Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb746b375916d993fdbd038976e286207ed000be26a8b6d441ff024e7356e19
+oid sha256:07bee832f06780a5be4e32fbb7f07653d8bf525239d17dbcf3682f3367f4ecad
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e375fef72ce3620c2a48a468e9ae068020b22d3a68f06824f1b0359423810c
+oid sha256:676fc96f6dd8b3bec153347640f6f09d1d511aea4f6654e3824ce1e9eebdb448
 size 591208618

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:985c3c780693d1e6bbb0e8f5ec9df28d42d9a9e6436b616b48b9e067157d0c2b
+oid sha256:47c8baa6870e4a9e07f813aaa5b50fca6773957dad188216f155ee519be011b2
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3319cd7470c264bee54329e29b5ec91d9c9a4808c2d538532945e481104091
+oid sha256:480dd149a7e539c29c101c27ba4934fb8fdb062e60fdebf07dc67a0615db8e80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.07232455164194107,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1500",
-  "epoch": 1.5357051446122343,
+  "best_metric": 0.07142073661088943,
+  "best_model_checkpoint": "miner_id_24/checkpoint-2000",
+  "epoch": 2.047606859482979,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,84 @@
       "eval_samples_per_second": 22.096,
       "eval_steps_per_second": 5.534,
       "step": 1500
+    },
+    {
+      "epoch": 1.586895316099309,
+      "grad_norm": 0.05019761994481087,
+      "learning_rate": 2.708829915600401e-05,
+      "loss": 0.0643,
+      "step": 1550
+    },
+    {
+      "epoch": 1.6380854875863835,
+      "grad_norm": 0.05420317500829697,
+      "learning_rate": 2.161309778686967e-05,
+      "loss": 0.0586,
+      "step": 1600
+    },
+    {
+      "epoch": 1.689275659073458,
+      "grad_norm": 0.05063829943537712,
+      "learning_rate": 1.6690435978090822e-05,
+      "loss": 0.0623,
+      "step": 1650
+    },
+    {
+      "epoch": 1.7404658305605323,
+      "grad_norm": 0.05515941604971886,
+      "learning_rate": 1.2353940501334881e-05,
+      "loss": 0.06,
+      "step": 1700
+    },
+    {
+      "epoch": 1.7916560020476069,
+      "grad_norm": 0.05263717472553253,
+      "learning_rate": 8.633234017856605e-06,
+      "loss": 0.0612,
+      "step": 1750
+    },
+    {
+      "epoch": 1.8428461735346815,
+      "grad_norm": 0.05191710218787193,
+      "learning_rate": 5.55373272568495e-06,
+      "loss": 0.0592,
+      "step": 1800
+    },
+    {
+      "epoch": 1.8940363450217559,
+      "grad_norm": 0.055449921637773514,
+      "learning_rate": 3.1364727412186366e-06,
+      "loss": 0.0603,
+      "step": 1850
+    },
+    {
+      "epoch": 1.9452265165088303,
+      "grad_norm": 0.0455612912774086,
+      "learning_rate": 1.3979664012209619e-06,
+      "loss": 0.0621,
+      "step": 1900
+    },
+    {
+      "epoch": 1.9964166879959047,
+      "grad_norm": 0.09055913984775543,
+      "learning_rate": 3.5008946681634066e-07,
+      "loss": 0.0642,
+      "step": 1950
+    },
+    {
+      "epoch": 2.047606859482979,
+      "grad_norm": 0.0834808498620987,
+      "learning_rate": 0.0,
+      "loss": 0.0524,
+      "step": 2000
+    },
+    {
+      "epoch": 2.047606859482979,
+      "eval_loss": 0.07142073661088943,
+      "eval_runtime": 75.0403,
+      "eval_samples_per_second": 21.922,
+      "eval_steps_per_second": 5.49,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -272,12 +350,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.535802208242893e+17,
+  "total_flos": 6.036170126603059e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null