Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b7a809433582d161b38c67cd89b7322d0097d57b5c652cbeab00f091ea8ba4
+oid sha256:fdb6c594faa71100bc9678a3e1e494e31f6ea5e06062e77727cbcf48b5edef7e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686a8549c2b90be18247ee6f8034081223588a2294132a4ce2b944e4efbee40b
+oid sha256:92920a5326d777abc0fad161d0de69a2798ac86627c08c1eb6e92af2715f9ee3
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e92354f299d1086bd459c5ac3e827da4ead88e24eaa996790d471683af607ef
+oid sha256:55d3e086b25a96d97ac1ae30bba5cbcb2adf3f4171cb27895e8faaf68cc1dcde
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edbb7bc0e29316fb3809ab6187b20804a928bd689b90f3f28641f77f8cd96233
+oid sha256:7f5cea2c54411ebd00e47ea071f9fd46b2089752f740026f2fcfac979cf295c2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd8dc07fdcd77939ab82199c131c120f9944d05539c25ffeaa00ee286cdd829
+oid sha256:2eb8155e10cf27b067d2ea8159a6e4592e1c0ccd526cc9e02da91982a89a498e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17a204006926d29265f75b7610933d436ff2d78593854e4ef63086b4fa01b96
+oid sha256:19d43bd691bf43c95273432f56f77b913401a956ed49f259059a97a425b14b1f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 7.100727088982239e-06,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12562814070351758,
+  "best_metric": 7.772435992592364e-07,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.25125628140703515,
   "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": 24.488,
       "eval_steps_per_second": 6.367,
       "step": 25
+    },
+    {
+      "epoch": 0.1306532663316583,
+      "grad_norm": 0.0012525977799668908,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.135678391959799,
+      "grad_norm": 0.0007943892851471901,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.1407035175879397,
+      "grad_norm": 0.003067328594624996,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.1457286432160804,
+      "grad_norm": 0.0008991939830593765,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.1507537688442211,
+      "grad_norm": 0.00046679627848789096,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.15577889447236182,
+      "grad_norm": 0.00047094107139855623,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.16080402010050251,
+      "grad_norm": 0.00032768698292784393,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.1658291457286432,
+      "grad_norm": 0.0002552347432356328,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.1708542713567839,
+      "grad_norm": 0.0002349390706513077,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.17587939698492464,
+      "grad_norm": 0.00030390697065740824,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.18090452261306533,
+      "grad_norm": 0.00018882301810663193,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.18592964824120603,
+      "grad_norm": 0.00014582593576051295,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.19095477386934673,
+      "grad_norm": 0.00023641975712962449,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.19597989949748743,
+      "grad_norm": 0.00016852810222189873,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 0.0002045270084636286,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.20603015075376885,
+      "grad_norm": 0.00016816142306197435,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.21105527638190955,
+      "grad_norm": 0.0001245664752786979,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.21608040201005024,
+      "grad_norm": 0.0001389732351526618,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.22110552763819097,
+      "grad_norm": 0.00014751502021681517,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.22613065326633167,
+      "grad_norm": 0.0001148287410615012,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.23115577889447236,
+      "grad_norm": 0.00013220967957749963,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.23618090452261306,
+      "grad_norm": 0.00010563267278485,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.24120603015075376,
+      "grad_norm": 0.00010591024329187348,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.24623115577889448,
+      "grad_norm": 0.00011068899766542017,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "grad_norm": 0.0006384285516105592,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.25125628140703515,
+      "eval_loss": 7.772435992592364e-07,
+      "eval_runtime": 2.0538,
+      "eval_samples_per_second": 24.345,
+      "eval_steps_per_second": 6.33,
+      "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