Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:393672c05d97e48292de25d106425aec769935168094a4bf696c76548a10772d
+oid sha256:f598ddda68e75cf4198ed91171642fe735f348fcf64ab31991f73f0d58923ef6
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f67cd20266dbaa3228423dc95437e68bad97159e6dbc31f8f6aae57993552f1
+oid sha256:0ecca48181f2d51c84019ae377c869d10c46618da1245867c1dc5d98d138e588
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:161fa4e58a2969d511f4422e45abb4aee11fc0a3a2d3b811a0eaf7448d3b0982
+oid sha256:d8a49bdaeb6b0785dcb22400b51559a9174b1478a892b9878d8a0c70336f4ebe
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7c066e3e6bf72abf01b481619dea78a5af96b3171179fb9ddf2d062262e6d5
+oid sha256:f9ae77dd97726870e2cb101e743dd612182d9905431e97bf83813c58aec63a28
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6d426fb44b10413c1e3d03f16ef5e123e3a73be8cf29cbe79f73cd1b7f96f7
+oid sha256:de0c317459a35a0b61ceaff66631bed93f810628aea5d2b65b7ef5a45ab2f11f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc642729bbf489bb2051019cd58c5bb19ca531c945c8790034df8d4ad00596c3
+oid sha256:8ad3bb7e0ad8f81d1a27cd6c0397544b5c7f45ec3830a5a7c27fc5fe5aa8dc24
 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": 11.754655838012695,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3421727972626176,
+  "best_metric": 11.751782417297363,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6843455945252352,
   "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": 322.757,
       "eval_steps_per_second": 83.917,
       "step": 25
+    },
+    {
+      "epoch": 0.3558597091531223,
+      "grad_norm": 0.05924524366855621,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.7548,
+      "step": 26
+    },
+    {
+      "epoch": 0.369546621043627,
+      "grad_norm": 0.05890587717294693,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7555,
+      "step": 27
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "grad_norm": 0.06674748659133911,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7537,
+      "step": 28
+    },
+    {
+      "epoch": 0.39692044482463645,
+      "grad_norm": 0.07175412774085999,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7531,
+      "step": 29
+    },
+    {
+      "epoch": 0.41060735671514115,
+      "grad_norm": 0.06633391231298447,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.7543,
+      "step": 30
+    },
+    {
+      "epoch": 0.42429426860564584,
+      "grad_norm": 0.07412329316139221,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.7534,
+      "step": 31
+    },
+    {
+      "epoch": 0.43798118049615054,
+      "grad_norm": 0.0746646448969841,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.7522,
+      "step": 32
+    },
+    {
+      "epoch": 0.4516680923866553,
+      "grad_norm": 0.08164186775684357,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.753,
+      "step": 33
+    },
+    {
+      "epoch": 0.46535500427716,
+      "grad_norm": 0.07409690320491791,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.7537,
+      "step": 34
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 0.08160021901130676,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.7525,
+      "step": 35
+    },
+    {
+      "epoch": 0.49272882805816937,
+      "grad_norm": 0.08488988131284714,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7517,
+      "step": 36
+    },
+    {
+      "epoch": 0.5064157399486741,
+      "grad_norm": 0.08493369817733765,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.7517,
+      "step": 37
+    },
+    {
+      "epoch": 0.5201026518391788,
+      "grad_norm": 0.07511982321739197,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.7528,
+      "step": 38
+    },
+    {
+      "epoch": 0.5337895637296834,
+      "grad_norm": 0.0729658454656601,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.7517,
+      "step": 39
+    },
+    {
+      "epoch": 0.5474764756201882,
+      "grad_norm": 0.07437953352928162,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7529,
+      "step": 40
+    },
+    {
+      "epoch": 0.561163387510693,
+      "grad_norm": 0.07642436772584915,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.752,
+      "step": 41
+    },
+    {
+      "epoch": 0.5748502994011976,
+      "grad_norm": 0.07863420993089676,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7523,
+      "step": 42
+    },
+    {
+      "epoch": 0.5885372112917023,
+      "grad_norm": 0.0825684666633606,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.7516,
+      "step": 43
+    },
+    {
+      "epoch": 0.602224123182207,
+      "grad_norm": 0.07915514707565308,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.7509,
+      "step": 44
+    },
+    {
+      "epoch": 0.6159110350727117,
+      "grad_norm": 0.08031726628541946,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.7516,
+      "step": 45
+    },
+    {
+      "epoch": 0.6295979469632165,
+      "grad_norm": 0.08885470032691956,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.7515,
+      "step": 46
+    },
+    {
+      "epoch": 0.6432848588537211,
+      "grad_norm": 0.09006766974925995,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.753,
+      "step": 47
+    },
+    {
+      "epoch": 0.6569717707442259,
+      "grad_norm": 0.08606462180614471,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7509,
+      "step": 48
+    },
+    {
+      "epoch": 0.6706586826347305,
+      "grad_norm": 0.08612215518951416,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.7511,
+      "step": 49
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "grad_norm": 0.0875965803861618,
+      "learning_rate": 1e-05,
+      "loss": 11.7513,
+      "step": 50
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "eval_loss": 11.751782417297363,
+      "eval_runtime": 0.154,
+      "eval_samples_per_second": 324.69,
+      "eval_steps_per_second": 84.419,
+      "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": 81943068672000.0,
+  "total_flos": 163886137344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null