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:e68de28d7bd65af07a17e58c640ec266720dc3e9f4f62ce178c38c1c1aff958e
+oid sha256:497dec360c02c24caa11259e602b44d8fd517df47c34d9a4e6b48d632bf929b4
 size 56662456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae6f186abc304db2729df25a07541ab547bdc00cbf4b25d96e1a39ebd3bd6d05
+oid sha256:c260ce5a28ab95808dfefed75384a3c8d70b71e247bda3ce1c54048fcffd8f67
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62ad4ace684592e178a4b88aa8a82edcbbe0ff3fe21fc4f6323cdfe3572fa2ed
+oid sha256:5dd5b78c04d24b8a631cb2ffc7107e81c81c1dfcf1b3ab3a0263e9887443af4d
 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": 0.7681506276130676,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.33195020746887965,
+  "best_metric": 0.7523407340049744,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.4979253112033195,
   "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": 34.508,
       "eval_steps_per_second": 8.796,
       "step": 20
+    },
+    {
+      "epoch": 0.34854771784232363,
+      "grad_norm": 0.6307705640792847,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.9407,
+      "step": 21
+    },
+    {
+      "epoch": 0.3983402489626556,
+      "grad_norm": 0.712988018989563,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.9777,
+      "step": 24
+    },
+    {
+      "epoch": 0.4149377593360996,
+      "eval_loss": 0.7552775144577026,
+      "eval_runtime": 1.4738,
+      "eval_samples_per_second": 34.605,
+      "eval_steps_per_second": 8.821,
+      "step": 25
+    },
+    {
+      "epoch": 0.44813278008298757,
+      "grad_norm": 0.851246178150177,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.1521,
+      "step": 27
+    },
+    {
+      "epoch": 0.4979253112033195,
+      "grad_norm": 1.9206782579421997,
+      "learning_rate": 0.0,
+      "loss": 3.5759,
+      "step": 30
+    },
+    {
+      "epoch": 0.4979253112033195,
+      "eval_loss": 0.7523407340049744,
+      "eval_runtime": 1.4728,
+      "eval_samples_per_second": 34.629,
+      "eval_steps_per_second": 8.827,
+      "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": 2463844697899008.0,
+  "total_flos": 3665720160288768.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null