Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ca28d4296e60bccfecb116ccb1a93dcd6b5d4195eaffc928b07ce02993ca6ae
+oid sha256:17215da0fb416ca0a7fb1982823ff08b1df84cf988584d5e61d06677cb087e4e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6421873091bbf7c43646db7e962cbc3a91b6b8ba0ba87d71b42699bb1d962ac9
+oid sha256:3655bd969e2ead6aed06a29bc28b3ead3045e4fdec1536fd035d35b726724cfa
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a77eef7c44e497cd4f32abd435af0732b83ba0fe4189c4d91fefcfcaaf7e5fd
+oid sha256:946bd0c1a8336ec46eb83cc9004be3fdeccabec922c7aac6b0802bbabedef386
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a7b52be3446c4a3c2a92ea6b4bed76dd6c0da57b7481ff211d852325b207f0
+oid sha256:6aaf0af3d47964457ebdde399d1c3e8dbfe2aa02cb17869da641b7f9e27357eb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b831edecc26da4c5965bfd227e746406a66a25873660e7fc1dbc68de812b042
+oid sha256:fac9a4b6001a5060d83234244dc9d3fdb974cce5f1c75a7e0a17ed77a3180076
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4e36d98fc104e2c4a44d9fa72fc5bcbbf576373659e5a99a3fe65d9c1584d9
+oid sha256:94159bbbaf679ba9efe3121c86ef2f8927f2371496a803a428faf5a14ea96695
 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": 0.5491692423820496,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.29336266960029334,
+  "best_metric": 0.42846938967704773,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5867253392005867,
   "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": 11.468,
       "eval_steps_per_second": 2.982,
       "step": 25
+    },
+    {
+      "epoch": 0.3050971763843051,
+      "grad_norm": 0.8793892860412598,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5375,
+      "step": 26
+    },
+    {
+      "epoch": 0.31683168316831684,
+      "grad_norm": 0.9343221187591553,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.6127,
+      "step": 27
+    },
+    {
+      "epoch": 0.32856618995232856,
+      "grad_norm": 0.7726524472236633,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5759,
+      "step": 28
+    },
+    {
+      "epoch": 0.3403006967363403,
+      "grad_norm": 0.8706146478652954,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.582,
+      "step": 29
+    },
+    {
+      "epoch": 0.35203520352035206,
+      "grad_norm": 0.8062698245048523,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5736,
+      "step": 30
+    },
+    {
+      "epoch": 0.3637697103043638,
+      "grad_norm": 0.7513149380683899,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5313,
+      "step": 31
+    },
+    {
+      "epoch": 0.3755042170883755,
+      "grad_norm": 0.935967743396759,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5571,
+      "step": 32
+    },
+    {
+      "epoch": 0.3872387238723872,
+      "grad_norm": 0.914279580116272,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5759,
+      "step": 33
+    },
+    {
+      "epoch": 0.39897323065639895,
+      "grad_norm": 1.027889609336853,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5879,
+      "step": 34
+    },
+    {
+      "epoch": 0.4107077374404107,
+      "grad_norm": 0.8476033806800842,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5156,
+      "step": 35
+    },
+    {
+      "epoch": 0.42244224422442245,
+      "grad_norm": 0.8978279829025269,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.5353,
+      "step": 36
+    },
+    {
+      "epoch": 0.43417675100843417,
+      "grad_norm": 0.9141674041748047,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6523,
+      "step": 37
+    },
+    {
+      "epoch": 0.4459112577924459,
+      "grad_norm": 0.44151484966278076,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3386,
+      "step": 38
+    },
+    {
+      "epoch": 0.45764576457645767,
+      "grad_norm": 0.5754418969154358,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4796,
+      "step": 39
+    },
+    {
+      "epoch": 0.4693802713604694,
+      "grad_norm": 0.6796362400054932,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4847,
+      "step": 40
+    },
+    {
+      "epoch": 0.4811147781444811,
+      "grad_norm": 0.662044107913971,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4703,
+      "step": 41
+    },
+    {
+      "epoch": 0.49284928492849284,
+      "grad_norm": 0.6517719626426697,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4554,
+      "step": 42
+    },
+    {
+      "epoch": 0.5045837917125046,
+      "grad_norm": 0.5648079514503479,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.434,
+      "step": 43
+    },
+    {
+      "epoch": 0.5163182984965163,
+      "grad_norm": 0.6545281410217285,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5286,
+      "step": 44
+    },
+    {
+      "epoch": 0.528052805280528,
+      "grad_norm": 0.7004388570785522,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.5022,
+      "step": 45
+    },
+    {
+      "epoch": 0.5397873120645398,
+      "grad_norm": 0.7332057952880859,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4996,
+      "step": 46
+    },
+    {
+      "epoch": 0.5515218188485516,
+      "grad_norm": 0.820666491985321,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.5126,
+      "step": 47
+    },
+    {
+      "epoch": 0.5632563256325632,
+      "grad_norm": 0.9013704061508179,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.5177,
+      "step": 48
+    },
+    {
+      "epoch": 0.574990832416575,
+      "grad_norm": 0.9810267090797424,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.4946,
+      "step": 49
+    },
+    {
+      "epoch": 0.5867253392005867,
+      "grad_norm": 1.5016697645187378,
+      "learning_rate": 1e-05,
+      "loss": 0.7266,
+      "step": 50
+    },
+    {
+      "epoch": 0.5867253392005867,
+      "eval_loss": 0.42846938967704773,
+      "eval_runtime": 4.3628,
+      "eval_samples_per_second": 11.461,
+      "eval_steps_per_second": 2.98,
+      "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": 1,
   "trial_name": null,
   "trial_params": null