Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b600c5905b99719178da324d8292eaa79fc98af69d8b538212109b050fd2de
+oid sha256:01642f1dfb7ae5aa993b79b6aba70f4045cf8775c30a17a13dae051558f1731d
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a32a0447bc215a538035c70dd7032eb360e7c097e3b44562408bb9f6826b092
+oid sha256:6b6bcc1ff1a7839bb02cc1d84f8caf45a3b3ed7e8e7f9be4a79b76ee560b58e6
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22c52c644f110c29d949d37a0dd6a9326820b814d0f54170e7b704e3d714e675
+oid sha256:67a843c5ebc96a4a5ea03c3b6dd16e6db290e47203eba35defda266ee83d12fb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9027982950210571,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00048107568523217913,
+  "best_metric": 1.7774372100830078,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0007216135278482687,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 15.66,
       "eval_steps_per_second": 3.915,
       "step": 20
+    },
+    {
+      "epoch": 0.0005051294694937881,
+      "grad_norm": 5.871511459350586,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.5545,
+      "step": 21
+    },
+    {
+      "epoch": 0.0005772908222786149,
+      "grad_norm": 5.881715774536133,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 6.5465,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006013446065402239,
+      "eval_loss": 1.795774221420288,
+      "eval_runtime": 2235.8074,
+      "eval_samples_per_second": 15.659,
+      "eval_steps_per_second": 3.915,
+      "step": 25
+    },
+    {
+      "epoch": 0.0006494521750634418,
+      "grad_norm": 11.0554780960083,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 6.722,
+      "step": 27
+    },
+    {
+      "epoch": 0.0007216135278482687,
+      "grad_norm": 13.766908645629883,
+      "learning_rate": 0.0,
+      "loss": 6.8375,
+      "step": 30
+    },
+    {
+      "epoch": 0.0007216135278482687,
+      "eval_loss": 1.7774372100830078,
+      "eval_runtime": 2235.4123,
+      "eval_samples_per_second": 15.662,
+      "eval_steps_per_second": 3.916,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.306929288708096e+16,
+  "total_flos": 1.960393933062144e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null