Training in progress, step 119, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae91c90ef75859027731c604bfc6ca06e3639e438452e4645294af700f2a8d66
+oid sha256:99344d15dd3670285c4341c9f5f6c4bf096b3cf81551e262d8f0b55512649533
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e289db4882b2c1c58bba99091d9639af2b498e6752146549dea6309c352f27f
+oid sha256:f45a70156c42effbabe1a04c759ac76c130021e61101c387055551e0f574f178
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf55cf1773a558357b021bc9146cb4e1b89ebbb77ff8ad46432024e900dad0a
+oid sha256:2c7376cb11d6367789d170f124b61c2fec883908127623afd8ff34624e8b46ae
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0c10982eb665343c8dba31f05c7d465d4c5194f456a3ed190ae86ac492fc1f
+oid sha256:c7608aefd0a07874121e96751a56d2178c6828644dce377c622c7e84992cb545
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a692f86f092a43efc7ce7159a66c7739c1d95cf353d47f3b3c45f53b1fb7e5bb
+oid sha256:ff5cac29dfc34981d35a51a3130a221b0dd59b5eb21dc54928b0ba787606ede6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25139db6ccdb6f09ac273ddd0f52eeb0b26e4f46607a386e43853be74b8493d
+oid sha256:a3162ff303999d7bd465e65a693c4f353476223147abf92d2e1a81f84beaf3ec
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb65275071074e7f8c415d4025dd63db767eccf1b1b13eb40847f779864aedd2
+oid sha256:ef75e921f866e994eb07f566eae5b88002af348a8ed338e0962d48b1c7d30dc1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.18359769880771637,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.09437300931933466,
+  "epoch": 0.11230388109000826,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 119,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -747,6 +747,139 @@
       "eval_samples_per_second": 50.2,
       "eval_steps_per_second": 13.052,
       "step": 100
+    },
+    {
+      "epoch": 0.09531673941252802,
+      "grad_norm": 0.5977703928947449,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 0.2196,
+      "step": 101
+    },
+    {
+      "epoch": 0.09626046950572137,
+      "grad_norm": 0.4760293960571289,
+      "learning_rate": 1.484855926217227e-05,
+      "loss": 0.1857,
+      "step": 102
+    },
+    {
+      "epoch": 0.09720419959891471,
+      "grad_norm": 0.2669781744480133,
+      "learning_rate": 1.4303927768609015e-05,
+      "loss": 0.1815,
+      "step": 103
+    },
+    {
+      "epoch": 0.09814792969210806,
+      "grad_norm": 0.18762975931167603,
+      "learning_rate": 1.3790200300522413e-05,
+      "loss": 0.1615,
+      "step": 104
+    },
+    {
+      "epoch": 0.0990916597853014,
+      "grad_norm": 0.22948940098285675,
+      "learning_rate": 1.330776697533392e-05,
+      "loss": 0.1608,
+      "step": 105
+    },
+    {
+      "epoch": 0.10003538987849475,
+      "grad_norm": 0.17586657404899597,
+      "learning_rate": 1.2856994146132542e-05,
+      "loss": 0.1506,
+      "step": 106
+    },
+    {
+      "epoch": 0.1009791199716881,
+      "grad_norm": 0.23077844083309174,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 0.162,
+      "step": 107
+    },
+    {
+      "epoch": 0.10192285006488144,
+      "grad_norm": 0.21372710168361664,
+      "learning_rate": 1.2051774915422163e-05,
+      "loss": 0.1605,
+      "step": 108
+    },
+    {
+      "epoch": 0.10286658015807479,
+      "grad_norm": 0.16886736452579498,
+      "learning_rate": 1.1697939986083733e-05,
+      "loss": 0.1506,
+      "step": 109
+    },
+    {
+      "epoch": 0.10381031025126813,
+      "grad_norm": 0.2670663595199585,
+      "learning_rate": 1.1376988032730134e-05,
+      "loss": 0.1698,
+      "step": 110
+    },
+    {
+      "epoch": 0.10475404034446148,
+      "grad_norm": 0.1998496651649475,
+      "learning_rate": 1.1089162781765398e-05,
+      "loss": 0.1691,
+      "step": 111
+    },
+    {
+      "epoch": 0.10569777043765483,
+      "grad_norm": 0.17204442620277405,
+      "learning_rate": 1.0834682803641197e-05,
+      "loss": 0.1822,
+      "step": 112
+    },
+    {
+      "epoch": 0.10664150053084817,
+      "grad_norm": 0.3721541464328766,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 0.2265,
+      "step": 113
+    },
+    {
+      "epoch": 0.10758523062404153,
+      "grad_norm": 0.5235680937767029,
+      "learning_rate": 1.0426506191312355e-05,
+      "loss": 0.1901,
+      "step": 114
+    },
+    {
+      "epoch": 0.10852896071723488,
+      "grad_norm": 0.312836229801178,
+      "learning_rate": 1.0273119520692275e-05,
+      "loss": 0.1713,
+      "step": 115
+    },
+    {
+      "epoch": 0.10947269081042822,
+      "grad_norm": 0.18158796429634094,
+      "learning_rate": 1.0153697814699859e-05,
+      "loss": 0.1683,
+      "step": 116
+    },
+    {
+      "epoch": 0.11041642090362157,
+      "grad_norm": 0.24202579259872437,
+      "learning_rate": 1.0068331760500774e-05,
+      "loss": 0.1639,
+      "step": 117
+    },
+    {
+      "epoch": 0.11136015099681491,
+      "grad_norm": 0.24022828042507172,
+      "learning_rate": 1.0017086183877188e-05,
+      "loss": 0.1677,
+      "step": 118
+    },
+    {
+      "epoch": 0.11230388109000826,
+      "grad_norm": 0.2230340838432312,
+      "learning_rate": 1e-05,
+      "loss": 0.1475,
+      "step": 119
     }
   ],
   "logging_steps": 1,
@@ -770,12 +903,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.1175706767654912e+18,
+  "total_flos": 1.3299091053509345e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null