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:e6e1342fffbbd4114b516b4a0da16484c5fd754f60a6365d88935e878290aaa4
+oid sha256:2b22fac208009ed59a39e051dce32bf48fea605b71be104fdab9c65dd6d1ee41
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6973bc56c66514b9d1a9924caf6e010e89379926cf2816ea1740f4ac87c06be9
+oid sha256:1515cf4457964a27f4e3ddef0f31d4b1de0337ec2ae7a1e1095197241bdb9939
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d45629cc89c6358361ba3ba84d12cfd0e050a34c2d50a2fba1ba9665e168eacb
+oid sha256:0b71293a5bb8c48f229f3f97f002cb89f7b21e92f1fdf3cb7189ad7ccf4e2629
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:500140dcc85aec0915c3c37c3544aa0878ce2fce454fea6cc812fcf1b02a1f4d
+oid sha256:f079cbabd2ef31714c480c8d20435fc96d4cce680c51bc2b1772583a720697de
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:651a291698af7bd2b6cebfcf071bf95ff5f48122fb2572f5fa7e7a5ca035e8c2
+oid sha256:84c62c19ae92a0e0e40c32df35362194724b8b81c53f6077c013059a043bf7de
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2a73452bf875885b9c8edaeab80cb1c350503482f1482b3d48f33e0c067152
+oid sha256:0b914b2c0423a6f66e481c72fcdf22c764eae4f39765423d905cf3d4d9192bf3
 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": 0.05299784243106842,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.16200891049007696,
+  "best_metric": 0.0015739009249955416,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3240178209801539,
   "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": 17.39,
       "eval_steps_per_second": 4.521,
       "step": 25
+    },
+    {
+      "epoch": 0.16848926690968002,
+      "grad_norm": 186.7551727294922,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 20.7695,
+      "step": 26
+    },
+    {
+      "epoch": 0.17496962332928312,
+      "grad_norm": 0.002963931765407324,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.1814499797488862,
+      "grad_norm": 0.0027682569343596697,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.18793033616848925,
+      "grad_norm": 0.0018720831722021103,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.19441069258809235,
+      "grad_norm": 0.0022603205870836973,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.20089104900769542,
+      "grad_norm": 0.0018970578676089644,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.2073714054272985,
+      "grad_norm": 0.0018754806369543076,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.21385176184690158,
+      "grad_norm": 0.005749805830419064,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.22033211826650465,
+      "grad_norm": 0.005470725707709789,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.22681247468610774,
+      "grad_norm": 0.04133632034063339,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0001,
+      "step": 35
+    },
+    {
+      "epoch": 0.2332928311057108,
+      "grad_norm": 0.014684452675282955,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0001,
+      "step": 36
+    },
+    {
+      "epoch": 0.2397731875253139,
+      "grad_norm": 0.00789859239012003,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.24625354394491697,
+      "grad_norm": 20.17969512939453,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7377,
+      "step": 38
+    },
+    {
+      "epoch": 0.25273390036452004,
+      "grad_norm": 18.82114028930664,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.2916,
+      "step": 39
+    },
+    {
+      "epoch": 0.25921425678412313,
+      "grad_norm": 0.0939214825630188,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0003,
+      "step": 40
+    },
+    {
+      "epoch": 0.2656946132037262,
+      "grad_norm": 0.010227395221590996,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0001,
+      "step": 41
+    },
+    {
+      "epoch": 0.27217496962332927,
+      "grad_norm": 0.0035552887711673975,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.27865532604293236,
+      "grad_norm": 0.5987063050270081,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0012,
+      "step": 43
+    },
+    {
+      "epoch": 0.28513568246253546,
+      "grad_norm": 0.001434679958038032,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.2916160388821385,
+      "grad_norm": 0.0024458535481244326,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.2980963953017416,
+      "grad_norm": 0.0011263227788731456,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.3045767517213447,
+      "grad_norm": 0.0018141833133995533,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.3110571081409477,
+      "grad_norm": 0.0025743048172444105,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.3175374645605508,
+      "grad_norm": 0.002356971614062786,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.3240178209801539,
+      "grad_norm": 0.015139484778046608,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3240178209801539,
+      "eval_loss": 0.0015739009249955416,
+      "eval_runtime": 2.8769,
+      "eval_samples_per_second": 17.38,
+      "eval_steps_per_second": 4.519,
+      "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": 2.936866703922954e+17,
+  "total_flos": 5.887878453138555e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null