Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2264533b0b1dae7ff4750f69a15e13ecf4118577f3a3084f7da4176f2256a904
+oid sha256:79ea3986d897987ed38b0d6473f07cb5a665218ef6897d9b774cfc416c6a5bab
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca0aa2fbc12fe1d4f24ee3071a4e9f3df3f984b9e422d26e9cb4ba18e9eebfe
+oid sha256:88e64e00697bd2bf5697cf23b5047c5b0b12b6520e5ea369fc39611df223934d
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6035b1803826af7c69ab2be3136ee65930daa8a717634b960bc087dd13821a1
+oid sha256:fc442fdef3c9e63101a8ef8aeb05f38ad69ac2e99caf60604e7bcba460da3c68
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16064a55dd17472906bad0b06c5ac77dc9b0e50894ec651a9d4f2af366a0df6c
+oid sha256:4f058deb7aa1285761b7b9743b279a18d9185f6f62bd784b7fb4987346fc9b9b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5847b909f3bd959e8499e05a7ea64a09102b0fd5ed10bb64f6dfebfb47de6b0
+oid sha256:d97e48a507da4c54419fcc797c7f84d781912998190cb7cf1cb02e6711547f40
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f15ebdf3fca3bf2ae91774b28cef12045aa87996c251bbd8673d3e7536bae1c
+oid sha256:caa4ea18ddc61231d90e9b924adea78ac0564ea1b618795b3f997482b7883e87
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
+oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.13392838835716248,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.05621332958577803,
+  "best_metric": 0.13140296936035156,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.08431999437866704,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 44.891,
       "eval_steps_per_second": 11.672,
       "step": 50
+    },
+    {
+      "epoch": 0.05733759617749359,
+      "grad_norm": 0.09779861569404602,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 0.1136,
+      "step": 51
+    },
+    {
+      "epoch": 0.05846186276920915,
+      "grad_norm": 0.12952782213687897,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 0.1409,
+      "step": 52
+    },
+    {
+      "epoch": 0.05958612936092471,
+      "grad_norm": 0.14181578159332275,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 0.1413,
+      "step": 53
+    },
+    {
+      "epoch": 0.06071039595264027,
+      "grad_norm": 0.1471935510635376,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 0.1423,
+      "step": 54
+    },
+    {
+      "epoch": 0.06183466254435583,
+      "grad_norm": 0.16710589826107025,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 0.1477,
+      "step": 55
+    },
+    {
+      "epoch": 0.06295892913607139,
+      "grad_norm": 0.1667054444551468,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 0.1463,
+      "step": 56
+    },
+    {
+      "epoch": 0.06408319572778695,
+      "grad_norm": 0.1824021190404892,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 0.1623,
+      "step": 57
+    },
+    {
+      "epoch": 0.06520746231950252,
+      "grad_norm": 0.18960590660572052,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 0.1452,
+      "step": 58
+    },
+    {
+      "epoch": 0.06633172891121807,
+      "grad_norm": 0.19344769418239594,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 0.1616,
+      "step": 59
+    },
+    {
+      "epoch": 0.06745599550293363,
+      "grad_norm": 0.17828473448753357,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 0.1266,
+      "step": 60
+    },
+    {
+      "epoch": 0.0685802620946492,
+      "grad_norm": 0.21599431335926056,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 0.1387,
+      "step": 61
+    },
+    {
+      "epoch": 0.06970452868636476,
+      "grad_norm": 0.2585263252258301,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.1556,
+      "step": 62
+    },
+    {
+      "epoch": 0.07082879527808031,
+      "grad_norm": 0.12306924909353256,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 0.1098,
+      "step": 63
+    },
+    {
+      "epoch": 0.07195306186979587,
+      "grad_norm": 0.11643731594085693,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 0.1332,
+      "step": 64
+    },
+    {
+      "epoch": 0.07307732846151144,
+      "grad_norm": 0.12227363139390945,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 0.1248,
+      "step": 65
+    },
+    {
+      "epoch": 0.074201595053227,
+      "grad_norm": 0.13636033236980438,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 0.1518,
+      "step": 66
+    },
+    {
+      "epoch": 0.07532586164494255,
+      "grad_norm": 0.14901277422904968,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 0.1477,
+      "step": 67
+    },
+    {
+      "epoch": 0.07645012823665812,
+      "grad_norm": 0.14018963277339935,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 0.1384,
+      "step": 68
+    },
+    {
+      "epoch": 0.07757439482837368,
+      "grad_norm": 0.14247332513332367,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 0.1249,
+      "step": 69
+    },
+    {
+      "epoch": 0.07869866142008924,
+      "grad_norm": 0.1646346151828766,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 0.1344,
+      "step": 70
+    },
+    {
+      "epoch": 0.0798229280118048,
+      "grad_norm": 0.17401055991649628,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 0.1621,
+      "step": 71
+    },
+    {
+      "epoch": 0.08094719460352036,
+      "grad_norm": 0.1905514895915985,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 0.1265,
+      "step": 72
+    },
+    {
+      "epoch": 0.08207146119523592,
+      "grad_norm": 0.20102576911449432,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 0.1469,
+      "step": 73
+    },
+    {
+      "epoch": 0.08319572778695149,
+      "grad_norm": 0.2370804399251938,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 0.1564,
+      "step": 74
+    },
+    {
+      "epoch": 0.08431999437866704,
+      "grad_norm": 0.38529258966445923,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 0.2007,
+      "step": 75
+    },
+    {
+      "epoch": 0.08431999437866704,
+      "eval_loss": 0.13140296936035156,
+      "eval_runtime": 1.1131,
+      "eval_samples_per_second": 44.918,
+      "eval_steps_per_second": 11.679,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.62480894509056e+17,
+  "total_flos": 2.43721341763584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null