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:fdc9c818855256a2d9595b789e2224c055496e3d4066240a7229d35ac5b38b3c
+oid sha256:97b39f0d00a6ad653a37273b08acd155f65d9bb6824cc5c7298ba93a3f8499f2
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71f437c8395940b5081b3904e8b773910244d5ec46f0af19360995606ac1b6cc
+oid sha256:cc592481b118a6c1ba8f5fbd0875b0a458f9d1b8668422da2b997ca77945573f
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4cada6afd391b47fa5c6b307469a5326aee5cea9c71a07ccdb423eb1ec04c49
+oid sha256:776c795d5ce00acdc5c227779c9000600f2c67c8f31649cef8f2748ee86585da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935feb3a63b37324efd90f0473c874080c886e9eea264139d581d13a208d37c1
+oid sha256:56d2b9cd8b76db862d8f36c96267d64ff69a21d07ce7f6eb4a0887810e44a8eb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.303171157836914,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.055206680008281,
+  "best_metric": 1.2887566089630127,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.062107515009316126,
   "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": 15.703,
       "eval_steps_per_second": 3.927,
       "step": 400
+    },
+    {
+      "epoch": 0.056586847008488025,
+      "grad_norm": 0.9718238115310669,
+      "learning_rate": 1.928928356813032e-05,
+      "loss": 0.99,
+      "step": 410
+    },
+    {
+      "epoch": 0.05796701400869505,
+      "grad_norm": 1.1397335529327393,
+      "learning_rate": 1.5347142288200977e-05,
+      "loss": 1.2706,
+      "step": 420
+    },
+    {
+      "epoch": 0.05934718100890208,
+      "grad_norm": 1.3210421800613403,
+      "learning_rate": 1.1822293121248375e-05,
+      "loss": 1.3519,
+      "step": 430
+    },
+    {
+      "epoch": 0.0607273480091091,
+      "grad_norm": 1.520512342453003,
+      "learning_rate": 8.731908778097302e-06,
+      "loss": 1.3422,
+      "step": 440
+    },
+    {
+      "epoch": 0.062107515009316126,
+      "grad_norm": 1.921901822090149,
+      "learning_rate": 6.09104530062326e-06,
+      "loss": 1.4561,
+      "step": 450
+    },
+    {
+      "epoch": 0.062107515009316126,
+      "eval_loss": 1.2887566089630127,
+      "eval_runtime": 194.0577,
+      "eval_samples_per_second": 15.722,
+      "eval_steps_per_second": 3.932,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.881983448947098e+16,
+  "total_flos": 8.862517275131904e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null