Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62ad2e326f185bde1e271307dc3b02f0e312c11f641168d881f4b69f4deb1627
+oid sha256:850d53b5b33adb1f1f366b5fcaea01f66017aff8c86e1e04e6923003d6c47106
 size 800116456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca1976255df581499346e7ce6a155ffa0f88edc2f9dccbd14dc6d2e9add27e80
+oid sha256:53129f540a8c2c9bb8061bfcbd7b289ea434c05b6076a81497b1d4d49bec822f
 size 406743412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c85d9288c51eaa7d2c1111e01e6d9ee843f460e8a388a3fd01a7ff38de7a191
+oid sha256:83d93fed6efecf1ebac1b8d0693a14b59f022796240821fda02be65ed6b0b803
 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": 1.4723252058029175,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03346720214190094,
+  "best_metric": 1.4047613143920898,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06693440428380187,
   "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": 17.394,
       "eval_steps_per_second": 2.185,
       "step": 25
+    },
+    {
+      "epoch": 0.03480589022757698,
+      "grad_norm": 1.174262523651123,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.03614457831325301,
+      "grad_norm": 1.49019193649292,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.1347,
+      "step": 27
+    },
+    {
+      "epoch": 0.03748326639892905,
+      "grad_norm": 1.8323603868484497,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.2095,
+      "step": 28
+    },
+    {
+      "epoch": 0.038821954484605084,
+      "grad_norm": 2.324418306350708,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4622,
+      "step": 29
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 2.313349962234497,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.663,
+      "step": 30
+    },
+    {
+      "epoch": 0.041499330655957165,
+      "grad_norm": 2.2213706970214844,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.3558,
+      "step": 31
+    },
+    {
+      "epoch": 0.0428380187416332,
+      "grad_norm": 2.226473093032837,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3718,
+      "step": 32
+    },
+    {
+      "epoch": 0.04417670682730924,
+      "grad_norm": 2.0623409748077393,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.4869,
+      "step": 33
+    },
+    {
+      "epoch": 0.04551539491298527,
+      "grad_norm": 2.212683916091919,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.5165,
+      "step": 34
+    },
+    {
+      "epoch": 0.04685408299866131,
+      "grad_norm": 2.247880220413208,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.497,
+      "step": 35
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 2.2593677043914795,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.5639,
+      "step": 36
+    },
+    {
+      "epoch": 0.049531459170013385,
+      "grad_norm": 2.508176803588867,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.6135,
+      "step": 37
+    },
+    {
+      "epoch": 0.050870147255689425,
+      "grad_norm": 2.3610587120056152,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.6932,
+      "step": 38
+    },
+    {
+      "epoch": 0.05220883534136546,
+      "grad_norm": 2.883047580718994,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.5647,
+      "step": 39
+    },
+    {
+      "epoch": 0.0535475234270415,
+      "grad_norm": 2.6520442962646484,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.711,
+      "step": 40
+    },
+    {
+      "epoch": 0.05488621151271754,
+      "grad_norm": 2.7636210918426514,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6489,
+      "step": 41
+    },
+    {
+      "epoch": 0.05622489959839357,
+      "grad_norm": 3.3009133338928223,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.8286,
+      "step": 42
+    },
+    {
+      "epoch": 0.05756358768406961,
+      "grad_norm": 4.271368503570557,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.0081,
+      "step": 43
+    },
+    {
+      "epoch": 0.058902275769745646,
+      "grad_norm": 5.240908622741699,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.1059,
+      "step": 44
+    },
+    {
+      "epoch": 0.060240963855421686,
+      "grad_norm": 8.063950538635254,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.7622,
+      "step": 45
+    },
+    {
+      "epoch": 0.06157965194109773,
+      "grad_norm": 8.115025520324707,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.3904,
+      "step": 46
+    },
+    {
+      "epoch": 0.06291834002677377,
+      "grad_norm": 9.404306411743164,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0908,
+      "step": 47
+    },
+    {
+      "epoch": 0.0642570281124498,
+      "grad_norm": 9.610150337219238,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.4451,
+      "step": 48
+    },
+    {
+      "epoch": 0.06559571619812583,
+      "grad_norm": 10.734207153320312,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.7998,
+      "step": 49
+    },
+    {
+      "epoch": 0.06693440428380187,
+      "grad_norm": 20.90941047668457,
+      "learning_rate": 0.0,
+      "loss": 3.1422,
+      "step": 50
+    },
+    {
+      "epoch": 0.06693440428380187,
+      "eval_loss": 1.4047613143920898,
+      "eval_runtime": 72.0554,
+      "eval_samples_per_second": 17.459,
+      "eval_steps_per_second": 2.193,
+      "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": 3.0679414421323776e+16,
+  "total_flos": 5.022044271516058e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null