Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9abf80906b105c0c360ae636f0800558d48e03ec9da84fc03e9b4b194a7bee9d
+oid sha256:55d670876d5f1751525dcd1d2485cf5d7938a220a74e8b0dcd9d896699533031
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39f4597a2b33bcadddd9fd6164f68e41cb1a5926a655366de881202c215f00a6
+oid sha256:d9729a6963b2957e86ec19b0fac726ef7b435831f474d0b9c87fbece7d753aaf
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60db35eaaf59d54810cc3396d09681e6762b8ffc025a18b6d17777c6226994ae
+oid sha256:4c512d0ec68529c72208266e352bf035e666cf5d0e9cc678a45723c56bd0c5ad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:592b5122d417637565352f7566132050eec2a906626a39c842bdac577b6525c7
+oid sha256:49838ce22375ff81ab95e730ba6e425e71946020d0f483d5548f40a9d96db546
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb954deaf5e01460394ee395779806b8cf99a0678a0fb6e439a5c1a0ef77cc2d
+oid sha256:7d1802dc80ca5a44afe3beb883e67388ba5ad510d06e12c9d5a74f255157dcb5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63a1e0d6d1f8818a4d6c410d7b651cf7a69c760183f9daabcf2126aebf686b41
+oid sha256:1b084907b83e0d4b14b6d6c6200a9ebf79dba356869597314fcba99794f43c4a
 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": 5.045346260070801,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.13656538067599863,
+  "best_metric": 4.896439075469971,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.27313076135199726,
   "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": 75.863,
       "eval_steps_per_second": 9.537,
       "step": 25
+    },
+    {
+      "epoch": 0.14202799590303858,
+      "grad_norm": 3.3359363079071045,
+      "learning_rate": 5e-05,
+      "loss": 4.9104,
+      "step": 26
+    },
+    {
+      "epoch": 0.14749061113007852,
+      "grad_norm": 2.990004301071167,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 4.9808,
+      "step": 27
+    },
+    {
+      "epoch": 0.15295322635711847,
+      "grad_norm": 2.493718385696411,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 4.9926,
+      "step": 28
+    },
+    {
+      "epoch": 0.15841584158415842,
+      "grad_norm": 2.0746469497680664,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 4.9458,
+      "step": 29
+    },
+    {
+      "epoch": 0.16387845681119836,
+      "grad_norm": 1.7948659658432007,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.8397,
+      "step": 30
+    },
+    {
+      "epoch": 0.1693410720382383,
+      "grad_norm": 1.6932811737060547,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 4.9024,
+      "step": 31
+    },
+    {
+      "epoch": 0.17480368726527826,
+      "grad_norm": 1.7441197633743286,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.8987,
+      "step": 32
+    },
+    {
+      "epoch": 0.1802663024923182,
+      "grad_norm": 1.8560411930084229,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 5.0526,
+      "step": 33
+    },
+    {
+      "epoch": 0.18572891771935815,
+      "grad_norm": 2.0022428035736084,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 5.0421,
+      "step": 34
+    },
+    {
+      "epoch": 0.1911915329463981,
+      "grad_norm": 2.142507314682007,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.9688,
+      "step": 35
+    },
+    {
+      "epoch": 0.19665414817343804,
+      "grad_norm": 2.3231780529022217,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 5.162,
+      "step": 36
+    },
+    {
+      "epoch": 0.202116763400478,
+      "grad_norm": 2.606092929840088,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 5.0821,
+      "step": 37
+    },
+    {
+      "epoch": 0.20757937862751794,
+      "grad_norm": 1.6653012037277222,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.721,
+      "step": 38
+    },
+    {
+      "epoch": 0.21304199385455788,
+      "grad_norm": 1.5581425428390503,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 4.7959,
+      "step": 39
+    },
+    {
+      "epoch": 0.21850460908159783,
+      "grad_norm": 1.4504172801971436,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 4.8705,
+      "step": 40
+    },
+    {
+      "epoch": 0.22396722430863775,
+      "grad_norm": 1.403963565826416,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 4.8881,
+      "step": 41
+    },
+    {
+      "epoch": 0.2294298395356777,
+      "grad_norm": 1.5083348751068115,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.8065,
+      "step": 42
+    },
+    {
+      "epoch": 0.23489245476271764,
+      "grad_norm": 1.3726880550384521,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 4.881,
+      "step": 43
+    },
+    {
+      "epoch": 0.24035506998975759,
+      "grad_norm": 1.4420634508132935,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.9621,
+      "step": 44
+    },
+    {
+      "epoch": 0.24581768521679753,
+      "grad_norm": 1.4268460273742676,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.8976,
+      "step": 45
+    },
+    {
+      "epoch": 0.2512803004438375,
+      "grad_norm": 1.5003798007965088,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 5.045,
+      "step": 46
+    },
+    {
+      "epoch": 0.2567429156708774,
+      "grad_norm": 1.7467073202133179,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 5.0144,
+      "step": 47
+    },
+    {
+      "epoch": 0.26220553089791737,
+      "grad_norm": 1.8754444122314453,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 4.9771,
+      "step": 48
+    },
+    {
+      "epoch": 0.2676681461249573,
+      "grad_norm": 2.1238296031951904,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 5.1125,
+      "step": 49
+    },
+    {
+      "epoch": 0.27313076135199726,
+      "grad_norm": 2.818662405014038,
+      "learning_rate": 0.0,
+      "loss": 5.192,
+      "step": 50
+    },
+    {
+      "epoch": 0.27313076135199726,
+      "eval_loss": 4.896439075469971,
+      "eval_runtime": 16.2375,
+      "eval_samples_per_second": 75.935,
+      "eval_steps_per_second": 9.546,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null