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:c04ebbba447daab700804f92655927c77542e7104c0fe79819b39636b9072808
+oid sha256:f60beb57bd01c4e1ea03fefb3051a289013b9dd885ddf6b282ff8ee28ad3c706
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b11d9f898446126b93ea2a48128c56babd7fb88b37f81eb55691e1baea4736
+oid sha256:65802ef8fa45122a64efe230bca45677fea3d97cf4e9ab21b7d74542ac4fcf91
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122b289cc19becc9a9af11e11ef7915f3575391719f99151f4d53961ecc5e956
+oid sha256:1bd1bed0e6d7c3bf60749226636af5b8b9df47a8a416848c55619d802567596b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf65015552cc06a93bad9ddc96f4111cd89be4e83248d195a0c85cf47916950
+oid sha256:33cb0fb4aed93ed56c09be913c47aab932d2ca019d1c788a45f77e4ec7b0ffea
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769f8c304a4638d297b0b125d6d1925114120c7f44f463ee81c0f7c7c593d2a9
+oid sha256:60c446f4aa826a5bff0a06878c25cbd08b78525bcbc80d29c13f7518dcc5e962
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eebaa580b9b090713eb1ab6cfa72922ed9a841518b8eebf67e1e541c4818491a
+oid sha256:4630c2aaa887ac3ce154d619f7d7c151c7188fda79f88a0800fb57f2306ea99a
 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": 1.3360475301742554,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011740189604062106,
+  "best_metric": 1.314715027809143,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02348037920812421,
   "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": 35.064,
       "eval_steps_per_second": 4.385,
       "step": 25
+    },
+    {
+      "epoch": 0.01220979718822459,
+      "grad_norm": 0.43993884325027466,
+      "learning_rate": 5e-05,
+      "loss": 1.5061,
+      "step": 26
+    },
+    {
+      "epoch": 0.012679404772387074,
+      "grad_norm": 0.41342392563819885,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4372,
+      "step": 27
+    },
+    {
+      "epoch": 0.013149012356549559,
+      "grad_norm": 0.44319623708724976,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3508,
+      "step": 28
+    },
+    {
+      "epoch": 0.013618619940712043,
+      "grad_norm": 0.3479222059249878,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.342,
+      "step": 29
+    },
+    {
+      "epoch": 0.014088227524874528,
+      "grad_norm": 0.38919132947921753,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3623,
+      "step": 30
+    },
+    {
+      "epoch": 0.01455783510903701,
+      "grad_norm": 0.35072675347328186,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2877,
+      "step": 31
+    },
+    {
+      "epoch": 0.015027442693199495,
+      "grad_norm": 0.38517889380455017,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3297,
+      "step": 32
+    },
+    {
+      "epoch": 0.015497050277361979,
+      "grad_norm": 0.3642725348472595,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3139,
+      "step": 33
+    },
+    {
+      "epoch": 0.015966657861524465,
+      "grad_norm": 0.3697044551372528,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2089,
+      "step": 34
+    },
+    {
+      "epoch": 0.016436265445686948,
+      "grad_norm": 0.4046227037906647,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.2511,
+      "step": 35
+    },
+    {
+      "epoch": 0.016905873029849434,
+      "grad_norm": 0.37819936871528625,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1577,
+      "step": 36
+    },
+    {
+      "epoch": 0.017375480614011916,
+      "grad_norm": 0.40968626737594604,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1753,
+      "step": 37
+    },
+    {
+      "epoch": 0.0178450881981744,
+      "grad_norm": 0.4086762070655823,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3645,
+      "step": 38
+    },
+    {
+      "epoch": 0.018314695782336885,
+      "grad_norm": 0.38058918714523315,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4081,
+      "step": 39
+    },
+    {
+      "epoch": 0.018784303366499368,
+      "grad_norm": 0.3770791292190552,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4182,
+      "step": 40
+    },
+    {
+      "epoch": 0.019253910950661854,
+      "grad_norm": 0.39039525389671326,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4629,
+      "step": 41
+    },
+    {
+      "epoch": 0.019723518534824337,
+      "grad_norm": 0.3564213514328003,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3281,
+      "step": 42
+    },
+    {
+      "epoch": 0.020193126118986823,
+      "grad_norm": 0.4056853652000427,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2944,
+      "step": 43
+    },
+    {
+      "epoch": 0.020662733703149305,
+      "grad_norm": 0.36049678921699524,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3175,
+      "step": 44
+    },
+    {
+      "epoch": 0.02113234128731179,
+      "grad_norm": 0.3310118317604065,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2527,
+      "step": 45
+    },
+    {
+      "epoch": 0.021601948871474274,
+      "grad_norm": 0.34343573451042175,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2651,
+      "step": 46
+    },
+    {
+      "epoch": 0.02207155645563676,
+      "grad_norm": 0.3476006090641022,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2322,
+      "step": 47
+    },
+    {
+      "epoch": 0.022541164039799243,
+      "grad_norm": 0.3565845489501953,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2381,
+      "step": 48
+    },
+    {
+      "epoch": 0.023010771623961725,
+      "grad_norm": 0.3808521628379822,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1995,
+      "step": 49
+    },
+    {
+      "epoch": 0.02348037920812421,
+      "grad_norm": 0.4298349916934967,
+      "learning_rate": 0.0,
+      "loss": 1.1051,
+      "step": 50
+    },
+    {
+      "epoch": 0.02348037920812421,
+      "eval_loss": 1.314715027809143,
+      "eval_runtime": 409.369,
+      "eval_samples_per_second": 35.044,
+      "eval_steps_per_second": 4.382,
+      "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": 3.04185763044524e+17,
+  "total_flos": 6.093040386509373e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null