Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a337e774f238d7b3ec7ac5e7b4d8c17a438573785824c6c4f93fa939dbb42ac
+oid sha256:b2934702da1a16ec9cf0fe7bd22dd2586d5706da5dd9ff4d78d58c0435e9e7b5
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76e6ea45a60028da44f5b5f956012ec79978563b710a89964d3165a82ae053c6
+oid sha256:ba7bb1317d85e9df7667b169c430daf74006559af213ae43bd87d55daeaa9387
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1918c7f88de125ce5246fd3922030589a12d0dd55aa33f9cff99ad5f2953d5
+oid sha256:91e9b21dbb7493e4e9f9ed1e9147a8289b785598a628f0287a0464fb065c7e38
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3febf3425d01f9a8670f76097b63bdde8ab2c4b9db69f7e047b33a3ea4a950e
+oid sha256:af8c70a94900d9b287ae32cb4f95d47fb8ad712363557219eb89e270f8b96010
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1823617219924927,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.19892014776925263,
+  "best_metric": 1.1736711263656616,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.2273373117362887,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 35.799,
       "eval_steps_per_second": 8.986,
       "step": 350
+    },
+    {
+      "epoch": 0.20460358056265984,
+      "grad_norm": 0.20923574268817902,
+      "learning_rate": 4.62847451355716e-05,
+      "loss": 1.1516,
+      "step": 360
+    },
+    {
+      "epoch": 0.21028701335606706,
+      "grad_norm": 0.2749004364013672,
+      "learning_rate": 4.035554509080588e-05,
+      "loss": 1.0708,
+      "step": 370
+    },
+    {
+      "epoch": 0.21597044614947428,
+      "grad_norm": 0.3869272768497467,
+      "learning_rate": 3.474128633231992e-05,
+      "loss": 1.0946,
+      "step": 380
+    },
+    {
+      "epoch": 0.2216538789428815,
+      "grad_norm": 0.6056302785873413,
+      "learning_rate": 2.946932096444165e-05,
+      "loss": 1.0444,
+      "step": 390
+    },
+    {
+      "epoch": 0.2273373117362887,
+      "grad_norm": 1.8501702547073364,
+      "learning_rate": 2.456533347250732e-05,
+      "loss": 1.2803,
+      "step": 400
+    },
+    {
+      "epoch": 0.2273373117362887,
+      "eval_loss": 1.1736711263656616,
+      "eval_runtime": 20.689,
+      "eval_samples_per_second": 35.816,
+      "eval_steps_per_second": 8.99,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6876104534982656e+16,
+  "total_flos": 1.927515861103411e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null