Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47f97b0a4bccaac33a9f2c5571584aebb19ed33ab12804e1b4c1ef7146438e4
+oid sha256:3beec5d8eadb9b3e8e4a8abbe2dc0d1b2e7ad7e38f527be3453ccf3482921e01
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa985bc0950ea375a377d917150c774b8ea48a331a2fb363118bd82041c4dd6
+oid sha256:957b9c9a982908bf9ac2dca2c63af2c0f6b1d1fae656da1b7d43ec9d4f776c89
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc058781cdbb2911c0a08aca3723ec2615b2ee617650513f58264c641fbb821
+oid sha256:aac016cd33d97d492e9a407a37dde267d3258c34e30e14d6c375b0dd17c5d563
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7277498245239258,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012175818823815902,
+  "best_metric": 0.7138856053352356,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.024351637647631805,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 66.637,
       "eval_steps_per_second": 8.342,
       "step": 25
+    },
+    {
+      "epoch": 0.012662851576768538,
+      "grad_norm": 0.6293425559997559,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.8072,
+      "step": 26
+    },
+    {
+      "epoch": 0.013149884329721175,
+      "grad_norm": 0.6541574597358704,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.7148,
+      "step": 27
+    },
+    {
+      "epoch": 0.01363691708267381,
+      "grad_norm": 0.699476957321167,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.7722,
+      "step": 28
+    },
+    {
+      "epoch": 0.014123949835626447,
+      "grad_norm": 0.6306124925613403,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.7482,
+      "step": 29
+    },
+    {
+      "epoch": 0.014610982588579081,
+      "grad_norm": 0.6237121224403381,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.6539,
+      "step": 30
+    },
+    {
+      "epoch": 0.015098015341531717,
+      "grad_norm": 0.712128758430481,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.6752,
+      "step": 31
+    },
+    {
+      "epoch": 0.015585048094484353,
+      "grad_norm": 0.6385212540626526,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6965,
+      "step": 32
+    },
+    {
+      "epoch": 0.01607208084743699,
+      "grad_norm": 0.6857041120529175,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.7628,
+      "step": 33
+    },
+    {
+      "epoch": 0.016559113600389627,
+      "grad_norm": 0.6993204951286316,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.7362,
+      "step": 34
+    },
+    {
+      "epoch": 0.017046146353342263,
+      "grad_norm": 0.7859645485877991,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8235,
+      "step": 35
+    },
+    {
+      "epoch": 0.0175331791062949,
+      "grad_norm": 0.6398217082023621,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.6597,
+      "step": 36
+    },
+    {
+      "epoch": 0.018020211859247535,
+      "grad_norm": 0.7026098966598511,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.6772,
+      "step": 37
+    },
+    {
+      "epoch": 0.01850724461220017,
+      "grad_norm": 0.7147570848464966,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.747,
+      "step": 38
+    },
+    {
+      "epoch": 0.018994277365152808,
+      "grad_norm": 0.7010482549667358,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.6467,
+      "step": 39
+    },
+    {
+      "epoch": 0.019481310118105444,
+      "grad_norm": 0.6586910486221313,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.7252,
+      "step": 40
+    },
+    {
+      "epoch": 0.01996834287105808,
+      "grad_norm": 0.673101007938385,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6697,
+      "step": 41
+    },
+    {
+      "epoch": 0.020455375624010716,
+      "grad_norm": 0.7123458981513977,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6856,
+      "step": 42
+    },
+    {
+      "epoch": 0.020942408376963352,
+      "grad_norm": 0.7723951935768127,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6852,
+      "step": 43
+    },
+    {
+      "epoch": 0.021429441129915988,
+      "grad_norm": 0.7186630368232727,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.6545,
+      "step": 44
+    },
+    {
+      "epoch": 0.021916473882868624,
+      "grad_norm": 0.7315675616264343,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.71,
+      "step": 45
+    },
+    {
+      "epoch": 0.02240350663582126,
+      "grad_norm": 0.7585425972938538,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.6676,
+      "step": 46
+    },
+    {
+      "epoch": 0.022890539388773896,
+      "grad_norm": 0.7263960242271423,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6473,
+      "step": 47
+    },
+    {
+      "epoch": 0.023377572141726533,
+      "grad_norm": 0.7787749171257019,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.6453,
+      "step": 48
+    },
+    {
+      "epoch": 0.02386460489467917,
+      "grad_norm": 0.8783103227615356,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7039,
+      "step": 49
+    },
+    {
+      "epoch": 0.024351637647631805,
+      "grad_norm": 0.9412726759910583,
+      "learning_rate": 0.0,
+      "loss": 0.5764,
+      "step": 50
+    },
+    {
+      "epoch": 0.024351637647631805,
+      "eval_loss": 0.7138856053352356,
+      "eval_runtime": 51.8403,
+      "eval_samples_per_second": 66.724,
+      "eval_steps_per_second": 8.353,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1932120607948800.0,
+  "total_flos": 3603404933824512.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null