Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1df2bd3aa6680bee7a39f957b5bd8d788315757f76aa07094cc7843367ca79
+oid sha256:e0b308a3fbbdfa2b5694643537f8b5f09d7f0404d0512c36e5cd5370e814ca65
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c3bfa8cd64ca989b964e39b45b51c7c0a843572ef38de6dfa27e80422ac2930
+oid sha256:ad835099fffb176e02153263d72686823638247052923fab94c9fe821ea9742f
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7baf5d87b3052ff1a491f25982bd8db187c7ac89df68ba711e87e010ca0ccf2a
+oid sha256:dc7f05a3504d69cd434a3c8e47dedbf1f1af3bc670e42109106144e46b752524
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6230a4f38a0ea478447f5ea0afea90b5855d705f677280e45e7e6abb464194a3
+oid sha256:303e83c678e93581d63a3650d04963a2cf914298a9658799e3e1f49cf7c8604f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.731415748596191,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.40816326530612246,
+  "best_metric": 11.730313301086426,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.46647230320699706,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 221.846,
       "eval_steps_per_second": 55.922,
       "step": 350
+    },
+    {
+      "epoch": 0.4198250728862974,
+      "grad_norm": 0.2629506587982178,
+      "learning_rate": 4.4741920297719214e-05,
+      "loss": 11.7342,
+      "step": 360
+    },
+    {
+      "epoch": 0.4314868804664723,
+      "grad_norm": 0.24675559997558594,
+      "learning_rate": 3.901036025444568e-05,
+      "loss": 11.7363,
+      "step": 370
+    },
+    {
+      "epoch": 0.44314868804664725,
+      "grad_norm": 0.23566007614135742,
+      "learning_rate": 3.358324345457592e-05,
+      "loss": 11.73,
+      "step": 380
+    },
+    {
+      "epoch": 0.45481049562682213,
+      "grad_norm": 0.24955187737941742,
+      "learning_rate": 2.8487010265626928e-05,
+      "loss": 11.7289,
+      "step": 390
+    },
+    {
+      "epoch": 0.46647230320699706,
+      "grad_norm": 0.33412033319473267,
+      "learning_rate": 2.3746489023423744e-05,
+      "loss": 11.7211,
+      "step": 400
+    },
+    {
+      "epoch": 0.46647230320699706,
+      "eval_loss": 11.730313301086426,
+      "eval_runtime": 1.6308,
+      "eval_samples_per_second": 221.361,
+      "eval_steps_per_second": 55.8,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 18127631155200.0,
+  "total_flos": 20717292748800.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null