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:ddbba15e81bfcf58052a41c18cd6b1b2dbb08d73044f26b95792512840987690
+oid sha256:a5eec99b848420f2625278c2e702443cc469264c360628802904f72514b80fee
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f90a8cde59d78d2d75b14df8a80e63fcfbf097b2ef768f2c0b07472d039cae4f
+oid sha256:a14a0f40e6d489891a2151063b4fafb169b09a68449a2ae085dbe7918a6a428f
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:933e7a10d39a8bc7b41a4d7891c460551af07930f25cbc6e9459a8df7bea5f1c
+oid sha256:2dca50c955c130474d70ac86b3de8b620beaf61893f79f17cf1f17fa18312d7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2575994729995728,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00033972728392283095,
+  "best_metric": 1.2234210968017578,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0005095909258842464,
   "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": 6.457,
       "eval_steps_per_second": 3.228,
       "step": 20
+    },
+    {
+      "epoch": 0.0003567136481189725,
+      "grad_norm": 2.105696439743042,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 4.4662,
+      "step": 21
+    },
+    {
+      "epoch": 0.00040767274070739715,
+      "grad_norm": 5.003188610076904,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 5.2284,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004246591049035387,
+      "eval_loss": 1.2291550636291504,
+      "eval_runtime": 3835.1312,
+      "eval_samples_per_second": 6.463,
+      "eval_steps_per_second": 3.232,
+      "step": 25
+    },
+    {
+      "epoch": 0.00045863183329582176,
+      "grad_norm": 2.9324259757995605,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 5.1058,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005095909258842464,
+      "grad_norm": 2.1682016849517822,
+      "learning_rate": 0.0,
+      "loss": 4.3811,
+      "step": 30
+    },
+    {
+      "epoch": 0.0005095909258842464,
+      "eval_loss": 1.2234210968017578,
+      "eval_runtime": 3832.4715,
+      "eval_samples_per_second": 6.468,
+      "eval_steps_per_second": 3.234,
+      "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": 6698012604628992.0,
+  "total_flos": 1.0128701987487744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null