Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104d00bdf293ee52e96075ac915e89e9d5e2ed0eb7ac9549fbd8f70754b47b1d
+oid sha256:fce3c66263b09cc29a8663bfadd455d008daf02c8855da4b711c0c0f1398290e
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76bbdb72e027dd9bf6d1c0dcb2a8172e2f7767b9ba6996603d2df4621c512e67
+oid sha256:5cb4ba286d4fbcc7cbe0d39ac15e4b39bd452596b20e1d7b62f38fcc1673511b
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52564497ffdee94962b08febe4d929acf362416c42156ae6c385e2362aa3e825
+oid sha256:74cd6be697de83d430849fe62ddd636a6de5ad60680dd38dd2dc6b9560d91271
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa7701d12a180d25c38a501f6752f8f326f35526dc47f222b0861bb391666d2
+oid sha256:68c5957a7f310682b3c18c2e74d7af8bd3219b506c1805e086615c7820efe8af
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb548f4f345f3c3f8dfe52d799b6d8be867ba3e41da850a4b94a3c1af3af66c7
+oid sha256:39ca003ba753245f851e7846596b1c8ffa4447efd9e61ae9b869d3d859ac7ed0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d043233ea411669a7abb931cb666352499871847f7d36d23d2c07742aebd0780
+oid sha256:3eec0274825980d06548d458415913c8144dd706fe252d0978ed35bd0868fdeb
 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": 1.6219940185546875,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012340346763744061,
+  "best_metric": 1.5829479694366455,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.024680693527488123,
   "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": 23.336,
       "eval_steps_per_second": 6.067,
       "step": 25
+    },
+    {
+      "epoch": 0.012833960634293824,
+      "grad_norm": 0.8619699478149414,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6531,
+      "step": 26
+    },
+    {
+      "epoch": 0.013327574504843585,
+      "grad_norm": 0.8271181583404541,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.6839,
+      "step": 27
+    },
+    {
+      "epoch": 0.013821188375393348,
+      "grad_norm": 0.8570282459259033,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.4859,
+      "step": 28
+    },
+    {
+      "epoch": 0.014314802245943111,
+      "grad_norm": 0.8331882953643799,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.6899,
+      "step": 29
+    },
+    {
+      "epoch": 0.014808416116492874,
+      "grad_norm": 0.7136693000793457,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.4245,
+      "step": 30
+    },
+    {
+      "epoch": 0.015302029987042635,
+      "grad_norm": 0.7932525873184204,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.5425,
+      "step": 31
+    },
+    {
+      "epoch": 0.015795643857592398,
+      "grad_norm": 0.8250367641448975,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.5708,
+      "step": 32
+    },
+    {
+      "epoch": 0.01628925772814216,
+      "grad_norm": 0.7967509627342224,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.5401,
+      "step": 33
+    },
+    {
+      "epoch": 0.016782871598691924,
+      "grad_norm": 0.8470743298530579,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.5565,
+      "step": 34
+    },
+    {
+      "epoch": 0.017276485469241685,
+      "grad_norm": 0.8121418356895447,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.5739,
+      "step": 35
+    },
+    {
+      "epoch": 0.01777009933979145,
+      "grad_norm": 0.8498193621635437,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.5876,
+      "step": 36
+    },
+    {
+      "epoch": 0.01826371321034121,
+      "grad_norm": 0.9225755333900452,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.5783,
+      "step": 37
+    },
+    {
+      "epoch": 0.01875732708089097,
+      "grad_norm": 0.7638592720031738,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.4589,
+      "step": 38
+    },
+    {
+      "epoch": 0.019250940951440736,
+      "grad_norm": 0.7743381261825562,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.5623,
+      "step": 39
+    },
+    {
+      "epoch": 0.019744554821990497,
+      "grad_norm": 0.7764542698860168,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5379,
+      "step": 40
+    },
+    {
+      "epoch": 0.020238168692540262,
+      "grad_norm": 0.7662834525108337,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.4034,
+      "step": 41
+    },
+    {
+      "epoch": 0.020731782563090023,
+      "grad_norm": 0.7414330244064331,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.4841,
+      "step": 42
+    },
+    {
+      "epoch": 0.021225396433639784,
+      "grad_norm": 0.7455458045005798,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.5619,
+      "step": 43
+    },
+    {
+      "epoch": 0.02171901030418955,
+      "grad_norm": 0.8360099196434021,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.5544,
+      "step": 44
+    },
+    {
+      "epoch": 0.02221262417473931,
+      "grad_norm": 0.795028805732727,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.5429,
+      "step": 45
+    },
+    {
+      "epoch": 0.02270623804528907,
+      "grad_norm": 0.7889432907104492,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.4098,
+      "step": 46
+    },
+    {
+      "epoch": 0.023199851915838836,
+      "grad_norm": 0.7665262222290039,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4591,
+      "step": 47
+    },
+    {
+      "epoch": 0.023693465786388597,
+      "grad_norm": 0.7203249335289001,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.4405,
+      "step": 48
+    },
+    {
+      "epoch": 0.02418707965693836,
+      "grad_norm": 0.8871418237686157,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5467,
+      "step": 49
+    },
+    {
+      "epoch": 0.024680693527488123,
+      "grad_norm": 0.9818035364151001,
+      "learning_rate": 1e-05,
+      "loss": 1.5304,
+      "step": 50
+    },
+    {
+      "epoch": 0.024680693527488123,
+      "eval_loss": 1.5829479694366455,
+      "eval_runtime": 2.1198,
+      "eval_samples_per_second": 23.588,
+      "eval_steps_per_second": 6.133,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null