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:f599f9d05d8669467ef70e250f4c9404f75c4a03a1347779ed38aa001c8f3aa8
+oid sha256:a513d08a104f5e64220271127f7025e924e46437722603c2eb37f7a6cec4c573
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18aaf0407db8e235f9b06c369e6d6939dd2f4d7c71d0e9e66472d61f0193615f
+oid sha256:23ad2a3162e073b0bcff1badb275e63b02c7d4e5ad3e4131d34a02ce2ec043b9
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4731cef1dfeac59fb691c761a3f10edd054f3525b8858019469426b2dc4b5aaf
+oid sha256:9e06f8f1edd74d47b90eceab415c4294d6bbf0b540417be3e217227a0fb537c7
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3714734f7385e97e87d04756da45c698a23e471231ad0eb6e8abbb836215b1ae
+oid sha256:dda381e9efa84bc517a039987d6afdaec546b2d9c84c2127d99c150aa983b535
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11f479f5170b8b2f14ec0acb6e33a31aceef4b81093b4f03c97456cf6bce7683
+oid sha256:28bc44aa4740c65e4e3e1144b46c30080ad702f21c937274d2a077b329e73bea
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e5722c006a35899b486f39f737ab707bc421b462f0ac2cbea9e95e354b3d999
+oid sha256:5d9baeab2d30953af2b013bd49e90f64ed9af3f246a3012541b3a8b711a32b99
 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": 0.33480188250541687,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.031431714600031434,
+  "best_metric": 0.1865025758743286,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06286342920006287,
   "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": 79.773,
       "eval_steps_per_second": 9.975,
       "step": 25
+    },
+    {
+      "epoch": 0.03268898318403269,
+      "grad_norm": 6.639444351196289,
+      "learning_rate": 5e-05,
+      "loss": 0.2724,
+      "step": 26
+    },
+    {
+      "epoch": 0.033946251768033946,
+      "grad_norm": 3.8194305896759033,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2312,
+      "step": 27
+    },
+    {
+      "epoch": 0.0352035203520352,
+      "grad_norm": 2.612955331802368,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1923,
+      "step": 28
+    },
+    {
+      "epoch": 0.03646078893603646,
+      "grad_norm": 1.882875680923462,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2243,
+      "step": 29
+    },
+    {
+      "epoch": 0.03771805752003772,
+      "grad_norm": 3.010631561279297,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.22,
+      "step": 30
+    },
+    {
+      "epoch": 0.038975326104038976,
+      "grad_norm": 3.0281689167022705,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1856,
+      "step": 31
+    },
+    {
+      "epoch": 0.04023259468804023,
+      "grad_norm": 2.0920002460479736,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2179,
+      "step": 32
+    },
+    {
+      "epoch": 0.04148986327204149,
+      "grad_norm": 1.6378231048583984,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1979,
+      "step": 33
+    },
+    {
+      "epoch": 0.042747131856042744,
+      "grad_norm": 3.4983468055725098,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2064,
+      "step": 34
+    },
+    {
+      "epoch": 0.04400440044004401,
+      "grad_norm": 4.694855690002441,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2309,
+      "step": 35
+    },
+    {
+      "epoch": 0.04526166902404526,
+      "grad_norm": 3.535817861557007,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2407,
+      "step": 36
+    },
+    {
+      "epoch": 0.04651893760804652,
+      "grad_norm": 4.406174659729004,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2433,
+      "step": 37
+    },
+    {
+      "epoch": 0.047776206192047775,
+      "grad_norm": 2.9204981327056885,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2023,
+      "step": 38
+    },
+    {
+      "epoch": 0.04903347477604903,
+      "grad_norm": 1.1347187757492065,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1773,
+      "step": 39
+    },
+    {
+      "epoch": 0.050290743360050294,
+      "grad_norm": 1.2280828952789307,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1617,
+      "step": 40
+    },
+    {
+      "epoch": 0.05154801194405155,
+      "grad_norm": 1.6335227489471436,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1701,
+      "step": 41
+    },
+    {
+      "epoch": 0.052805280528052806,
+      "grad_norm": 1.564247488975525,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1975,
+      "step": 42
+    },
+    {
+      "epoch": 0.05406254911205406,
+      "grad_norm": 2.325559377670288,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1812,
+      "step": 43
+    },
+    {
+      "epoch": 0.05531981769605532,
+      "grad_norm": 2.336494207382202,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1892,
+      "step": 44
+    },
+    {
+      "epoch": 0.056577086280056574,
+      "grad_norm": 2.2626729011535645,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1759,
+      "step": 45
+    },
+    {
+      "epoch": 0.05783435486405784,
+      "grad_norm": 2.434901714324951,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1839,
+      "step": 46
+    },
+    {
+      "epoch": 0.05909162344805909,
+      "grad_norm": 2.663579225540161,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1751,
+      "step": 47
+    },
+    {
+      "epoch": 0.06034889203206035,
+      "grad_norm": 2.5975544452667236,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1966,
+      "step": 48
+    },
+    {
+      "epoch": 0.061606160616061605,
+      "grad_norm": 1.679148554801941,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2511,
+      "step": 49
+    },
+    {
+      "epoch": 0.06286342920006287,
+      "grad_norm": 3.370861291885376,
+      "learning_rate": 0.0,
+      "loss": 0.2432,
+      "step": 50
+    },
+    {
+      "epoch": 0.06286342920006287,
+      "eval_loss": 0.1865025758743286,
+      "eval_runtime": 67.1822,
+      "eval_samples_per_second": 79.753,
+      "eval_steps_per_second": 9.973,
+      "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