Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:121dc6327b5af86a847f01632d0e06385eb711c31e565456f5c6062f0cb1879f
+oid sha256:061c34a8ed6809cd0904d70b19b43324b3658413d60d98a7f6d48e2c3bffaef4
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e512cc25240e50625a18a266122f40a09cb785b35b3c6f0fb2afd353cf2d837b
+oid sha256:1b94daf7dfa353715d4f279c393bf368a95cc77df273199877d1783020bbc946
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ec7fddaa93b8a5104562fd596c16565abf5deb95425dbc4839aa86c8fa34863
+oid sha256:0c68f05fddafe7d9625cc40fb5e03db579f2837d87b6225adf6c39031a56218a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:321b462a2538632d6d720f0cf198c8f471dee11f51db9b50cc50d1fa7f132bbe
+oid sha256:60663a94a33586da5717f6f80de424ce9fe5b18a8c8d13d4ca09aa40f102443b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3295012414455414,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.036968576709796676,
+  "best_metric": 0.3060170114040375,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.05545286506469501,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,92 @@
       "eval_samples_per_second": 1.309,
       "eval_steps_per_second": 0.655,
       "step": 20
+    },
+    {
+      "epoch": 0.038817005545286505,
+      "grad_norm": 4.1342549324035645,
+      "learning_rate": 0.00019975141040730207,
+      "loss": 1.0818,
+      "step": 21
+    },
+    {
+      "epoch": 0.04066543438077634,
+      "grad_norm": 6.201707363128662,
+      "learning_rate": 0.0001997041811497882,
+      "loss": 1.361,
+      "step": 22
+    },
+    {
+      "epoch": 0.04251386321626617,
+      "grad_norm": 3.2470476627349854,
+      "learning_rate": 0.00019965285344390184,
+      "loss": 1.5608,
+      "step": 23
+    },
+    {
+      "epoch": 0.04436229205175601,
+      "grad_norm": 3.960193157196045,
+      "learning_rate": 0.00019959742939952392,
+      "loss": 1.2768,
+      "step": 24
+    },
+    {
+      "epoch": 0.04621072088724584,
+      "grad_norm": 4.521762371063232,
+      "learning_rate": 0.00019953791129491983,
+      "loss": 1.6174,
+      "step": 25
+    },
+    {
+      "epoch": 0.04621072088724584,
+      "eval_loss": 0.3227802515029907,
+      "eval_runtime": 174.8819,
+      "eval_samples_per_second": 1.304,
+      "eval_steps_per_second": 0.652,
+      "step": 25
+    },
+    {
+      "epoch": 0.04805914972273567,
+      "grad_norm": 5.535987377166748,
+      "learning_rate": 0.00019947430157664576,
+      "loss": 1.5342,
+      "step": 26
+    },
+    {
+      "epoch": 0.04990757855822551,
+      "grad_norm": 3.174276113510132,
+      "learning_rate": 0.00019940660285944803,
+      "loss": 1.3247,
+      "step": 27
+    },
+    {
+      "epoch": 0.051756007393715345,
+      "grad_norm": 2.9018266201019287,
+      "learning_rate": 0.00019933481792615583,
+      "loss": 1.0521,
+      "step": 28
+    },
+    {
+      "epoch": 0.053604436229205174,
+      "grad_norm": 4.290431022644043,
+      "learning_rate": 0.0001992589497275665,
+      "loss": 1.2776,
+      "step": 29
+    },
+    {
+      "epoch": 0.05545286506469501,
+      "grad_norm": 3.15394926071167,
+      "learning_rate": 0.0001991790013823246,
+      "loss": 1.2662,
+      "step": 30
+    },
+    {
+      "epoch": 0.05545286506469501,
+      "eval_loss": 0.3060170114040375,
+      "eval_runtime": 173.945,
+      "eval_samples_per_second": 1.311,
+      "eval_steps_per_second": 0.655,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -215,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.829013890367488e+16,
+  "total_flos": 4.243520835551232e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null