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:ca6230cc01573ec53e4f8c05669d763a0c2af83b4983322561c1f22952962d88
+oid sha256:8ee17438b5ce1492e0b476151ab827bb8fa3793b7a5b43203f3c95d4892862f6
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d1aaca7fdaa3c6c630eeb8dbe8c0fe2699a782fd57ef06279dc31d0255257b
+oid sha256:8b65e933c421ccd6d50ff2c6b3089b22b9f07eb09e449b81754a4ef025cfb39d
 size 25986468

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fa71b1aaabfb669344b6aa7e7990f7d1474766bb14bf5d01af02c0fbe1c5c6f
+oid sha256:bcc6fdb64e2e9fefcbbeacc879ffdfa1d0c92a6ba1bb55cb65ddbc807f81eba2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f83d259563f490ff1ff7e4916ac178dc618734e66d8ea8288665df23ceab41
+oid sha256:5fa0f7e2faaa98aa485e5dc42922e1b1819381507fa6961c3be50a0b49af04c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1991453170776367,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.06391307821362946,
+  "best_metric": 1.1967874765396118,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.07190221299033314,
   "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": 53.57,
       "eval_steps_per_second": 13.398,
       "step": 400
+    },
+    {
+      "epoch": 0.06551090516897021,
+      "grad_norm": 0.4205108880996704,
+      "learning_rate": 2.024419859625558e-05,
+      "loss": 1.3338,
+      "step": 410
+    },
+    {
+      "epoch": 0.06710873212431094,
+      "grad_norm": 0.5228121280670166,
+      "learning_rate": 1.610690180741885e-05,
+      "loss": 1.3194,
+      "step": 420
+    },
+    {
+      "epoch": 0.06870655907965167,
+      "grad_norm": 0.5643351674079895,
+      "learning_rate": 1.240755515695374e-05,
+      "loss": 1.1673,
+      "step": 430
+    },
+    {
+      "epoch": 0.07030438603499241,
+      "grad_norm": 0.6846547722816467,
+      "learning_rate": 9.164181489884296e-06,
+      "loss": 1.1176,
+      "step": 440
+    },
+    {
+      "epoch": 0.07190221299033314,
+      "grad_norm": 1.4567266702651978,
+      "learning_rate": 6.392582196693718e-06,
+      "loss": 0.9772,
+      "step": 450
+    },
+    {
+      "epoch": 0.07190221299033314,
+      "eval_loss": 1.1967874765396118,
+      "eval_runtime": 49.249,
+      "eval_samples_per_second": 53.504,
+      "eval_steps_per_second": 13.381,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1181518286225408e+16,
+  "total_flos": 1.25454319091712e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null