Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3440c86b8b88cc2da5a2e39e27a46b84d667a99c438c256f77d8a0f7875ef23f
+oid sha256:e8ec9a5609b0c67fcad014abed5c4396b7f4c247145e83cdfaf1ec97b34ee0fe
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a25fff4450dd8b61ff947bafb3cff0998b05ff9798895f247c6776ab2fc3889
+oid sha256:1c5b127ddd2d90fe9486b5a8effdeceda0881cd3ae0e8abb2c27bb9cbfeef168
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3863cb9fe532bc088238dc1cb8b728c9cabe47e45da05252cff3a64c0873df03
+oid sha256:43b0deb5b7c3c84f6dd5341a2dfc455a7d3484e5a5e8cabd1ec98720c5fc6d34
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1148810386657715,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0014216914574114554,
+  "best_metric": 1.0782692432403564,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0021325371861171828,
   "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": 3.22,
       "eval_steps_per_second": 1.61,
       "step": 20
+    },
+    {
+      "epoch": 0.001492776030282028,
+      "grad_norm": 2.7787132263183594,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 4.6107,
+      "step": 21
+    },
+    {
+      "epoch": 0.0017060297488937462,
+      "grad_norm": 3.437938690185547,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 4.4289,
+      "step": 24
+    },
+    {
+      "epoch": 0.0017771143217643192,
+      "eval_loss": 1.0836812257766724,
+      "eval_runtime": 1842.4959,
+      "eval_samples_per_second": 3.215,
+      "eval_steps_per_second": 1.608,
+      "step": 25
+    },
+    {
+      "epoch": 0.0019192834675054646,
+      "grad_norm": 2.346892833709717,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 4.3868,
+      "step": 27
+    },
+    {
+      "epoch": 0.0021325371861171828,
+      "grad_norm": 2.5171074867248535,
+      "learning_rate": 0.0,
+      "loss": 4.3477,
+      "step": 30
+    },
+    {
+      "epoch": 0.0021325371861171828,
+      "eval_loss": 1.0782692432403564,
+      "eval_runtime": 1839.9719,
+      "eval_samples_per_second": 3.22,
+      "eval_steps_per_second": 1.61,
+      "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": 1.2695579394048e+16,
+  "total_flos": 1.9043369091072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null