Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2b161e8bc9876a4f57639483ab4f03ecf4650ac7a020e045d2c08e4c277d74
+oid sha256:3c9de87c920816ee805ad6f0dcc048fe47192a63dee5a90180ea68ad0ee3ce96
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1734b51ad697d4c7c595278b77f79965d95999e3deb80a31ea76ad67e2d864d
+oid sha256:81529912341fabc5dfb9e803b11f514589f1bbb9a589b89e52e8f8e7b1e0973d
 size 18810356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:550860cff63886cd432a55f8848c8d62e312a5d9b9bf22bfda8663babbdbb92f
+oid sha256:e5a59fb166c95ba4ca8df491eb4ff9d8576a87883e8e6c47c6166836bd7eda3a
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f398ec605d9c9cdba56060aebcb72b7c65adf12fa1c75b756614fa39cc370089
+oid sha256:6c4651949407010a02df1b68ceaab868428ade8f98ceca4a68f2ae05b6e6aa52
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.802130699157715,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.013545546901456146,
+  "best_metric": 2.758694648742676,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.015803138051698837,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 51.245,
       "eval_steps_per_second": 12.814,
       "step": 300
+    },
+    {
+      "epoch": 0.013997065131504685,
+      "grad_norm": 2.6413748264312744,
+      "learning_rate": 7.770300570103407e-05,
+      "loss": 2.5587,
+      "step": 310
+    },
+    {
+      "epoch": 0.014448583361553222,
+      "grad_norm": 2.954564094543457,
+      "learning_rate": 7.08257580765679e-05,
+      "loss": 2.5426,
+      "step": 320
+    },
+    {
+      "epoch": 0.014900101591601761,
+      "grad_norm": 4.0135931968688965,
+      "learning_rate": 6.410282417486901e-05,
+      "loss": 2.715,
+      "step": 330
+    },
+    {
+      "epoch": 0.015351619821650299,
+      "grad_norm": 4.68234395980835,
+      "learning_rate": 5.756695745411955e-05,
+      "loss": 2.6955,
+      "step": 340
+    },
+    {
+      "epoch": 0.015803138051698837,
+      "grad_norm": 10.842591285705566,
+      "learning_rate": 5.125000000000002e-05,
+      "loss": 3.2327,
+      "step": 350
+    },
+    {
+      "epoch": 0.015803138051698837,
+      "eval_loss": 2.758694648742676,
+      "eval_runtime": 188.1269,
+      "eval_samples_per_second": 49.573,
+      "eval_steps_per_second": 12.396,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2708084592476160.0,
+  "total_flos": 3158681030492160.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null