Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45f8c4bc1f37da4289a38763e7e2d6611782b9c7bec62efe7626b1c2a0837d45
+oid sha256:cd90e9e29133934e00d97b10690111e1ab031a06c3bd7360878cc1bde347518f
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a77d3705790d1d5c062eb5df83ec5414e8f50a5146ca961b44427bb13f0038a
+oid sha256:971ab3330e8ffedad7c0d7ef02a763bd89a35f4231f6d7b46a5640c3e6b56e4c
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad79bde13cc0e75f70807143e7038291157eb5d840dc9f9aafd9691fdc9ddea
+oid sha256:78d6800c3cd765d1c4116dc8282730fc0f9dccafb29d8eeeeacf30169488da38
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:852b7a078606e27651eef4cbeb9f93838030f7048a305402ab3efe259ff71e65
+oid sha256:949848d7467650eca7a218f3c334e982f3ff5b97aaad6e52e7601fbbd68bcc11
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff8eaddde3bb51320c88643e1b9517fea1b3b486231315704814e8c0f48d041
+oid sha256:5300c2d21f90d1cd8ee461f0c8d83f345e4a04f42115016cab53e2a2d40b3144
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e88b0364f928c2a2e3d4be19d3dd708f6f3450df8f53c1ed490200ba548842
+oid sha256:028e86573a2e7014388c5005aa1b24e336f4bbb2590213c7ad851d968ce4b47d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8b460eb34577dc31e89c5d46049a264caffc8e9f90e68fb640444126fba5f4
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4157150089740753,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.6666666666666665,
+  "epoch": 3.2452830188679247,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,41 @@
       "eval_samples_per_second": 108.176,
       "eval_steps_per_second": 14.531,
       "step": 25
+    },
+    {
+      "epoch": 2.767295597484277,
+      "grad_norm": 0.43570584058761597,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 0.4734,
+      "step": 26
+    },
+    {
+      "epoch": 2.867924528301887,
+      "grad_norm": 0.547036349773407,
+      "learning_rate": 2.8058334845816213e-06,
+      "loss": 0.4908,
+      "step": 27
+    },
+    {
+      "epoch": 3.0440251572327046,
+      "grad_norm": 0.7520437240600586,
+      "learning_rate": 1.2536043909088191e-06,
+      "loss": 0.7204,
+      "step": 28
+    },
+    {
+      "epoch": 3.1446540880503147,
+      "grad_norm": 0.4165114760398865,
+      "learning_rate": 3.143895053378698e-07,
+      "loss": 0.4098,
+      "step": 29
+    },
+    {
+      "epoch": 3.2452830188679247,
+      "grad_norm": 0.3665567934513092,
+      "learning_rate": 0.0,
+      "loss": 0.3763,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +256,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.16708196040704e+16,
+  "total_flos": 5.000498352488448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null