Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f26ecd45384b5f0b75f17b142655c339256349c66e81d8c41ba7d471e051efd
+oid sha256:50690a2067b4f55a831c80a8ad7c9de7ba41b6c776ffc6d61bac820a920e5285
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c858b42f4928dbfacf66589b7604c0c0cd93f9ca0b3263cb0c345c663f7aa2
+oid sha256:467c0128ef2b86c413edd23056f0056fc2d4eaa8225bda002855354f474359b2
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f589cdc8adb695a9a26b669b4afed6a0acea4337ae464f7c4c015c70e1182a
+oid sha256:b34ffde75a9f5669e1c8a7e881b3110da5a1be84070f76d80f348434ba729ecf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f18fffb0e3a0ef336b47179743ab4126e50cd1f6b973081299b4ddb7dd17108
+oid sha256:b880929b96bf75acbc85f47d876c46d359fd62d1478ce33a372b0c060023cc3a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e3feeaf0cb2e18e2a639e1a4dbc0e4904c0909b9ea1c45912f8b1713d0de1d
+oid sha256:b0e4249ff6a680977c90ce618286998e69c58663c049a77e0ba9a6d23c96107e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:898278affd6a9a4756a8d9bbe28e167dd71767815151ca235e3ea1cda09fa12a
+oid sha256:a2feaab34299e5d4c191dee1d96d761a6aeb502db66d24b986c68043182cfcbd
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af915b3bd1f4e2109b462a6794b6020da77edbf1d90b3213a0a05f6b1d4f617
+oid sha256:9a2759c51def6f12ecf076b0cf2571dc6049a636d579f7f0a8bd8ae37daff96c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.8585520386695862,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.9047619047619047,
+  "epoch": 3.0476190476190474,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,111 @@
       "eval_samples_per_second": 46.988,
       "eval_steps_per_second": 6.335,
       "step": 25
+    },
+    {
+      "epoch": 1.980952380952381,
+      "grad_norm": 0.9605194330215454,
+      "learning_rate": 2.991522876735154e-05,
+      "loss": 0.887,
+      "step": 26
+    },
+    {
+      "epoch": 2.057142857142857,
+      "grad_norm": 2.160217523574829,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 1.6403,
+      "step": 27
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.0214014053344727,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.9062,
+      "step": 28
+    },
+    {
+      "epoch": 2.2095238095238097,
+      "grad_norm": 1.190313458442688,
+      "learning_rate": 1.928936436551661e-05,
+      "loss": 0.853,
+      "step": 29
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 1.1187245845794678,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 0.8842,
+      "step": 30
+    },
+    {
+      "epoch": 2.361904761904762,
+      "grad_norm": 0.9486127495765686,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 0.8989,
+      "step": 31
+    },
+    {
+      "epoch": 2.4380952380952383,
+      "grad_norm": 1.1477197408676147,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 0.8428,
+      "step": 32
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 0.8318337798118591,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.8689,
+      "step": 33
+    },
+    {
+      "epoch": 2.5904761904761906,
+      "grad_norm": 0.9033652544021606,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 0.8886,
+      "step": 34
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 1.3068876266479492,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 0.8713,
+      "step": 35
+    },
+    {
+      "epoch": 2.742857142857143,
+      "grad_norm": 1.5723620653152466,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.8887,
+      "step": 36
+    },
+    {
+      "epoch": 2.819047619047619,
+      "grad_norm": 0.7510371804237366,
+      "learning_rate": 1.5299867030334814e-06,
+      "loss": 0.8693,
+      "step": 37
+    },
+    {
+      "epoch": 2.895238095238095,
+      "grad_norm": 0.9378589987754822,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 0.8705,
+      "step": 38
+    },
+    {
+      "epoch": 2.9714285714285715,
+      "grad_norm": 1.0388190746307373,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.8689,
+      "step": 39
+    },
+    {
+      "epoch": 3.0476190476190474,
+      "grad_norm": 2.3041744232177734,
+      "learning_rate": 0.0,
+      "loss": 1.5959,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -221,12 +326,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.83042868150272e+16,
+  "total_flos": 1.2528685890404352e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null