Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a718becf150ec18fb753e7f0eaf721bf416d1cd1dae9d87cace4493c65f37c0
+oid sha256:9c95e12e1f062f53bb859bf713b816a8cfe0e67c1171981c22d3141fc45b1472
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9469ab6934b38e545678248fee878a149a8fabb5d21a3928a0c16ae4f90e9309
+oid sha256:7306246f3390b91c747fe0a4a202bce24027bbed9ec4749536ff676e89f76545
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c95650e5a35b97e0c1024a8f3aed9e4823cfe6226ef4c4879b27170a1fc51abf
+oid sha256:89a9c0d7971264778ce022a3ce58343389d51c5b89a574ed01b9aacc6e91714d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19076b64865d508a23445ecf51025026e2e6caa48d059ffc4aec9ef53d08c265
+oid sha256:a96a58659a7570ad0e6afce77838879dbeab7bfe610c30cd997657f4edf2a997
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ffad26c99d0f56b3be3ea0cf29832a929a1a2f867422892fbc521f69a2aa0bb
+oid sha256:e2bf3cf68a7e0249e81898135541af69f48c4b6a49c6cf7b5124c7c99eefd30b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:740caf7da7314562958c69a45f970e8ecbec1e0f12a005cc361a5e4157b0e6d5
+oid sha256:34c52b30ff889a22911bed8731f03ede0153d7902c13f05e4c86c3337fd7351b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5735299587249756,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5571030640668524,
+  "best_metric": 0.5250022411346436,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1142061281337048,
   "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": 36.564,
       "eval_steps_per_second": 4.586,
       "step": 25
+    },
+    {
+      "epoch": 0.5793871866295265,
+      "grad_norm": 6.091929912567139,
+      "learning_rate": 5e-05,
+      "loss": 0.5637,
+      "step": 26
+    },
+    {
+      "epoch": 0.6016713091922006,
+      "grad_norm": 1.8379416465759277,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5558,
+      "step": 27
+    },
+    {
+      "epoch": 0.6239554317548747,
+      "grad_norm": 1.373220682144165,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5139,
+      "step": 28
+    },
+    {
+      "epoch": 0.6462395543175488,
+      "grad_norm": 3.242717742919922,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5975,
+      "step": 29
+    },
+    {
+      "epoch": 0.6685236768802229,
+      "grad_norm": 1.5490792989730835,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5589,
+      "step": 30
+    },
+    {
+      "epoch": 0.6908077994428969,
+      "grad_norm": 1.0958337783813477,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5849,
+      "step": 31
+    },
+    {
+      "epoch": 0.713091922005571,
+      "grad_norm": 1.335720181465149,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5244,
+      "step": 32
+    },
+    {
+      "epoch": 0.7353760445682451,
+      "grad_norm": 1.8901203870773315,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4989,
+      "step": 33
+    },
+    {
+      "epoch": 0.7576601671309192,
+      "grad_norm": 1.3303558826446533,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5267,
+      "step": 34
+    },
+    {
+      "epoch": 0.7799442896935933,
+      "grad_norm": 0.8487653136253357,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4921,
+      "step": 35
+    },
+    {
+      "epoch": 0.8022284122562674,
+      "grad_norm": 1.4701528549194336,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4972,
+      "step": 36
+    },
+    {
+      "epoch": 0.8245125348189415,
+      "grad_norm": 3.763484001159668,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5617,
+      "step": 37
+    },
+    {
+      "epoch": 0.8467966573816156,
+      "grad_norm": 3.6227574348449707,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5396,
+      "step": 38
+    },
+    {
+      "epoch": 0.8690807799442897,
+      "grad_norm": 0.6843830943107605,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5328,
+      "step": 39
+    },
+    {
+      "epoch": 0.8913649025069638,
+      "grad_norm": 2.871105432510376,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5647,
+      "step": 40
+    },
+    {
+      "epoch": 0.9136490250696379,
+      "grad_norm": 1.7284497022628784,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5141,
+      "step": 41
+    },
+    {
+      "epoch": 0.935933147632312,
+      "grad_norm": 2.233738422393799,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5297,
+      "step": 42
+    },
+    {
+      "epoch": 0.958217270194986,
+      "grad_norm": 0.8520792722702026,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5582,
+      "step": 43
+    },
+    {
+      "epoch": 0.9805013927576601,
+      "grad_norm": 2.821225881576538,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5086,
+      "step": 44
+    },
+    {
+      "epoch": 1.0027855153203342,
+      "grad_norm": 3.3593173027038574,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6117,
+      "step": 45
+    },
+    {
+      "epoch": 1.0250696378830084,
+      "grad_norm": 1.817628026008606,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5412,
+      "step": 46
+    },
+    {
+      "epoch": 1.0473537604456824,
+      "grad_norm": 1.0740711688995361,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5352,
+      "step": 47
+    },
+    {
+      "epoch": 1.0696378830083566,
+      "grad_norm": 4.573311805725098,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5294,
+      "step": 48
+    },
+    {
+      "epoch": 1.0919220055710306,
+      "grad_norm": 2.1602420806884766,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4741,
+      "step": 49
+    },
+    {
+      "epoch": 1.1142061281337048,
+      "grad_norm": 3.4920172691345215,
+      "learning_rate": 0.0,
+      "loss": 0.5032,
+      "step": 50
+    },
+    {
+      "epoch": 1.1142061281337048,
+      "eval_loss": 0.5250022411346436,
+      "eval_runtime": 8.3188,
+      "eval_samples_per_second": 36.423,
+      "eval_steps_per_second": 4.568,
+      "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": 8.051627496623309e+16,
+  "total_flos": 1.6068485461311488e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null