Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72025eee6c8df79570a58f6dfb4738763a40398724aaf8c956bbea01f3d19d9b
+oid sha256:4a13c38a5e8a10c453232fb808b95d43116441c99f250f8c100fda576959b9d2
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b7903ceb63f7319d7743707770b8458bbb24c5490fbd6cb08d05c524c733f2d
+oid sha256:28aca89fee032ac1494bc318106ecc362c633271aea450c760905896b0149b4e
 size 136814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f7e85ec0c7cf94e6539c614b2cdae35e592e6008d0e889a34268e7ffb5ad26
+oid sha256:593090ac6ddb613a0b67633813c2dfd6652e5eceb859bc48ecee91149eae4ce7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf4d0d730ccc9e2c8ddc5f19d724b476847a4fd05d50494d967b231b2616759
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.035011291503906,
-  "best_model_checkpoint": "miner_id_24/checkpoint-40",
-  "epoch": 0.00134432317529134,
+  "best_metric": 11.03365707397461,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.001680403969114175,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,92 @@
       "eval_samples_per_second": 114.773,
       "eval_steps_per_second": 28.697,
       "step": 40
+    },
+    {
+      "epoch": 0.0013779312546736235,
+      "grad_norm": 1.4056628942489624,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 44.1327,
+      "step": 41
+    },
+    {
+      "epoch": 0.0014115393340559071,
+      "grad_norm": 1.4018856287002563,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 44.1258,
+      "step": 42
+    },
+    {
+      "epoch": 0.0014451474134381905,
+      "grad_norm": 1.462540864944458,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 44.1366,
+      "step": 43
+    },
+    {
+      "epoch": 0.001478755492820474,
+      "grad_norm": 1.461982011795044,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 44.1334,
+      "step": 44
+    },
+    {
+      "epoch": 0.0015123635722027575,
+      "grad_norm": 1.422272801399231,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 44.1435,
+      "step": 45
+    },
+    {
+      "epoch": 0.0015123635722027575,
+      "eval_loss": 11.033855438232422,
+      "eval_runtime": 217.7428,
+      "eval_samples_per_second": 115.076,
+      "eval_steps_per_second": 28.772,
+      "step": 45
+    },
+    {
+      "epoch": 0.001545971651585041,
+      "grad_norm": 1.3762067556381226,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 44.1391,
+      "step": 46
+    },
+    {
+      "epoch": 0.0015795797309673244,
+      "grad_norm": 1.4046872854232788,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 44.1509,
+      "step": 47
+    },
+    {
+      "epoch": 0.001613187810349608,
+      "grad_norm": 1.41513192653656,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 44.1355,
+      "step": 48
+    },
+    {
+      "epoch": 0.0016467958897318916,
+      "grad_norm": 1.422555923461914,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 44.121,
+      "step": 49
+    },
+    {
+      "epoch": 0.001680403969114175,
+      "grad_norm": 1.4306371212005615,
+      "learning_rate": 0.0,
+      "loss": 44.1407,
+      "step": 50
+    },
+    {
+      "epoch": 0.001680403969114175,
+      "eval_loss": 11.03365707397461,
+      "eval_runtime": 218.4711,
+      "eval_samples_per_second": 114.693,
+      "eval_steps_per_second": 28.677,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -382,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 299473305600.0,
+  "total_flos": 374341632000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null