Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e34d71116f5d53311f8563d56a4b2a8ae8922d47f01a6478ca680c5ff0226b
+oid sha256:ad2d11a9bddd7770db87f9b42a8ed8e102eed2a3dbd1d6ff22dd654b799a38f8
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c080b252798c977ddf50c71f9c984dc311955998348163bea5508e48fdb17582
+oid sha256:fa098a11b269c334c0f830b179216dca726c074a4d1b03cbd97d828dc8be5c1a
 size 71878996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a47ffee245dfaa06d6600e46c3920bab53b5c0fb7a226fcdbcd88e4859ad27
+oid sha256:4ce025dc182850fd44d97bf4a1c7e72399421e26e7d990faf77c871f6ec090cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0c9560ea4ec378bff0927b20fa3ef4645adc76e93a49024ae06865cbf33e40
+oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.38608717918396,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.14106859460412627,
+  "best_metric": 2.3778696060180664,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.15870216892964203,
   "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": 46.27,
       "eval_steps_per_second": 11.587,
       "step": 400
+    },
+    {
+      "epoch": 0.1445953094692294,
+      "grad_norm": 1.2735577821731567,
+      "learning_rate": 1.9193792065317794e-05,
+      "loss": 1.7573,
+      "step": 410
+    },
+    {
+      "epoch": 0.14812202433433258,
+      "grad_norm": 1.839368224143982,
+      "learning_rate": 1.5271166336279193e-05,
+      "loss": 1.9701,
+      "step": 420
+    },
+    {
+      "epoch": 0.15164873919943572,
+      "grad_norm": 2.7484800815582275,
+      "learning_rate": 1.1763766917677837e-05,
+      "loss": 2.355,
+      "step": 430
+    },
+    {
+      "epoch": 0.1551754540645389,
+      "grad_norm": 4.71662712097168,
+      "learning_rate": 8.688681506918602e-06,
+      "loss": 2.7201,
+      "step": 440
+    },
+    {
+      "epoch": 0.15870216892964203,
+      "grad_norm": 7.315682888031006,
+      "learning_rate": 6.060891611016215e-06,
+      "loss": 2.8181,
+      "step": 450
+    },
+    {
+      "epoch": 0.15870216892964203,
+      "eval_loss": 2.3778696060180664,
+      "eval_runtime": 25.8544,
+      "eval_samples_per_second": 46.182,
+      "eval_steps_per_second": 11.565,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4018810864533504.0,
+  "total_flos": 4525992524120064.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null