Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff89c7db7aba3de06c3b0d401744451daafa848b2d549bcb44ab8c4226837f8
+oid sha256:4400d36b07f3cdfc2612f90e8c7a58c5a9c935815558b5c6a15d93f1b1160fdb
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45bc44327684b83d99826468d9b0b569538399fe3367ffad32754926e43b79bf
+oid sha256:2650514e2f5b36d864b15c40bf6b910360f39f5bb084a4c03e78b91b7c618653
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:832c2c442cbf71daf394540d727b118ab5b6db1652a2abe4106d73ca87deac6e
+oid sha256:330796178c89f0a970539182417e271745b4e562e5f628fb3ab81d04129143f0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4210d0f4c79be19a1b0c8a85facc89fa1bc09497d44c3c3383a1a0c00e4709d7
+oid sha256:8c579f5f648f371ddcf6d84448bace40e1d46168d2f7b5fae9b6105a9c79d201
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9632947444915771,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.5805515239477503,
+  "best_metric": 1.9480090141296387,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.6531204644412192,
   "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": 11.89,
       "eval_steps_per_second": 2.993,
       "step": 400
+    },
+    {
+      "epoch": 0.5950653120464441,
+      "grad_norm": 0.8925508856773376,
+      "learning_rate": 2.033969009906811e-05,
+      "loss": 1.9807,
+      "step": 410
+    },
+    {
+      "epoch": 0.6095791001451378,
+      "grad_norm": 0.901614248752594,
+      "learning_rate": 1.6182877759340637e-05,
+      "loss": 1.9157,
+      "step": 420
+    },
+    {
+      "epoch": 0.6240928882438317,
+      "grad_norm": 1.059577226638794,
+      "learning_rate": 1.2466081360524275e-05,
+      "loss": 1.9516,
+      "step": 430
+    },
+    {
+      "epoch": 0.6386066763425254,
+      "grad_norm": 1.138191819190979,
+      "learning_rate": 9.207408761062996e-06,
+      "loss": 1.9491,
+      "step": 440
+    },
+    {
+      "epoch": 0.6531204644412192,
+      "grad_norm": 3.2761425971984863,
+      "learning_rate": 6.422735886300764e-06,
+      "loss": 1.889,
+      "step": 450
+    },
+    {
+      "epoch": 0.6531204644412192,
+      "eval_loss": 1.9480090141296387,
+      "eval_runtime": 24.632,
+      "eval_samples_per_second": 11.773,
+      "eval_steps_per_second": 2.964,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0333318014409114e+17,
+  "total_flos": 1.1634410976077414e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null