49d0ba3431ca2aae2a79890563b406b94495e99caae25883a190d3
+oid sha256:88f52de36a984efd41e524a6385fb0d045ab097df06346cd62fde039dc559fb0
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8bccb02c4fd4e6c8c34f0a4232e2b2e52997c515bc635e97c60de1fa73c87db
+oid sha256:3b755806378981de9043df7e6fb9040a4956d482785c45c1100277e6bb6b7929
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303e83c678e93581d63a3650d04963a2cf914298a9658799e3e1f49cf7c8604f
+oid sha256:f03fffc232f1b8a6305d6fa9076c1e1bca28e4d7666df088caa1812431cf9135
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8156729936599731,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.14730252255569876,
+  "best_metric": 0.8050962686538696,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.1657153378751611,
   "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": 10.883,
       "eval_steps_per_second": 2.721,
       "step": 400
+    },
+    {
+      "epoch": 0.15098508561959123,
+      "grad_norm": 0.9257370233535767,
+      "learning_rate": 1.9384775070942844e-05,
+      "loss": 1.6284,
+      "step": 410
+    },
+    {
+      "epoch": 0.1546676486834837,
+      "grad_norm": 1.1275734901428223,
+      "learning_rate": 1.5423118240122765e-05,
+      "loss": 1.6474,
+      "step": 420
+    },
+    {
+      "epoch": 0.15835021174737618,
+      "grad_norm": 1.0271503925323486,
+      "learning_rate": 1.188081932481891e-05,
+      "loss": 1.5823,
+      "step": 430
+    },
+    {
+      "epoch": 0.16203277481126865,
+      "grad_norm": 0.9594849944114685,
+      "learning_rate": 8.775136049276001e-06,
+      "loss": 1.6091,
+      "step": 440
+    },
+    {
+      "epoch": 0.1657153378751611,
+      "grad_norm": 1.3645907640457153,
+      "learning_rate": 6.121198990230306e-06,
+      "loss": 1.4868,
+      "step": 450
+    },
+    {
+      "epoch": 0.1657153378751611,
+      "eval_loss": 0.8050962686538696,
+      "eval_runtime": 105.3167,
+      "eval_samples_per_second": 10.862,
+      "eval_steps_per_second": 2.716,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2082564750009958e+17,
+  "total_flos": 1.3587688094642995e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null