Training in progress, step 12, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a7e48288fb7e98130effc09a443086aeda45a1543b20413a9a14e8463e2a6b
+oid sha256:a71600f62dd80c2cb2771c778f9fcc7687fd433d5acd8919c1667b806cf333e1
 size 828526568

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a5e2465a21776f6b11aaad5ae5e73e5299188394a8b13ec35feaf5b3e9e22e7
+oid sha256:1b82159ba1842f5020191443502e307172d245b5bf63a145c25271448111e3ec
 size 1657755122

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d567a1ce8013f3d1353502f65107776932e5bf44bc8ca8d1700e44afd824f4
+oid sha256:398dc8fa67b696a75dd1b612994af1eb7c36a2bab5fa2451729db67847b86e09
 size 828793718

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c721dc9e7a128695aa757659b455b66eed608e12fb70ec3e7da6ee4fe17684
+oid sha256:665f0ba302167a9bd53533aaddc229d42076af770231d3d86051da7e37633fd6
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f79d01ac59109f9fb23deb4e3fb4d5a3ceb1f25a06de4a1189f362027e8b273
+oid sha256:4f4bf140f1750c409018fa2d22904d6214c4bbb78a9a8f54c136f62b8c60edb7
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f82b0d1cefd4f4436ae808681102171b3999df3c7fc173bd2452a3218ed3ea3a
+oid sha256:913fc19bf2ad8265632a721056db64133a2c28d72c90664e19bbea762ef652b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 9,
-  "best_metric": 0.2719385325908661,
-  "best_model_checkpoint": "miner_id_24/checkpoint-9",
-  "epoch": 0.032454361054766734,
+  "best_global_step": 12,
+  "best_metric": 0.25252172350883484,
+  "best_model_checkpoint": "miner_id_24/checkpoint-12",
+  "epoch": 0.043272481406355645,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,35 @@
       "eval_samples_per_second": 6.301,
       "eval_steps_per_second": 0.789,
       "step": 9
+    },
+    {
+      "epoch": 0.03606040117196304,
+      "grad_norm": 0.1475931704044342,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.2489,
+      "step": 10
+    },
+    {
+      "epoch": 0.03966644128915934,
+      "grad_norm": 0.2981042265892029,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.2705,
+      "step": 11
+    },
+    {
+      "epoch": 0.043272481406355645,
+      "grad_norm": 0.18590322136878967,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.282,
+      "step": 12
+    },
+    {
+      "epoch": 0.043272481406355645,
+      "eval_loss": 0.25252172350883484,
+      "eval_runtime": 297.3539,
+      "eval_samples_per_second": 6.282,
+      "eval_steps_per_second": 0.787,
+      "step": 12
     }
   ],
   "logging_steps": 1,
@@ -126,12 +155,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.2563477975046554e+17,
+  "total_flos": 2.762101349322588e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null