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:bd299ebe9ecb4819d53f9c783c3d5f130a61dbb42d40996e49df93f1bd23be07
+oid sha256:3b52a8c6e5caa880cd27aab2a8b47dacf3c7cb9eb3aa3597d57f3503a5879ae8
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd772bb66647cfb45540e77f1d1587867228e2f17373df481b667aabc734dbcb
+oid sha256:c3513b069bf366eba85ff5e7ffd0bd160cf31d07fe8502b10dd12e7e7e0f583b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3494ed3420a176d38a0dddaa06e5ea2d0ebd0bc45b44b29f87560e179045387d
+oid sha256:9db2cf49156e469fcfecaece32419d55a7139b0ad8093bc4ff272d30d4bfe095
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f838c88c67e5fdcedc222cc20491d09c73b3f2a634db9ba86548891a8289027f
+oid sha256:61df941dbc7885bba6ab4194c73b47d1653a40cb52e7cc88ca3e50328aca7832
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bef276cc2d2385d701eabc7ed08bb81aa0f0f573c7abace9aa8fb278238440d
+oid sha256:3849f9fc859644281cdda0acef3b462add010b95b2d3368af0fa6eae6478dfcb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b0dd70e90473f5fac7075d829e9fbc6ffbf670a367fccad8c4c6df7197e1a66
+oid sha256:528d63aaee84528c2428b9ff24f5039d256cb8d3d48286c99ba0dfd11b187d88
 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": 0.6450268030166626,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.20212228398180898,
+  "best_metric": 0.6268936991691589,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.40424456796361796,
   "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": 14.335,
       "eval_steps_per_second": 3.727,
       "step": 25
+    },
+    {
+      "epoch": 0.21020717534108135,
+      "grad_norm": 0.5683823823928833,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7581,
+      "step": 26
+    },
+    {
+      "epoch": 0.21829206670035373,
+      "grad_norm": 0.5637506246566772,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.7071,
+      "step": 27
+    },
+    {
+      "epoch": 0.22637695805962607,
+      "grad_norm": 0.44266441464424133,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7379,
+      "step": 28
+    },
+    {
+      "epoch": 0.23446184941889844,
+      "grad_norm": 0.3773636519908905,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7573,
+      "step": 29
+    },
+    {
+      "epoch": 0.2425467407781708,
+      "grad_norm": 0.3675413131713867,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6714,
+      "step": 30
+    },
+    {
+      "epoch": 0.25063163213744316,
+      "grad_norm": 0.37877586483955383,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7193,
+      "step": 31
+    },
+    {
+      "epoch": 0.25871652349671553,
+      "grad_norm": 0.41423583030700684,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.6975,
+      "step": 32
+    },
+    {
+      "epoch": 0.26680141485598785,
+      "grad_norm": 0.4509444832801819,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.7055,
+      "step": 33
+    },
+    {
+      "epoch": 0.2748863062152602,
+      "grad_norm": 0.4025251567363739,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.6764,
+      "step": 34
+    },
+    {
+      "epoch": 0.2829711975745326,
+      "grad_norm": 0.4443969428539276,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.6929,
+      "step": 35
+    },
+    {
+      "epoch": 0.29105608893380497,
+      "grad_norm": 0.4087773859500885,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.6093,
+      "step": 36
+    },
+    {
+      "epoch": 0.2991409802930773,
+      "grad_norm": 0.40454772114753723,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6058,
+      "step": 37
+    },
+    {
+      "epoch": 0.30722587165234966,
+      "grad_norm": 0.34317758679389954,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5982,
+      "step": 38
+    },
+    {
+      "epoch": 0.31531076301162203,
+      "grad_norm": 0.3430269658565521,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.6715,
+      "step": 39
+    },
+    {
+      "epoch": 0.3233956543708944,
+      "grad_norm": 0.3907616138458252,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6747,
+      "step": 40
+    },
+    {
+      "epoch": 0.3314805457301668,
+      "grad_norm": 0.35974612832069397,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6912,
+      "step": 41
+    },
+    {
+      "epoch": 0.3395654370894391,
+      "grad_norm": 0.47870934009552,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.7493,
+      "step": 42
+    },
+    {
+      "epoch": 0.34765032844871147,
+      "grad_norm": 0.4124900698661804,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6813,
+      "step": 43
+    },
+    {
+      "epoch": 0.35573521980798384,
+      "grad_norm": 0.3971357047557831,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.7382,
+      "step": 44
+    },
+    {
+      "epoch": 0.3638201111672562,
+      "grad_norm": 0.4053785800933838,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6815,
+      "step": 45
+    },
+    {
+      "epoch": 0.3719050025265285,
+      "grad_norm": 0.42002072930336,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6561,
+      "step": 46
+    },
+    {
+      "epoch": 0.3799898938858009,
+      "grad_norm": 0.4654466211795807,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6316,
+      "step": 47
+    },
+    {
+      "epoch": 0.3880747852450733,
+      "grad_norm": 0.4234202802181244,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.6168,
+      "step": 48
+    },
+    {
+      "epoch": 0.39615967660434565,
+      "grad_norm": 0.49169376492500305,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.5986,
+      "step": 49
+    },
+    {
+      "epoch": 0.40424456796361796,
+      "grad_norm": 0.5422549843788147,
+      "learning_rate": 1e-05,
+      "loss": 0.5929,
+      "step": 50
+    },
+    {
+      "epoch": 0.40424456796361796,
+      "eval_loss": 0.6268936991691589,
+      "eval_runtime": 3.4738,
+      "eval_samples_per_second": 14.393,
+      "eval_steps_per_second": 3.742,
+      "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