Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48484f029cb87b6919e213d85fe315e84b56e73d68992c6410f688317a2d4fc6
+oid sha256:a6dfcfea2b36dbe21d65269d9dd30c45ef6fac12ab9a22459e42ee63db079a7d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b27e4269eaf3e887c01cf088b9e2c528f707e3c1c129000f6599efc0d3587d
+oid sha256:1e9561f9a960702cfde444c8d899acedc66472c4a5ee5864b8f3ca8498fdbfec
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee359dbb81f7a2d940f7240d214565022e70569ab037ed99eaee1a054715174
+oid sha256:4f72075e8c7700716db501feddd99718d917be80aa4ad4bba6080dba2e4a381c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7773d9c69220dd17db12a8a47cdba5dabf11dd0b6adc22e0d631f806bfb2f9d4
+oid sha256:f06acf56809b57487d32e4e0a78a55a0bd4b992c96d0bc6199f596de4972e4e9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:701aaef980a51fdc00e73830dd3f917ec3105caa5c8dfadf976c1a450b81dd03
+oid sha256:b49e8f9f28f019e7d775ecbcc942e8150f4c61b01057a44dc4512dacae109252
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bd65dcd050ae0171d53a416aa65a38dcd44d66e5713af762c82604c7b0f6064
+oid sha256:5a87b79bb44927c90f2318abe45b187ac50e200a06d4d93b8da2706aa029662a
 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": 1.1888800859451294,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.20110608345902464,
+  "best_metric": 1.1219658851623535,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4022121669180493,
   "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": 17.575,
       "eval_steps_per_second": 4.57,
       "step": 25
+    },
+    {
+      "epoch": 0.20915032679738563,
+      "grad_norm": 56.16391372680664,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 20.0174,
+      "step": 26
+    },
+    {
+      "epoch": 0.2171945701357466,
+      "grad_norm": 68.69602966308594,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 19.5351,
+      "step": 27
+    },
+    {
+      "epoch": 0.2252388134741076,
+      "grad_norm": 62.31421661376953,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 18.7906,
+      "step": 28
+    },
+    {
+      "epoch": 0.23328305681246858,
+      "grad_norm": 53.402610778808594,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 18.4947,
+      "step": 29
+    },
+    {
+      "epoch": 0.24132730015082957,
+      "grad_norm": 70.05078125,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 20.6999,
+      "step": 30
+    },
+    {
+      "epoch": 0.24937154348919055,
+      "grad_norm": 54.77640151977539,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 20.1772,
+      "step": 31
+    },
+    {
+      "epoch": 0.2574157868275515,
+      "grad_norm": 98.4924087524414,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 19.2579,
+      "step": 32
+    },
+    {
+      "epoch": 0.2654600301659125,
+      "grad_norm": 53.991050720214844,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 18.3679,
+      "step": 33
+    },
+    {
+      "epoch": 0.27350427350427353,
+      "grad_norm": 57.84612274169922,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 18.6821,
+      "step": 34
+    },
+    {
+      "epoch": 0.2815485168426345,
+      "grad_norm": 90.99256134033203,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 17.9972,
+      "step": 35
+    },
+    {
+      "epoch": 0.2895927601809955,
+      "grad_norm": 52.215545654296875,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 19.1813,
+      "step": 36
+    },
+    {
+      "epoch": 0.29763700351935646,
+      "grad_norm": 57.910064697265625,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 18.8931,
+      "step": 37
+    },
+    {
+      "epoch": 0.30568124685771747,
+      "grad_norm": 61.40287399291992,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 18.1066,
+      "step": 38
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 68.80261993408203,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 19.6066,
+      "step": 39
+    },
+    {
+      "epoch": 0.32176973353443944,
+      "grad_norm": 76.48763275146484,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 18.5249,
+      "step": 40
+    },
+    {
+      "epoch": 0.3298139768728004,
+      "grad_norm": 77.12066650390625,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 18.2736,
+      "step": 41
+    },
+    {
+      "epoch": 0.3378582202111614,
+      "grad_norm": 56.564598083496094,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 19.7781,
+      "step": 42
+    },
+    {
+      "epoch": 0.34590246354952237,
+      "grad_norm": 54.434967041015625,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 18.5295,
+      "step": 43
+    },
+    {
+      "epoch": 0.3539467068878834,
+      "grad_norm": 43.34243392944336,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 19.221,
+      "step": 44
+    },
+    {
+      "epoch": 0.36199095022624433,
+      "grad_norm": 49.38004684448242,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 18.6659,
+      "step": 45
+    },
+    {
+      "epoch": 0.37003519356460535,
+      "grad_norm": 47.048587799072266,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 19.2094,
+      "step": 46
+    },
+    {
+      "epoch": 0.3780794369029663,
+      "grad_norm": 39.93241882324219,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 18.0108,
+      "step": 47
+    },
+    {
+      "epoch": 0.3861236802413273,
+      "grad_norm": 31.25848388671875,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 17.8436,
+      "step": 48
+    },
+    {
+      "epoch": 0.3941679235796883,
+      "grad_norm": 41.93825912475586,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 18.9396,
+      "step": 49
+    },
+    {
+      "epoch": 0.4022121669180493,
+      "grad_norm": 42.091880798339844,
+      "learning_rate": 1e-05,
+      "loss": 17.6779,
+      "step": 50
+    },
+    {
+      "epoch": 0.4022121669180493,
+      "eval_loss": 1.1219658851623535,
+      "eval_runtime": 2.8474,
+      "eval_samples_per_second": 17.56,
+      "eval_steps_per_second": 4.566,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null