Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20bfa195723cb5e5627947c48f26aab5046a0409b339033a16d2f22718804e40
+oid sha256:5675512a0f4a0690adb6856c62f98e6c7a91c16adfec78eb7b5c6873212c9b16
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:211637f21c3abdb1716a1fabcb8c5e63d3351e48bc0fa4f7667befe8ef431889
+oid sha256:e971049b33d8baa5fd33a0f4ec20729c0f4b6803ca663ed3694eeb510f3b0849
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c4ead089cf94832276d3e2bad2b7c18561fea4acccb1d58107ff810a0ef91cd
+oid sha256:8a14570f9e7677b9c2cd15afab549c8871548f9b1c9a9a9381b998248d253daa
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2661f04b964aebdbfc5fe2d76ad72c51b84450f62ecbdcf121c15876692362c9
+oid sha256:275a3f467a10238121d3751994e96dac39b01caeff52940c5c443f8040986af4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2757760286331177,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.23048112935753384,
+  "best_metric": 1.2717281579971313,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.25929127052722556,
   "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": 16.276,
       "eval_steps_per_second": 4.075,
       "step": 400
+    },
+    {
+      "epoch": 0.23624315759147219,
+      "grad_norm": 0.691465437412262,
+      "learning_rate": 2.053067310469316e-05,
+      "loss": 1.7634,
+      "step": 410
+    },
+    {
+      "epoch": 0.24200518582541056,
+      "grad_norm": 0.6821807026863098,
+      "learning_rate": 1.633482966318421e-05,
+      "loss": 1.3809,
+      "step": 420
+    },
+    {
+      "epoch": 0.2477672140593489,
+      "grad_norm": 0.761147141456604,
+      "learning_rate": 1.2583133767665349e-05,
+      "loss": 1.3838,
+      "step": 430
+    },
+    {
+      "epoch": 0.2535292422932872,
+      "grad_norm": 0.964479923248291,
+      "learning_rate": 9.293863303420395e-06,
+      "loss": 1.1305,
+      "step": 440
+    },
+    {
+      "epoch": 0.25929127052722556,
+      "grad_norm": 1.2261676788330078,
+      "learning_rate": 6.483043265514856e-06,
+      "loss": 0.7941,
+      "step": 450
+    },
+    {
+      "epoch": 0.25929127052722556,
+      "eval_loss": 1.2717281579971313,
+      "eval_runtime": 44.7154,
+      "eval_samples_per_second": 16.348,
+      "eval_steps_per_second": 4.093,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.243788459599462e+16,
+  "total_flos": 8.16127674459095e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null