Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13638ca269452274c469a728c2e57084f2a5f5e3de23078e2e45568c4c56b1a9
+oid sha256:dc7fa99fdd4d6c31b329b1be72e788d9f167967026cbccc1742776961f71112f
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ad05a9806caee8297429916b47846749055e2bc8e9df1c5b1fe26ad1fd23898
+oid sha256:64d74fbd491a79b79033eee61686b1179a70c12150e1a47c3de6fcd6d9a0f974
 size 13005370

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41c9fae84cbbe816955ea508cba4ec30911e58aad9024588ce5d9da34c93b91a
+oid sha256:50200231444aa1f757768f96ac0fd114116e02d48b0d3a0cea9fc67de5069f9f
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89df26d2648b7bbd96c19b1cc0947215f3b7f788b7b6e7a6d1179c8d03cbffea
+oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.877124786376953,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.003861861224016915,
+  "best_metric": 2.874143123626709,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.004344593877019029,
   "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": 73.241,
       "eval_steps_per_second": 18.31,
       "step": 400
+    },
+    {
+      "epoch": 0.003958407754617338,
+      "grad_norm": 13.854421615600586,
+      "learning_rate": 1.9671249579380422e-05,
+      "loss": 5.1705,
+      "step": 410
+    },
+    {
+      "epoch": 0.00405495428521776,
+      "grad_norm": 16.01457977294922,
+      "learning_rate": 1.5651046095888127e-05,
+      "loss": 5.1288,
+      "step": 420
+    },
+    {
+      "epoch": 0.004151500815818184,
+      "grad_norm": 13.360790252685547,
+      "learning_rate": 1.205639793553052e-05,
+      "loss": 5.3445,
+      "step": 430
+    },
+    {
+      "epoch": 0.004248047346418606,
+      "grad_norm": 15.994139671325684,
+      "learning_rate": 8.904817862812098e-06,
+      "loss": 5.7003,
+      "step": 440
+    },
+    {
+      "epoch": 0.004344593877019029,
+      "grad_norm": 25.979543685913086,
+      "learning_rate": 6.211660059051443e-06,
+      "loss": 6.8299,
+      "step": 450
+    },
+    {
+      "epoch": 0.004344593877019029,
+      "eval_loss": 2.874143123626709,
+      "eval_runtime": 602.9673,
+      "eval_samples_per_second": 72.329,
+      "eval_steps_per_second": 18.082,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4097626853081088.0,
+  "total_flos": 4610936480464896.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null