Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86842072a86c1fbfe24bb2e711e1666d8d3323731b0a6b71e64e1b2cbbaf52ed
+oid sha256:8210a0b50da7fd33208abfb412fac5049c16b6f63ced0bcdbf53909d1d5daca1
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532da984f6568a047876364cd8a190012d03c61d1b67c32346b02636eb944b11
+oid sha256:d1e944da48fb616f6b095af7675b849cdc14a65623c7b346efe86e4780e183c1
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b47a025ca265ce7c3bef466cc3aa9a5f0953f8b9621fcbdbd0af52bd3a48206
+oid sha256:8911b5f46997fa9f12867e8137d6f3c05ab465feed07980c8e04741b612f58c8
 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": 0.8729479908943176,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.037778617302606725,
+  "best_metric": 0.864070475101471,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.042500944465432566,
   "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": 17.358,
       "eval_steps_per_second": 4.342,
       "step": 400
+    },
+    {
+      "epoch": 0.038723082735171895,
+      "grad_norm": 0.7448956966400146,
+      "learning_rate": 2.081714761313074e-05,
+      "loss": 0.917,
+      "step": 410
+    },
+    {
+      "epoch": 0.039667548167737064,
+      "grad_norm": 0.9566893577575684,
+      "learning_rate": 1.656275751894957e-05,
+      "loss": 1.004,
+      "step": 420
+    },
+    {
+      "epoch": 0.04061201360030223,
+      "grad_norm": 0.772722065448761,
+      "learning_rate": 1.275871237837696e-05,
+      "loss": 0.8142,
+      "step": 430
+    },
+    {
+      "epoch": 0.0415564790328674,
+      "grad_norm": 1.1294012069702148,
+      "learning_rate": 9.423545116956494e-06,
+      "loss": 0.7214,
+      "step": 440
+    },
+    {
+      "epoch": 0.042500944465432566,
+      "grad_norm": 3.888120174407959,
+      "learning_rate": 6.573504334335994e-06,
+      "loss": 0.7121,
+      "step": 450
+    },
+    {
+      "epoch": 0.042500944465432566,
+      "eval_loss": 0.864070475101471,
+      "eval_runtime": 257.296,
+      "eval_samples_per_second": 17.326,
+      "eval_steps_per_second": 4.334,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.7372490686464e+16,
+  "total_flos": 7.5783538212864e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null