Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a9c099118c9e83cf9aadbcffeac2fb263d6ba0d2a921178c38101dd864343d7
+oid sha256:53fec6a2b5e742d28dad9a7dad4e9c4f7c5e0a6958188ae57c1a557a8733f939
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41c7dfc00f89c256c4902ab6bee0ab504cef3de7f07c56a88477436d8724e7db
+oid sha256:c430f7411545b2cf6db4248dedc8263477a0b442e37d01a7d6a4e5a69d8862b1
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a93fec9bcb1251e9a95d3e2b8ec08f7e93e65d591f07e75a28bce76a0b36ea
+oid sha256:61af23bf882955cc95b803cbfc24683d818d99896bd154256ecaf8b57bd0943c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77858979842af30610605725d24f2f5fca6625387df2fa451d2f8b0671b06b7f
+oid sha256:ccb2d71f3f4bcc20f6af60751af20bb26a5d26674495d4912d3a473b6c1ff10b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9141cdacbe45fb8cf8ea89a1f529769da27469fc2903a858e8386f605cfb907f
+oid sha256:6bfde0fd8ae73deca238d4678df321bc7b213da87ca51a316d68b3609243b9bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d34d7c8e8d5258d431113eb222e61245afecfc853d63a156d27906ea6a9363a
+oid sha256:439a0f3a815108584e7a7da9d2f89bcb234af334034ba90cba2725c1bb33ca92
 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": 0.7038731575012207,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.045625641610585146,
+  "best_metric": 0.6613091826438904,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09125128322117029,
   "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": 24.559,
       "eval_steps_per_second": 6.385,
       "step": 25
+    },
+    {
+      "epoch": 0.04745066727500855,
+      "grad_norm": 0.35777395963668823,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.336,
+      "step": 26
+    },
+    {
+      "epoch": 0.04927569293943196,
+      "grad_norm": 0.45620062947273254,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6215,
+      "step": 27
+    },
+    {
+      "epoch": 0.051100718603855365,
+      "grad_norm": 0.48935970664024353,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.636,
+      "step": 28
+    },
+    {
+      "epoch": 0.05292574426827877,
+      "grad_norm": 0.44577130675315857,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5593,
+      "step": 29
+    },
+    {
+      "epoch": 0.05475076993270218,
+      "grad_norm": 0.6385313272476196,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.702,
+      "step": 30
+    },
+    {
+      "epoch": 0.05657579559712558,
+      "grad_norm": 0.5207433104515076,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.682,
+      "step": 31
+    },
+    {
+      "epoch": 0.05840082126154899,
+      "grad_norm": 0.5813780426979065,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.6973,
+      "step": 32
+    },
+    {
+      "epoch": 0.060225846925972396,
+      "grad_norm": 0.5056950449943542,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.7042,
+      "step": 33
+    },
+    {
+      "epoch": 0.0620508725903958,
+      "grad_norm": 0.6021554470062256,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8092,
+      "step": 34
+    },
+    {
+      "epoch": 0.06387589825481921,
+      "grad_norm": 0.6422117948532104,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9383,
+      "step": 35
+    },
+    {
+      "epoch": 0.06570092391924262,
+      "grad_norm": 0.7147862315177917,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.022,
+      "step": 36
+    },
+    {
+      "epoch": 0.06752594958366602,
+      "grad_norm": 0.7200132012367249,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.9203,
+      "step": 37
+    },
+    {
+      "epoch": 0.06935097524808943,
+      "grad_norm": 0.38760125637054443,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4126,
+      "step": 38
+    },
+    {
+      "epoch": 0.07117600091251283,
+      "grad_norm": 0.31938913464546204,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3984,
+      "step": 39
+    },
+    {
+      "epoch": 0.07300102657693623,
+      "grad_norm": 0.37477895617485046,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.5531,
+      "step": 40
+    },
+    {
+      "epoch": 0.07482605224135964,
+      "grad_norm": 0.45120054483413696,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6015,
+      "step": 41
+    },
+    {
+      "epoch": 0.07665107790578304,
+      "grad_norm": 0.4910838305950165,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.56,
+      "step": 42
+    },
+    {
+      "epoch": 0.07847610357020646,
+      "grad_norm": 0.46236470341682434,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6936,
+      "step": 43
+    },
+    {
+      "epoch": 0.08030112923462986,
+      "grad_norm": 0.5043991208076477,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.683,
+      "step": 44
+    },
+    {
+      "epoch": 0.08212615489905327,
+      "grad_norm": 0.5607537627220154,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8357,
+      "step": 45
+    },
+    {
+      "epoch": 0.08395118056347667,
+      "grad_norm": 0.5264842510223389,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6738,
+      "step": 46
+    },
+    {
+      "epoch": 0.08577620622790008,
+      "grad_norm": 0.5766991972923279,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7206,
+      "step": 47
+    },
+    {
+      "epoch": 0.08760123189232348,
+      "grad_norm": 0.6205928325653076,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9237,
+      "step": 48
+    },
+    {
+      "epoch": 0.0894262575567469,
+      "grad_norm": 0.7550768852233887,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.0183,
+      "step": 49
+    },
+    {
+      "epoch": 0.09125128322117029,
+      "grad_norm": 0.8377938270568848,
+      "learning_rate": 1e-05,
+      "loss": 0.9597,
+      "step": 50
+    },
+    {
+      "epoch": 0.09125128322117029,
+      "eval_loss": 0.6613091826438904,
+      "eval_runtime": 2.0395,
+      "eval_samples_per_second": 24.516,
+      "eval_steps_per_second": 6.374,
+      "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