Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6170acef45e873dcdb306e056937ad5ca40be354767d8a1073e4e25fdd6b3724
+oid sha256:22f79343d41daf61d1684c03532c2ec96a1b395b6de7996aba38a584ce551853
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8908b12ec3011c1417670cf495c55f8053ebbe689ef188ca79f5940ce30b5d
+oid sha256:3a18642765975c0f713967e429dfaed8c1c04a4f2d63fae121eed714251707cf
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2758a5ce23f879b123515ced84fd0dd826fcfb5c4411b012a59d7cfacddf9f61
+oid sha256:0f269d14dfca53f0f0747d1b3be3e67f857f0e2db19ca65df6ae2eb7e922f69d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ff27ccab7418414bd7d2ef161db2c34b765cc7991ea6c39e16cffa0ce1bd79
+oid sha256:da361ec952eb30ca1530acf7c88257283efeb271459c0b11640357d474683de4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e93a4c28667c9bbcff094b5f659dcd2a7ed35e6dc126d6679e1e1e8f7e209d1c
+oid sha256:c0df284e60d332bbc2cda22f75eee7d9773d8930981b09b7f0cb85a9e8733287
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2df08819056231801e95f0e0b01fcc658e03bd1d1b294aef9b30de19aef71a
+oid sha256:305f4fcb4218706ff4c9b229e9bd9b44bd9c286df6dd089ae518e050fa76ecc3
 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": 11.040526390075684,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.051759834368530024,
+  "best_metric": 11.014021873474121,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10351966873706005,
   "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": 481.058,
       "eval_steps_per_second": 125.075,
       "step": 25
+    },
+    {
+      "epoch": 0.053830227743271224,
+      "grad_norm": 6.273050785064697,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 176.543,
+      "step": 26
+    },
+    {
+      "epoch": 0.055900621118012424,
+      "grad_norm": 4.564478874206543,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 176.7715,
+      "step": 27
+    },
+    {
+      "epoch": 0.057971014492753624,
+      "grad_norm": 4.060601234436035,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 176.7596,
+      "step": 28
+    },
+    {
+      "epoch": 0.060041407867494824,
+      "grad_norm": 4.104419231414795,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 176.7908,
+      "step": 29
+    },
+    {
+      "epoch": 0.062111801242236024,
+      "grad_norm": 4.079372406005859,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 176.8614,
+      "step": 30
+    },
+    {
+      "epoch": 0.06418219461697723,
+      "grad_norm": 3.9627532958984375,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 176.7196,
+      "step": 31
+    },
+    {
+      "epoch": 0.06625258799171843,
+      "grad_norm": 4.171489238739014,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 176.7438,
+      "step": 32
+    },
+    {
+      "epoch": 0.06832298136645963,
+      "grad_norm": 4.367033958435059,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 176.5595,
+      "step": 33
+    },
+    {
+      "epoch": 0.07039337474120083,
+      "grad_norm": 4.644000053405762,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 176.4825,
+      "step": 34
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 4.799984455108643,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 176.5039,
+      "step": 35
+    },
+    {
+      "epoch": 0.07453416149068323,
+      "grad_norm": 5.801799297332764,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 176.2772,
+      "step": 36
+    },
+    {
+      "epoch": 0.07660455486542443,
+      "grad_norm": 6.784635543823242,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 176.0369,
+      "step": 37
+    },
+    {
+      "epoch": 0.07867494824016563,
+      "grad_norm": 7.3659515380859375,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 175.6978,
+      "step": 38
+    },
+    {
+      "epoch": 0.08074534161490683,
+      "grad_norm": 6.215569972991943,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 176.2542,
+      "step": 39
+    },
+    {
+      "epoch": 0.08281573498964803,
+      "grad_norm": 4.460636615753174,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 176.5287,
+      "step": 40
+    },
+    {
+      "epoch": 0.08488612836438923,
+      "grad_norm": 4.100980281829834,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 176.6485,
+      "step": 41
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 4.223078727722168,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 176.5936,
+      "step": 42
+    },
+    {
+      "epoch": 0.08902691511387163,
+      "grad_norm": 4.136197090148926,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 176.5854,
+      "step": 43
+    },
+    {
+      "epoch": 0.09109730848861283,
+      "grad_norm": 4.319904804229736,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 176.4969,
+      "step": 44
+    },
+    {
+      "epoch": 0.09316770186335403,
+      "grad_norm": 4.2462158203125,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 176.4756,
+      "step": 45
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 4.513911247253418,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 176.411,
+      "step": 46
+    },
+    {
+      "epoch": 0.09730848861283643,
+      "grad_norm": 4.598360538482666,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 176.2859,
+      "step": 47
+    },
+    {
+      "epoch": 0.09937888198757763,
+      "grad_norm": 5.463926792144775,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 176.1009,
+      "step": 48
+    },
+    {
+      "epoch": 0.10144927536231885,
+      "grad_norm": 5.886993408203125,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 175.9742,
+      "step": 49
+    },
+    {
+      "epoch": 0.10351966873706005,
+      "grad_norm": 8.994738578796387,
+      "learning_rate": 1e-05,
+      "loss": 175.2022,
+      "step": 50
+    },
+    {
+      "epoch": 0.10351966873706005,
+      "eval_loss": 11.014021873474121,
+      "eval_runtime": 0.1074,
+      "eval_samples_per_second": 465.736,
+      "eval_steps_per_second": 121.091,
+      "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": 19055561932800.0,
+  "total_flos": 38111123865600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null