Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82f313cd05fb53d3397134f89f0bdc0a8b9205f28665538a36ca727bbbf0e228
+oid sha256:f7873b8b25a2f6945d1f7cac0a1be427258adcc0d08f92177b7c21ac4cee81ba
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73b8edf22cccb98f8c94ab62713e36746a95cf3c0634304c5d495ee9739e77ca
+oid sha256:5c25c3ec48317d842bdcddfa6ec74b67d68c0f339f3d9e5cabfed18f15e26f89
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ece648e8a2fbf2593cc9f7c847485a4460433efc10011077ab57feff819104c
+oid sha256:c87413fd4ce4d8feea698aebad0c897a9e2df9a13bec3729a34f57061bcaedda
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8809557f23994aecd83a546ca437b026270c0b32f4178207f3729a6225bf929e
+oid sha256:a7f667714deff93b5bfa8317e9b36e39d87a122655fb659434a376c303da48f0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9467c35fd3a91ef42abad2f134a3bbeae3fec565155d64192a59392f3011f90e
+oid sha256:10fdb4d858e25ff9020e3d1c9db6ad735310d25a23ebd83c13497b1f82a26bf8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685d6e3226636bb9c536dc055c44525d43c4b320854d96077f4208032e6a7bc5
+oid sha256:4f3dbd3b7b1d07a812b5de07ac7d2299b2f785faee4519850f9b3d2b297a6d34
 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": 0.548164963722229,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02637826431020839,
+  "best_metric": 0.5266842842102051,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05275652862041678,
   "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": 12.119,
       "eval_steps_per_second": 3.151,
       "step": 25
+    },
+    {
+      "epoch": 0.027433394882616723,
+      "grad_norm": 0.07384027540683746,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5594,
+      "step": 26
+    },
+    {
+      "epoch": 0.02848852545502506,
+      "grad_norm": 0.08900860697031021,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.4782,
+      "step": 27
+    },
+    {
+      "epoch": 0.029543656027433394,
+      "grad_norm": 0.11665589362382889,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4881,
+      "step": 28
+    },
+    {
+      "epoch": 0.03059878659984173,
+      "grad_norm": 0.13971996307373047,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4862,
+      "step": 29
+    },
+    {
+      "epoch": 0.031653917172250065,
+      "grad_norm": 0.16317173838615417,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5448,
+      "step": 30
+    },
+    {
+      "epoch": 0.0327090477446584,
+      "grad_norm": 0.17055854201316833,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4616,
+      "step": 31
+    },
+    {
+      "epoch": 0.03376417831706674,
+      "grad_norm": 0.20446307957172394,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5126,
+      "step": 32
+    },
+    {
+      "epoch": 0.03481930888947507,
+      "grad_norm": 0.19352230429649353,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5322,
+      "step": 33
+    },
+    {
+      "epoch": 0.03587443946188341,
+      "grad_norm": 0.1872176229953766,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5782,
+      "step": 34
+    },
+    {
+      "epoch": 0.036929570034291745,
+      "grad_norm": 0.18367165327072144,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.51,
+      "step": 35
+    },
+    {
+      "epoch": 0.03798470060670008,
+      "grad_norm": 0.2161339670419693,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.5731,
+      "step": 36
+    },
+    {
+      "epoch": 0.03903983117910841,
+      "grad_norm": 0.29164037108421326,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.559,
+      "step": 37
+    },
+    {
+      "epoch": 0.04009496175151675,
+      "grad_norm": 0.08342503756284714,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6285,
+      "step": 38
+    },
+    {
+      "epoch": 0.04115009232392509,
+      "grad_norm": 0.07071754336357117,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.5103,
+      "step": 39
+    },
+    {
+      "epoch": 0.042205222896333425,
+      "grad_norm": 0.0784253254532814,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4681,
+      "step": 40
+    },
+    {
+      "epoch": 0.043260353468741755,
+      "grad_norm": 0.09445218741893768,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5245,
+      "step": 41
+    },
+    {
+      "epoch": 0.04431548404115009,
+      "grad_norm": 0.1052173376083374,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4996,
+      "step": 42
+    },
+    {
+      "epoch": 0.04537061461355843,
+      "grad_norm": 0.10680738091468811,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4858,
+      "step": 43
+    },
+    {
+      "epoch": 0.04642574518596676,
+      "grad_norm": 0.11538807302713394,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5183,
+      "step": 44
+    },
+    {
+      "epoch": 0.0474808757583751,
+      "grad_norm": 0.1201535016298294,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4874,
+      "step": 45
+    },
+    {
+      "epoch": 0.048536006330783435,
+      "grad_norm": 0.14609256386756897,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.5095,
+      "step": 46
+    },
+    {
+      "epoch": 0.04959113690319177,
+      "grad_norm": 0.15216562151908875,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4945,
+      "step": 47
+    },
+    {
+      "epoch": 0.0506462674756001,
+      "grad_norm": 0.19578099250793457,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5177,
+      "step": 48
+    },
+    {
+      "epoch": 0.05170139804800844,
+      "grad_norm": 0.2716890871524811,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.577,
+      "step": 49
+    },
+    {
+      "epoch": 0.05275652862041678,
+      "grad_norm": 0.5881212949752808,
+      "learning_rate": 1e-05,
+      "loss": 0.692,
+      "step": 50
+    },
+    {
+      "epoch": 0.05275652862041678,
+      "eval_loss": 0.5266842842102051,
+      "eval_runtime": 4.1068,
+      "eval_samples_per_second": 12.175,
+      "eval_steps_per_second": 3.165,
+      "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": 2.6394132033306624e+17,
+  "total_flos": 5.2730742643359744e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null