Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e1a8ae74b334063a9d3997acf056086795a5faa1fa541d3fb2d95d0a3493353
+oid sha256:9e9ef98b0b8a405b78cf7932e4e5e18613d6ed7174297640f84857b2eb1a28d4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de969705c1310ad8760b566ff6a28ddeb17edc1736b29f861fd923375ecd2bb
+oid sha256:92b4f5761a7d669df030236b3a1322fcb81a9d1f661dd048e22e3469a4e35bdc
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0ea1d7368eae0b0f78f4a05544b7405546d8f47c146e006faf2f056e23d37c
+oid sha256:1e9f1f33c806b45b9414ac45b69970fd50ad8f4e6fedf1de277a6cfa462b86dc
 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": 1.8154946565628052,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0011156667503416729,
+  "best_metric": 1.7814539670944214,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0016735001255125093,
   "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": 7.832,
       "eval_steps_per_second": 1.958,
       "step": 20
+    },
+    {
+      "epoch": 0.0011714500878587566,
+      "grad_norm": 0.5717261433601379,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.7195,
+      "step": 21
+    },
+    {
+      "epoch": 0.0013388001004100076,
+      "grad_norm": 0.6992154121398926,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.8193,
+      "step": 24
+    },
+    {
+      "epoch": 0.001394583437927091,
+      "eval_loss": 1.7873667478561401,
+      "eval_runtime": 1926.2101,
+      "eval_samples_per_second": 7.838,
+      "eval_steps_per_second": 1.96,
+      "step": 25
+    },
+    {
+      "epoch": 0.0015061501129612586,
+      "grad_norm": 0.6408898234367371,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.7178,
+      "step": 27
+    },
+    {
+      "epoch": 0.0016735001255125093,
+      "grad_norm": 0.7179284691810608,
+      "learning_rate": 0.0,
+      "loss": 1.8085,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016735001255125093,
+      "eval_loss": 1.7814539670944214,
+      "eval_runtime": 1926.588,
+      "eval_samples_per_second": 7.836,
+      "eval_steps_per_second": 1.959,
+      "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": 1.576510477565952e+16,
+  "total_flos": 2.3183977611264e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null