Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41af64f7f1ffe24a13adcbe91e2aa4db88321ccd39bcc292571ed71b09f79d7e
+oid sha256:925178035321eed914aa0ebeb17fda38c4a384d0ef978f399930e3eea85bf31e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d80460711b3bf9ccaf0c3a08ab656b66d299adda763db607ddc4b856a323031
+oid sha256:e4e20a2242ec4f17c5b57e625b092ba9a95496803f9539cd7b782910ec74c982
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5df2e38ab667d7934d9bdf8b9b5dcdfe16c0ed4b2531dc35fbad0d2b36ac12a6
+oid sha256:316bea9b8f50e4e327b3d7b3623996860e552e62155f65bfef3de94066f47b89
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a324402bdf0476edb109dbf95bf84646a8ccc2a72c304be37288e039516a03f
+oid sha256:d18f56583d64440389f3b3048f611d67531f2d64c37f0b5c9f4d54f3322b844d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb1146b910206e56ba222275268a924b62e358e4a5e6ad8ae4f4555ea0923b7a
+oid sha256:9d6ec6ffea364928322158b36e4b1b3b2392b5a86abc2f729e91eb4db0b9cd44
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6128fe6c4da8439b1984cf68ad33a5ce9102fce5cfe50490b7d43be8c4dbbfbd
+oid sha256:e2e072047a80e29b474b923485a9fb3576d1a4f473eb53c146f4dfc1a1c65fae
 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": 1.4290605783462524,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2437538086532602,
+  "best_metric": 1.4016363620758057,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4875076173065204,
   "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": 34.806,
       "eval_steps_per_second": 4.382,
       "step": 25
+    },
+    {
+      "epoch": 0.2535039609993906,
+      "grad_norm": 0.37998339533805847,
+      "learning_rate": 5e-05,
+      "loss": 1.3721,
+      "step": 26
+    },
+    {
+      "epoch": 0.263254113345521,
+      "grad_norm": 4.013329029083252,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4348,
+      "step": 27
+    },
+    {
+      "epoch": 0.2730042656916514,
+      "grad_norm": 3.586048126220703,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4187,
+      "step": 28
+    },
+    {
+      "epoch": 0.28275441803778184,
+      "grad_norm": 0.8806138038635254,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.3836,
+      "step": 29
+    },
+    {
+      "epoch": 0.29250457038391225,
+      "grad_norm": 3.003892183303833,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3781,
+      "step": 30
+    },
+    {
+      "epoch": 0.30225472273004267,
+      "grad_norm": 3.9937074184417725,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3954,
+      "step": 31
+    },
+    {
+      "epoch": 0.3120048750761731,
+      "grad_norm": 2.614459276199341,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4087,
+      "step": 32
+    },
+    {
+      "epoch": 0.3217550274223035,
+      "grad_norm": 1.8414186239242554,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3564,
+      "step": 33
+    },
+    {
+      "epoch": 0.33150517976843386,
+      "grad_norm": 1.4713647365570068,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3688,
+      "step": 34
+    },
+    {
+      "epoch": 0.34125533211456427,
+      "grad_norm": 2.7540950775146484,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3867,
+      "step": 35
+    },
+    {
+      "epoch": 0.3510054844606947,
+      "grad_norm": 2.6376547813415527,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3858,
+      "step": 36
+    },
+    {
+      "epoch": 0.3607556368068251,
+      "grad_norm": 2.066033363342285,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.3884,
+      "step": 37
+    },
+    {
+      "epoch": 0.3705057891529555,
+      "grad_norm": 0.3976193368434906,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3782,
+      "step": 38
+    },
+    {
+      "epoch": 0.3802559414990859,
+      "grad_norm": 1.089373230934143,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.3808,
+      "step": 39
+    },
+    {
+      "epoch": 0.39000609384521634,
+      "grad_norm": 2.4371533393859863,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3528,
+      "step": 40
+    },
+    {
+      "epoch": 0.39975624619134675,
+      "grad_norm": 2.702479362487793,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3396,
+      "step": 41
+    },
+    {
+      "epoch": 0.40950639853747717,
+      "grad_norm": 1.2285147905349731,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3758,
+      "step": 42
+    },
+    {
+      "epoch": 0.4192565508836076,
+      "grad_norm": 0.20587307214736938,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.3853,
+      "step": 43
+    },
+    {
+      "epoch": 0.42900670322973794,
+      "grad_norm": 0.4681832492351532,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.357,
+      "step": 44
+    },
+    {
+      "epoch": 0.43875685557586835,
+      "grad_norm": 1.2280807495117188,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4035,
+      "step": 45
+    },
+    {
+      "epoch": 0.44850700792199877,
+      "grad_norm": 0.6826702356338501,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3778,
+      "step": 46
+    },
+    {
+      "epoch": 0.4582571602681292,
+      "grad_norm": 0.7341272234916687,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.379,
+      "step": 47
+    },
+    {
+      "epoch": 0.4680073126142596,
+      "grad_norm": 1.1211836338043213,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.39,
+      "step": 48
+    },
+    {
+      "epoch": 0.47775746496039,
+      "grad_norm": 0.9799886345863342,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.3842,
+      "step": 49
+    },
+    {
+      "epoch": 0.4875076173065204,
+      "grad_norm": 0.6755764484405518,
+      "learning_rate": 0.0,
+      "loss": 1.3731,
+      "step": 50
+    },
+    {
+      "epoch": 0.4875076173065204,
+      "eval_loss": 1.4016363620758057,
+      "eval_runtime": 19.8486,
+      "eval_samples_per_second": 34.813,
+      "eval_steps_per_second": 4.383,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null