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:b832e2aedad2d2512a4a3a1870df92bdf171bdea4ba3f044e61df1d8707839e6
+oid sha256:360aa8ebbeecaa054bb075ef3451cbfb773017f1a0aaaed2785dd5af2a3bcf48
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d7c18dc27a551d22f83b7688e7f6d7272543e4fbf625ba118103d4026dba9a
+oid sha256:982388bbec0a4b0833616c72c8cbe744976a66385b7a9187ef61808e014f3ff7
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:056ce5bcfa882871deecdd29d91b841bb9a411dd80dcf147368cf66a179c12e7
+oid sha256:400458b2697ef403b04ad49b0954cb6e3d3e5495a00822545bdfc20afc4c5db9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d8164230dbbfc96b8ceac574240f513f362f8d12924fc843c2835f559ce732
+oid sha256:c35e85554108ccdafbc3d356be96617f23cc87924171bf37babc9f3ea0e16561
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33997f41e672fbd21e0612965d5f077cb4a30389fe61c282af0d347aa3ccf0c2
+oid sha256:c583ce8ee61c9b14a0800d7134fa7790a3377fb5f8e92169578043f8a8cbbca3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21c373642f2ea69c77286f6a2b95abf404d079988cf2d06ecc4eb7a5b65b0bcf
+oid sha256:4124611a9cbf847e57644432222ccf70e9a264770cefb38bd97cf3e83d2f237d
 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": 0.6586966514587402,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9501187648456056,
+  "best_metric": 0.6436007022857666,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9002375296912115,
   "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": 27.095,
       "eval_steps_per_second": 7.045,
       "step": 25
+    },
+    {
+      "epoch": 0.9881235154394299,
+      "grad_norm": 0.3798254430294037,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7236,
+      "step": 26
+    },
+    {
+      "epoch": 1.0261282660332542,
+      "grad_norm": 0.27939629554748535,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9871,
+      "step": 27
+    },
+    {
+      "epoch": 1.0641330166270784,
+      "grad_norm": 0.12196327745914459,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4242,
+      "step": 28
+    },
+    {
+      "epoch": 1.1021377672209025,
+      "grad_norm": 0.15212561190128326,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5408,
+      "step": 29
+    },
+    {
+      "epoch": 1.1401425178147269,
+      "grad_norm": 0.16143955290317535,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4121,
+      "step": 30
+    },
+    {
+      "epoch": 1.178147268408551,
+      "grad_norm": 0.21406219899654388,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4644,
+      "step": 31
+    },
+    {
+      "epoch": 1.2161520190023754,
+      "grad_norm": 0.2238663136959076,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5473,
+      "step": 32
+    },
+    {
+      "epoch": 1.2541567695961995,
+      "grad_norm": 0.1697235107421875,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.564,
+      "step": 33
+    },
+    {
+      "epoch": 1.2921615201900236,
+      "grad_norm": 0.14793650805950165,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5657,
+      "step": 34
+    },
+    {
+      "epoch": 1.330166270783848,
+      "grad_norm": 0.13581204414367676,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.403,
+      "step": 35
+    },
+    {
+      "epoch": 1.3681710213776723,
+      "grad_norm": 0.15603549778461456,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4114,
+      "step": 36
+    },
+    {
+      "epoch": 1.4061757719714965,
+      "grad_norm": 0.180665522813797,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3648,
+      "step": 37
+    },
+    {
+      "epoch": 1.4441805225653206,
+      "grad_norm": 0.24020951986312866,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6151,
+      "step": 38
+    },
+    {
+      "epoch": 1.482185273159145,
+      "grad_norm": 0.27907803654670715,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6972,
+      "step": 39
+    },
+    {
+      "epoch": 1.520190023752969,
+      "grad_norm": 0.18653662502765656,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4836,
+      "step": 40
+    },
+    {
+      "epoch": 1.5581947743467932,
+      "grad_norm": 0.13568323850631714,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3973,
+      "step": 41
+    },
+    {
+      "epoch": 1.5961995249406176,
+      "grad_norm": 0.15123961865901947,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4341,
+      "step": 42
+    },
+    {
+      "epoch": 1.634204275534442,
+      "grad_norm": 0.1637600213289261,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4071,
+      "step": 43
+    },
+    {
+      "epoch": 1.672209026128266,
+      "grad_norm": 0.21520577371120453,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5047,
+      "step": 44
+    },
+    {
+      "epoch": 1.7102137767220902,
+      "grad_norm": 0.2549339830875397,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.5903,
+      "step": 45
+    },
+    {
+      "epoch": 1.7482185273159145,
+      "grad_norm": 0.17493799328804016,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4101,
+      "step": 46
+    },
+    {
+      "epoch": 1.7862232779097387,
+      "grad_norm": 0.17536883056163788,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6796,
+      "step": 47
+    },
+    {
+      "epoch": 1.8242280285035628,
+      "grad_norm": 0.1408592164516449,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4314,
+      "step": 48
+    },
+    {
+      "epoch": 1.8622327790973872,
+      "grad_norm": 0.1548309326171875,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4308,
+      "step": 49
+    },
+    {
+      "epoch": 1.9002375296912115,
+      "grad_norm": 0.16854378581047058,
+      "learning_rate": 1e-05,
+      "loss": 0.3758,
+      "step": 50
+    },
+    {
+      "epoch": 1.9002375296912115,
+      "eval_loss": 0.6436007022857666,
+      "eval_runtime": 1.8363,
+      "eval_samples_per_second": 27.229,
+      "eval_steps_per_second": 7.079,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null