Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad560950c30ee361bd6e56e76dd7ae3fd01a32e5b336f872a1f88cce5a9878e
+oid sha256:c92d4c7896e11345b2b7c4827d397a458a5d2d9d5f55c52ca5f5f8755221472e
 size 180385008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ab3ea18d7ba145a72a83a961c286a4452f07c9d4e23da8071a0e1c9fdd13c44
+oid sha256:08edc2a91eccab3e32730f5faa4997ea48ebd8270ebdce507af60652bb527dfc
 size 91850618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:673d714655f2ba834946cb072196c6921336a9e8f589e820a8194fa31d869878
+oid sha256:6e7e5a12693f00be90f0da9a98492cc0f44532f9b4cd3b4845e8a211e8f495e8
 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": 2.2623276710510254,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.06610477607007106,
+  "best_metric": 2.243114471435547,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.07436787307882994,
   "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": 58.318,
       "eval_steps_per_second": 14.58,
       "step": 400
+    },
+    {
+      "epoch": 0.06775739547182284,
+      "grad_norm": 2.179595470428467,
+      "learning_rate": 2.081714761313074e-05,
+      "loss": 2.2334,
+      "step": 410
+    },
+    {
+      "epoch": 0.06941001487357462,
+      "grad_norm": 2.5870578289031982,
+      "learning_rate": 1.656275751894957e-05,
+      "loss": 2.1487,
+      "step": 420
+    },
+    {
+      "epoch": 0.07106263427532639,
+      "grad_norm": 3.1885182857513428,
+      "learning_rate": 1.275871237837696e-05,
+      "loss": 2.0605,
+      "step": 430
+    },
+    {
+      "epoch": 0.07271525367707816,
+      "grad_norm": 5.060018539428711,
+      "learning_rate": 9.423545116956494e-06,
+      "loss": 2.3016,
+      "step": 440
+    },
+    {
+      "epoch": 0.07436787307882994,
+      "grad_norm": 12.431950569152832,
+      "learning_rate": 6.573504334335994e-06,
+      "loss": 2.5269,
+      "step": 450
+    },
+    {
+      "epoch": 0.07436787307882994,
+      "eval_loss": 2.243114471435547,
+      "eval_runtime": 43.9155,
+      "eval_samples_per_second": 58.021,
+      "eval_steps_per_second": 14.505,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.00722165153792e+16,
+  "total_flos": 1.13234235359232e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null