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:cef808decc69f38946b6d022ab672054b7fa59406a8a35ff3cfa020ca20f40b8
+oid sha256:25901447d2676d8f2c55df97798ea741a98b505bf8e2a1d5e477e46776a956a8
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4867f7c9f37f3fe65b10c656a894ec522a1da144f26c4ce86fa10267337bcd00
+oid sha256:3518dc9232e6b039d84e9c18cc6b0092dcf658aef14b9229fe85950636bc4cfd
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e2b22111dfe82b04bd8ce837e692c14307641607adc1cbf472ac1fbac2fc8e
+oid sha256:2b4189f1f8d3324ef864094755a72f5c047271673b1404ef79bb1c40363ab720
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a73c164ab83c553ca4345bd8298aa711fdfac4e7e65c6e4f6745a6420438f4a
+oid sha256:6ac089046021e4b4453d075a5244a496dd1ca7e7ad3041d92b1aa5326e5952f6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd88f48afa779c343f24dca1a5214b6609544f3deefb7098a6e8ac4b250fbe62
+oid sha256:a8db5241dd4c1d8a236e92b499a61f9f566803dcde5bdfe3e432742a559d5cca
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75d3d252aa3f5e1adb8727e0c21d838200f8e6af6505c257489bd33c0d1ddab7
+oid sha256:3832c6a72c322ce93fbff2babc33b16b3ef50d5d518c72f4cf2aa3eb6c9d96ee
 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": 2.4363224506378174,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08218615163344976,
+  "best_metric": 2.372469186782837,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16437230326689953,
   "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": 88.515,
       "eval_steps_per_second": 11.097,
       "step": 25
+    },
+    {
+      "epoch": 0.08547359769878775,
+      "grad_norm": 2.3405513763427734,
+      "learning_rate": 5e-05,
+      "loss": 2.5165,
+      "step": 26
+    },
+    {
+      "epoch": 0.08876104376412575,
+      "grad_norm": 2.2251501083374023,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.2263,
+      "step": 27
+    },
+    {
+      "epoch": 0.09204848982946373,
+      "grad_norm": 2.1191866397857666,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.2702,
+      "step": 28
+    },
+    {
+      "epoch": 0.09533593589480173,
+      "grad_norm": 2.2065281867980957,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.2773,
+      "step": 29
+    },
+    {
+      "epoch": 0.09862338196013971,
+      "grad_norm": 1.8443723917007446,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.2602,
+      "step": 30
+    },
+    {
+      "epoch": 0.10191082802547771,
+      "grad_norm": 1.5738049745559692,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1641,
+      "step": 31
+    },
+    {
+      "epoch": 0.1051982740908157,
+      "grad_norm": 1.3031741380691528,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1899,
+      "step": 32
+    },
+    {
+      "epoch": 0.1084857201561537,
+      "grad_norm": 1.0444599390029907,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.1833,
+      "step": 33
+    },
+    {
+      "epoch": 0.11177316622149168,
+      "grad_norm": 1.0775002241134644,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.2802,
+      "step": 34
+    },
+    {
+      "epoch": 0.11506061228682966,
+      "grad_norm": 1.175281047821045,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.2692,
+      "step": 35
+    },
+    {
+      "epoch": 0.11834805835216766,
+      "grad_norm": 1.396524429321289,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.3438,
+      "step": 36
+    },
+    {
+      "epoch": 0.12163550441750565,
+      "grad_norm": 1.8557279109954834,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.4395,
+      "step": 37
+    },
+    {
+      "epoch": 0.12492295048284364,
+      "grad_norm": 0.9615146517753601,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.3882,
+      "step": 38
+    },
+    {
+      "epoch": 0.12821039654818164,
+      "grad_norm": 0.9084357619285583,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.1733,
+      "step": 39
+    },
+    {
+      "epoch": 0.13149784261351963,
+      "grad_norm": 0.8892095685005188,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.2233,
+      "step": 40
+    },
+    {
+      "epoch": 0.1347852886788576,
+      "grad_norm": 0.8900955319404602,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.1454,
+      "step": 41
+    },
+    {
+      "epoch": 0.1380727347441956,
+      "grad_norm": 0.9376126527786255,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1985,
+      "step": 42
+    },
+    {
+      "epoch": 0.14136018080953358,
+      "grad_norm": 0.996600866317749,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.1821,
+      "step": 43
+    },
+    {
+      "epoch": 0.1446476268748716,
+      "grad_norm": 0.9531171321868896,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.198,
+      "step": 44
+    },
+    {
+      "epoch": 0.14793507294020958,
+      "grad_norm": 0.9684677124023438,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.2519,
+      "step": 45
+    },
+    {
+      "epoch": 0.15122251900554756,
+      "grad_norm": 1.0261461734771729,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.2534,
+      "step": 46
+    },
+    {
+      "epoch": 0.15450996507088555,
+      "grad_norm": 1.2255746126174927,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.1516,
+      "step": 47
+    },
+    {
+      "epoch": 0.15779741113622356,
+      "grad_norm": 1.3936471939086914,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.4314,
+      "step": 48
+    },
+    {
+      "epoch": 0.16108485720156154,
+      "grad_norm": 1.5317000150680542,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.4603,
+      "step": 49
+    },
+    {
+      "epoch": 0.16437230326689953,
+      "grad_norm": 2.6237375736236572,
+      "learning_rate": 0.0,
+      "loss": 2.6934,
+      "step": 50
+    },
+    {
+      "epoch": 0.16437230326689953,
+      "eval_loss": 2.372469186782837,
+      "eval_runtime": 23.1603,
+      "eval_samples_per_second": 88.513,
+      "eval_steps_per_second": 11.097,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null