Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb338e95e0b6e1f2f451a15993110fa2fe791fbdf7a1ec220ffbe60b5957a609
+oid sha256:fe3ad8513eb75dc736315b7297998bf158e5e0527bfe7611c312479de6b290be
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a996cf5e3a773f2ee8c312691fec987be2d26fe2814b46dd94da5a9bd66dcac
+oid sha256:81c42d2bbf0fd47b45c80cf54b3c4c03a05bfa8d807512c99116751a23b1d5eb
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
+oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2322335243225098,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00047112587305513353,
+  "best_metric": 2.1887054443359375,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0009422517461102671,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 4.674,
       "eval_steps_per_second": 2.337,
       "step": 10
+    },
+    {
+      "epoch": 0.0005653510476661603,
+      "grad_norm": 0.5005286335945129,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 2.2123,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007066888095827003,
+      "grad_norm": 0.6007933020591736,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.231,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007066888095827003,
+      "eval_loss": 2.204803705215454,
+      "eval_runtime": 1911.5406,
+      "eval_samples_per_second": 4.676,
+      "eval_steps_per_second": 2.338,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008480265714992403,
+      "grad_norm": 0.6446805596351624,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 2.2172,
+      "step": 18
+    },
+    {
+      "epoch": 0.0009422517461102671,
+      "eval_loss": 2.1887054443359375,
+      "eval_runtime": 1909.8438,
+      "eval_samples_per_second": 4.68,
+      "eval_steps_per_second": 2.34,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null