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:db815cdfa495949b111171dbf7390c7fa364e1fa431279b9ef6f75eaee666908
+oid sha256:d2cb4b4c08742143b49b391afed06d9e842e3901bb64d7013f1c4010f41c7aeb
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb6423abf49eb6740136a49b951d9095d9757bb286c10144d7a2a4e9b52465a8
+oid sha256:9ee9a12eb3f16c3532f555fb0d81e506f1f1c5b3ce56183b94f132041bfe6fa9
 size 100824826

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee1b014a37ac7431018f1946eeac05a32ea5b0cad897818c96c09ce063f4092
+oid sha256:55dad3ee06ed78f02d25744060f24f12df0c2d54ff658f8f557d0a7c7a266141
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d0655ca8c022a330d2150c9d8ddf77f4f167f98b84e4253b127e5a024c5f8a7
+oid sha256:76e3df845a0f90d0f4d821d241318dd9a125c7b27ce63887a47524548ea913c2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b401328b93594069dac02bf716af4218b66619f107a943606440319be707f9
+oid sha256:5fc8dbac4bebd32e040762dcf4a3b4184646065ce86692ee26e4dab969a9c167
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff7330460854f0b24082b62ea45a3ca73a5044c4c80d5bcdade44caabce1e110
+oid sha256:06a1856edfdc77577a74cf88e7f0d96e3874f74c320352173e3f93937fa7106a
 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": 1.498545527458191,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.21668472372697725,
+  "best_metric": 1.4524505138397217,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4333694474539545,
   "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": 28.955,
       "eval_steps_per_second": 7.528,
       "step": 25
+    },
+    {
+      "epoch": 0.22535211267605634,
+      "grad_norm": 32.12018966674805,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 50.9971,
+      "step": 26
+    },
+    {
+      "epoch": 0.23401950162513543,
+      "grad_norm": 38.02103805541992,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 50.2586,
+      "step": 27
+    },
+    {
+      "epoch": 0.24268689057421453,
+      "grad_norm": 32.75697708129883,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 50.45,
+      "step": 28
+    },
+    {
+      "epoch": 0.2513542795232936,
+      "grad_norm": 18.196666717529297,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 51.8491,
+      "step": 29
+    },
+    {
+      "epoch": 0.2600216684723727,
+      "grad_norm": 16.83131217956543,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 59.5798,
+      "step": 30
+    },
+    {
+      "epoch": 0.26868905742145177,
+      "grad_norm": 20.428844451904297,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 63.1483,
+      "step": 31
+    },
+    {
+      "epoch": 0.27735644637053086,
+      "grad_norm": 26.761188507080078,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 68.5665,
+      "step": 32
+    },
+    {
+      "epoch": 0.28602383531960995,
+      "grad_norm": 28.98684310913086,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 60.8287,
+      "step": 33
+    },
+    {
+      "epoch": 0.29469122426868904,
+      "grad_norm": 28.409412384033203,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 53.0851,
+      "step": 34
+    },
+    {
+      "epoch": 0.30335861321776814,
+      "grad_norm": 22.734962463378906,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 53.2058,
+      "step": 35
+    },
+    {
+      "epoch": 0.3120260021668472,
+      "grad_norm": 23.15952491760254,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 38.0991,
+      "step": 36
+    },
+    {
+      "epoch": 0.3206933911159263,
+      "grad_norm": 22.231393814086914,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 33.401,
+      "step": 37
+    },
+    {
+      "epoch": 0.3293607800650054,
+      "grad_norm": 25.417402267456055,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 33.4547,
+      "step": 38
+    },
+    {
+      "epoch": 0.3380281690140845,
+      "grad_norm": 14.123833656311035,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 49.6472,
+      "step": 39
+    },
+    {
+      "epoch": 0.3466955579631636,
+      "grad_norm": 12.762784957885742,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 50.7568,
+      "step": 40
+    },
+    {
+      "epoch": 0.3553629469122427,
+      "grad_norm": 12.12992000579834,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 49.1412,
+      "step": 41
+    },
+    {
+      "epoch": 0.3640303358613218,
+      "grad_norm": 11.25378131866455,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 55.4105,
+      "step": 42
+    },
+    {
+      "epoch": 0.37269772481040087,
+      "grad_norm": 11.424920082092285,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 57.2247,
+      "step": 43
+    },
+    {
+      "epoch": 0.38136511375947996,
+      "grad_norm": 11.259847640991211,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 60.8376,
+      "step": 44
+    },
+    {
+      "epoch": 0.39003250270855905,
+      "grad_norm": 11.650426864624023,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 60.549,
+      "step": 45
+    },
+    {
+      "epoch": 0.39869989165763814,
+      "grad_norm": 12.492819786071777,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 58.7039,
+      "step": 46
+    },
+    {
+      "epoch": 0.40736728060671723,
+      "grad_norm": 13.810831069946289,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 53.8405,
+      "step": 47
+    },
+    {
+      "epoch": 0.4160346695557963,
+      "grad_norm": 15.549020767211914,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 46.2514,
+      "step": 48
+    },
+    {
+      "epoch": 0.4247020585048754,
+      "grad_norm": 20.43636703491211,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 29.5193,
+      "step": 49
+    },
+    {
+      "epoch": 0.4333694474539545,
+      "grad_norm": 34.72649383544922,
+      "learning_rate": 1e-05,
+      "loss": 25.3959,
+      "step": 50
+    },
+    {
+      "epoch": 0.4333694474539545,
+      "eval_loss": 1.4524505138397217,
+      "eval_runtime": 1.7327,
+      "eval_samples_per_second": 28.856,
+      "eval_steps_per_second": 7.503,
+      "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": 1.2405446367248384e+16,
+  "total_flos": 2.482250105801933e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null