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:e6c73bd97c5614b53e14c1bb45380c347fb773eddb3bb16e495af8c152b2ece2
+oid sha256:b40c957b5adf13ea97bbb88af01dfa4f8a80628d491c98fc4a676ee88d910b49
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c3f8306250475625099a070027b969dde72240e69834348a76b832ff93c3736
+oid sha256:1285ce239fc151433f057e158f5fa7e36b0ebaacfae7e710948f979cbcc1e3e2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871060961d8e9692ebdc235c06d32b2923a9bedbbe64bf44789ae70a358ccc70
+oid sha256:1a90a1f3d62f986f91122b0aca3a3d97977515718d4b6eabc4df2760f8d0661a
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac18cb6ddd928568724612710ea71cede3e2db7106bdbef50a0de354bb8ce34
+oid sha256:4ee043967ce601e764db7db585c232b51a34ef9fb2bcba289fd3ad942e16f6cd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7134d670f24bdeca93f45c19965da17bf370a337e1e469b291ee835edbd1b0a7
+oid sha256:48c4b74dff5c670769f67b3f447d4f10e63365e7bd712ff5ae56e0d0bc89d631
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b745d0826d7e2b483b577dd456792929a0659ddb6a97e1ac8ea1b09d481ac6
+oid sha256:861ea9cd6eafda2ebbcd31278283cff2fd37eccbdc8463fcab2b45c6c4762cd0
 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": 0.7934057116508484,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.030797659377887282,
+  "best_metric": 0.6850450038909912,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.061595318755774564,
   "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": 14.205,
       "eval_steps_per_second": 3.693,
       "step": 25
+    },
+    {
+      "epoch": 0.032029565753002774,
+      "grad_norm": 1.4556480646133423,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8112,
+      "step": 26
+    },
+    {
+      "epoch": 0.033261472128118266,
+      "grad_norm": 1.612951636314392,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.7809,
+      "step": 27
+    },
+    {
+      "epoch": 0.03449337850323375,
+      "grad_norm": 1.323860764503479,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7672,
+      "step": 28
+    },
+    {
+      "epoch": 0.035725284878349244,
+      "grad_norm": 1.0248310565948486,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7685,
+      "step": 29
+    },
+    {
+      "epoch": 0.036957191253464736,
+      "grad_norm": 0.8862748742103577,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.7488,
+      "step": 30
+    },
+    {
+      "epoch": 0.03818909762858023,
+      "grad_norm": 0.9572337865829468,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7286,
+      "step": 31
+    },
+    {
+      "epoch": 0.03942100400369572,
+      "grad_norm": 0.8555094003677368,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.6902,
+      "step": 32
+    },
+    {
+      "epoch": 0.04065291037881121,
+      "grad_norm": 0.8972882032394409,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.7359,
+      "step": 33
+    },
+    {
+      "epoch": 0.041884816753926704,
+      "grad_norm": 0.848060131072998,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.7489,
+      "step": 34
+    },
+    {
+      "epoch": 0.043116723129042196,
+      "grad_norm": 0.8404566645622253,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.7202,
+      "step": 35
+    },
+    {
+      "epoch": 0.04434862950415768,
+      "grad_norm": 0.920179545879364,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.7751,
+      "step": 36
+    },
+    {
+      "epoch": 0.045580535879273174,
+      "grad_norm": 1.0430974960327148,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8446,
+      "step": 37
+    },
+    {
+      "epoch": 0.046812442254388666,
+      "grad_norm": 0.8427203893661499,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.79,
+      "step": 38
+    },
+    {
+      "epoch": 0.04804434862950416,
+      "grad_norm": 0.8341359496116638,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6782,
+      "step": 39
+    },
+    {
+      "epoch": 0.04927625500461965,
+      "grad_norm": 0.8260400295257568,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6713,
+      "step": 40
+    },
+    {
+      "epoch": 0.05050816137973514,
+      "grad_norm": 0.8403255939483643,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6926,
+      "step": 41
+    },
+    {
+      "epoch": 0.051740067754850634,
+      "grad_norm": 0.7738561034202576,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6656,
+      "step": 42
+    },
+    {
+      "epoch": 0.05297197412996612,
+      "grad_norm": 0.770875096321106,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.7192,
+      "step": 43
+    },
+    {
+      "epoch": 0.05420388050508161,
+      "grad_norm": 0.7651665806770325,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.7163,
+      "step": 44
+    },
+    {
+      "epoch": 0.055435786880197103,
+      "grad_norm": 0.7298194169998169,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6863,
+      "step": 45
+    },
+    {
+      "epoch": 0.056667693255312596,
+      "grad_norm": 0.8660922050476074,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.7219,
+      "step": 46
+    },
+    {
+      "epoch": 0.05789959963042809,
+      "grad_norm": 0.7966043949127197,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6923,
+      "step": 47
+    },
+    {
+      "epoch": 0.05913150600554358,
+      "grad_norm": 0.9422286152839661,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.7498,
+      "step": 48
+    },
+    {
+      "epoch": 0.06036341238065907,
+      "grad_norm": 0.9889546036720276,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.7543,
+      "step": 49
+    },
+    {
+      "epoch": 0.061595318755774564,
+      "grad_norm": 1.1552159786224365,
+      "learning_rate": 1e-05,
+      "loss": 0.8377,
+      "step": 50
+    },
+    {
+      "epoch": 0.061595318755774564,
+      "eval_loss": 0.6850450038909912,
+      "eval_runtime": 3.5123,
+      "eval_samples_per_second": 14.236,
+      "eval_steps_per_second": 3.701,
+      "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": 2,
   "trial_name": null,
   "trial_params": null