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:cf7fe3ce77fa248b8d8f23630cdbdca3f3e5ce328370eb9c085a2b5d52264c90
+oid sha256:98ee01c9d1d725033ec557886a6454b429244e48416d913b197e0ed106d8ef8c
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1675b48e02d55433c0dbbaf2978315d09031bb026c47b1b0a6df0853d59d5902
+oid sha256:61b502ca4b66c2c1cf435d4c6933a9d6fb910bb116f3e97ad0b48c8ca0ca8ba9
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:598940c273ae0e381dbe5ecdc9a61e1813303c7eabf2da0772be3bac44077bb9
+oid sha256:45395054b2f03208ec421207e7ecf7fcbf7ab887e98f2e98d240bbd264b1e41f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a607ed79cb269189f22c668c589dcb86edfee8d3b8e6e8f18f56d7b6c0bde4e0
+oid sha256:c4a7013ad699cdbd4687a756cbad637840e40c643633e099b2497c48ddd51991
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60cfca1cac7bbc8c0cecb55c7d8fa90d506d4709a85fea20ae83a2c97b37fd05
+oid sha256:cbe087001ac59180b30fc69f929ec546dcc1895cfc4d8518c778ea09ec927593
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd13f61ea63b8017dab1ff3e53c8de6e05ab465613b2270323d3fd23586735de
+oid sha256:d45c824ce51fffe47243f6a0bbbd0e5eaaba0d1d8d2a133c6bc84dcbd00f3acf
 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": 0.4253615736961365,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.217910447761194,
+  "best_metric": 0.4024839401245117,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.435820895522388,
   "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": 86.087,
       "eval_steps_per_second": 10.99,
       "step": 25
+    },
+    {
+      "epoch": 1.2656716417910447,
+      "grad_norm": 0.18392308056354523,
+      "learning_rate": 5e-05,
+      "loss": 0.3783,
+      "step": 26
+    },
+    {
+      "epoch": 1.3134328358208955,
+      "grad_norm": 0.17759908735752106,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4182,
+      "step": 27
+    },
+    {
+      "epoch": 1.3611940298507463,
+      "grad_norm": 0.19861653447151184,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4159,
+      "step": 28
+    },
+    {
+      "epoch": 1.408955223880597,
+      "grad_norm": 0.21638356149196625,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3822,
+      "step": 29
+    },
+    {
+      "epoch": 1.4567164179104477,
+      "grad_norm": 0.2728606164455414,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3745,
+      "step": 30
+    },
+    {
+      "epoch": 1.5044776119402985,
+      "grad_norm": 0.1896788477897644,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3724,
+      "step": 31
+    },
+    {
+      "epoch": 1.5522388059701493,
+      "grad_norm": 0.19130320847034454,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4189,
+      "step": 32
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.2291479855775833,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4087,
+      "step": 33
+    },
+    {
+      "epoch": 1.6477611940298509,
+      "grad_norm": 0.24589583277702332,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4007,
+      "step": 34
+    },
+    {
+      "epoch": 1.6955223880597015,
+      "grad_norm": 0.25085797905921936,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3735,
+      "step": 35
+    },
+    {
+      "epoch": 1.7432835820895523,
+      "grad_norm": 0.2219715267419815,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3978,
+      "step": 36
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 0.1881018429994583,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3952,
+      "step": 37
+    },
+    {
+      "epoch": 1.8388059701492536,
+      "grad_norm": 0.21645773947238922,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4167,
+      "step": 38
+    },
+    {
+      "epoch": 1.8865671641791044,
+      "grad_norm": 0.2337845265865326,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.377,
+      "step": 39
+    },
+    {
+      "epoch": 1.9343283582089552,
+      "grad_norm": 0.2754746079444885,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.368,
+      "step": 40
+    },
+    {
+      "epoch": 2.005970149253731,
+      "grad_norm": 0.30742526054382324,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5339,
+      "step": 41
+    },
+    {
+      "epoch": 2.053731343283582,
+      "grad_norm": 0.1772758960723877,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3891,
+      "step": 42
+    },
+    {
+      "epoch": 2.1014925373134328,
+      "grad_norm": 0.19144101440906525,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3792,
+      "step": 43
+    },
+    {
+      "epoch": 2.1492537313432836,
+      "grad_norm": 0.2184714525938034,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3801,
+      "step": 44
+    },
+    {
+      "epoch": 2.1970149253731344,
+      "grad_norm": 0.25839197635650635,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.384,
+      "step": 45
+    },
+    {
+      "epoch": 2.244776119402985,
+      "grad_norm": 0.26673170924186707,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3292,
+      "step": 46
+    },
+    {
+      "epoch": 2.292537313432836,
+      "grad_norm": 0.18285243213176727,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4068,
+      "step": 47
+    },
+    {
+      "epoch": 2.3402985074626868,
+      "grad_norm": 0.20161080360412598,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3849,
+      "step": 48
+    },
+    {
+      "epoch": 2.388059701492537,
+      "grad_norm": 0.21239733695983887,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3788,
+      "step": 49
+    },
+    {
+      "epoch": 2.435820895522388,
+      "grad_norm": 0.23920461535453796,
+      "learning_rate": 0.0,
+      "loss": 0.3511,
+      "step": 50
+    },
+    {
+      "epoch": 2.435820895522388,
+      "eval_loss": 0.4024839401245117,
+      "eval_runtime": 1.638,
+      "eval_samples_per_second": 86.08,
+      "eval_steps_per_second": 10.989,
+      "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