Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801e0fc9acdda56cb20318da741c49e654f042b34c32ee13be6a50030b3741fc
+oid sha256:b4279ab7ce5b8617464c086e04e871fb36bf1537af3985d8385719bf5b3582fa
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe7e066f799d64847ea896414e2382b722acb87ceb9ae6678bd6d2bf2e879964
+oid sha256:c3b3d382d023393277ae9ea00df19abb08106276787640364781718bb4d9f7db
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616c4652e6f7f54c5efbafba1126e02f67b94d525b8948316212cae3e86b94bc
+oid sha256:3eb58af1117ad8c80a50ad226231ae68584f87b19807d46e0193fc79ea521ee2
 size 14180

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": 0.7875542640686035,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.021388413590809095,
+  "best_metric": 0.7825099229812622,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.024443901246638963,
   "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": 24.344,
       "eval_steps_per_second": 6.088,
       "step": 350
+    },
+    {
+      "epoch": 0.02199951112197507,
+      "grad_norm": 0.13537642359733582,
+      "learning_rate": 4.62847451355716e-05,
+      "loss": 0.7125,
+      "step": 360
+    },
+    {
+      "epoch": 0.022610608653141042,
+      "grad_norm": 0.15358619391918182,
+      "learning_rate": 4.035554509080588e-05,
+      "loss": 0.7337,
+      "step": 370
+    },
+    {
+      "epoch": 0.023221706184307016,
+      "grad_norm": 0.16124075651168823,
+      "learning_rate": 3.474128633231992e-05,
+      "loss": 0.7682,
+      "step": 380
+    },
+    {
+      "epoch": 0.02383280371547299,
+      "grad_norm": 0.15972477197647095,
+      "learning_rate": 2.946932096444165e-05,
+      "loss": 0.7327,
+      "step": 390
+    },
+    {
+      "epoch": 0.024443901246638963,
+      "grad_norm": 0.16827918589115143,
+      "learning_rate": 2.456533347250732e-05,
+      "loss": 0.819,
+      "step": 400
+    },
+    {
+      "epoch": 0.024443901246638963,
+      "eval_loss": 0.7825099229812622,
+      "eval_runtime": 284.0898,
+      "eval_samples_per_second": 24.253,
+      "eval_steps_per_second": 6.065,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8933419417206784e+16,
+  "total_flos": 3.3069719548329984e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null