Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f983e7c66880ee98c81515a520726d30dd4b8a9596315f1fd5b4e14f654bd60
+oid sha256:baeb7b0af2e0f1adc50527ed15e70e16db821ed91041cfe3aa3c126d71b78f70
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c913e77242d333f2e2aae912580d07bc70f85385b0b0cad97cad20f525fa68c5
+oid sha256:525a1aa1ac209279c690ddbf2ab0ae66f8f74f79f0c46bb37fe0e886cdccaaff
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1653c951f7583b8f259d5b4ec4d815208b4d0f7002c38b7d86a02261c520a5bf
+oid sha256:8f50382a7b74721780781f51be66dff804a86521a06c2e4edc45eb8b3dd006cd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
+oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0443766117095947,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.14432617716038246,
+  "best_metric": 2.035742998123169,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.16236694930543027,
   "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": 15.894,
       "eval_steps_per_second": 3.977,
       "step": 400
+    },
+    {
+      "epoch": 0.14793433158939204,
+      "grad_norm": 1.3404114246368408,
+      "learning_rate": 2.081714761313074e-05,
+      "loss": 2.2207,
+      "step": 410
+    },
+    {
+      "epoch": 0.1515424860184016,
+      "grad_norm": 1.5793532133102417,
+      "learning_rate": 1.656275751894957e-05,
+      "loss": 2.0376,
+      "step": 420
+    },
+    {
+      "epoch": 0.15515064044741114,
+      "grad_norm": 1.5471128225326538,
+      "learning_rate": 1.275871237837696e-05,
+      "loss": 2.1071,
+      "step": 430
+    },
+    {
+      "epoch": 0.15875879487642072,
+      "grad_norm": 2.025006055831909,
+      "learning_rate": 9.423545116956494e-06,
+      "loss": 1.9576,
+      "step": 440
+    },
+    {
+      "epoch": 0.16236694930543027,
+      "grad_norm": 3.5461795330047607,
+      "learning_rate": 6.573504334335994e-06,
+      "loss": 1.9234,
+      "step": 450
+    },
+    {
+      "epoch": 0.16236694930543027,
+      "eval_loss": 2.035742998123169,
+      "eval_runtime": 73.4959,
+      "eval_samples_per_second": 15.878,
+      "eval_steps_per_second": 3.973,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.797129560142643e+16,
+  "total_flos": 8.758806966593126e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null