Training in progress, step 119, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2161b68ccac46e6adcd39ba08b77a3f91e0f2d1d756864d956937a8c5a8b4da8
+oid sha256:e18428ad05cb4e6c1b584c058e2fe14da0c9e36dd875f9be9df4c20094727584
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b8ce07d2a26cfd741e33d4f6cba3520b2e9931ec74e73202768eb8eab525c03
+oid sha256:801b16c9421594dade7766d149e9314adb312c94db62033937687ed3a8bf4de2
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05eabad5d38bd773f86e444a7e0ad02897d6a6f894ea79a1e09dc6681d7675a
+oid sha256:d4b765b05d3c53e16a9d2d02ec93a05005c1486765b1f6eebc4e14ba587d1870
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab04f831dc42a73b689ad827233bb992b90cde844689cfc48c5f5c480364d1a
+oid sha256:c60ebc4332412fbe392efb0482c16dbb3e31176bd7b2c64af371d9fe15a93e19
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd9fc477f33ded6549ad4af59b4ff8a5b9d1b72a63718aa33c37c0bd747f03a
+oid sha256:9875d5ce88db2ca80c244cdf4f526dc596d572f6e9ae1e7d390c8b845fef5468
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b005e28f81720d7af39998e1c738c455b03a1a40d3b8af1f0f1f7b251d2cd50
+oid sha256:14edcf96bcbc38162e4db8b93a1c2620863f043c99df62f734efd4663e4b759e
 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": 0.8136073350906372,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 1.5775203352230713,
+  "epoch": 1.8772491989154547,
   "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": 50.43,
       "eval_steps_per_second": 13.112,
       "step": 100
+    },
+    {
+      "epoch": 1.593295538575302,
+      "grad_norm": 0.23437979817390442,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 0.8343,
+      "step": 101
+    },
+    {
+      "epoch": 1.6090707419275327,
+      "grad_norm": 0.23647752404212952,
+      "learning_rate": 1.484855926217227e-05,
+      "loss": 0.9165,
+      "step": 102
+    },
+    {
+      "epoch": 1.6248459452797634,
+      "grad_norm": 0.18379107117652893,
+      "learning_rate": 1.4303927768609015e-05,
+      "loss": 0.8544,
+      "step": 103
+    },
+    {
+      "epoch": 1.6406211486319942,
+      "grad_norm": 0.18732428550720215,
+      "learning_rate": 1.3790200300522413e-05,
+      "loss": 0.875,
+      "step": 104
+    },
+    {
+      "epoch": 1.6563963519842249,
+      "grad_norm": 0.16876737773418427,
+      "learning_rate": 1.330776697533392e-05,
+      "loss": 0.8525,
+      "step": 105
+    },
+    {
+      "epoch": 1.6721715553364556,
+      "grad_norm": 0.1615445613861084,
+      "learning_rate": 1.2856994146132542e-05,
+      "loss": 0.8207,
+      "step": 106
+    },
+    {
+      "epoch": 1.6879467586886863,
+      "grad_norm": 0.17801810801029205,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 0.8531,
+      "step": 107
+    },
+    {
+      "epoch": 1.703721962040917,
+      "grad_norm": 0.18149054050445557,
+      "learning_rate": 1.2051774915422163e-05,
+      "loss": 0.9099,
+      "step": 108
+    },
+    {
+      "epoch": 1.7194971653931477,
+      "grad_norm": 0.1865503042936325,
+      "learning_rate": 1.1697939986083733e-05,
+      "loss": 0.8604,
+      "step": 109
+    },
+    {
+      "epoch": 1.7352723687453784,
+      "grad_norm": 0.18773400783538818,
+      "learning_rate": 1.1376988032730134e-05,
+      "loss": 0.8526,
+      "step": 110
+    },
+    {
+      "epoch": 1.751047572097609,
+      "grad_norm": 0.19192053377628326,
+      "learning_rate": 1.1089162781765398e-05,
+      "loss": 0.833,
+      "step": 111
+    },
+    {
+      "epoch": 1.7668227754498398,
+      "grad_norm": 0.23631104826927185,
+      "learning_rate": 1.0834682803641197e-05,
+      "loss": 0.8052,
+      "step": 112
+    },
+    {
+      "epoch": 1.7825979788020705,
+      "grad_norm": 0.22724592685699463,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 0.804,
+      "step": 113
+    },
+    {
+      "epoch": 1.7983731821543012,
+      "grad_norm": 0.1648131012916565,
+      "learning_rate": 1.0426506191312355e-05,
+      "loss": 0.8892,
+      "step": 114
+    },
+    {
+      "epoch": 1.814148385506532,
+      "grad_norm": 0.19587408006191254,
+      "learning_rate": 1.0273119520692275e-05,
+      "loss": 0.8797,
+      "step": 115
+    },
+    {
+      "epoch": 1.8299235888587626,
+      "grad_norm": 0.20268595218658447,
+      "learning_rate": 1.0153697814699859e-05,
+      "loss": 0.8665,
+      "step": 116
+    },
+    {
+      "epoch": 1.8456987922109933,
+      "grad_norm": 0.2090834677219391,
+      "learning_rate": 1.0068331760500774e-05,
+      "loss": 0.8841,
+      "step": 117
+    },
+    {
+      "epoch": 1.861473995563224,
+      "grad_norm": 0.18287914991378784,
+      "learning_rate": 1.0017086183877188e-05,
+      "loss": 0.8637,
+      "step": 118
+    },
+    {
+      "epoch": 1.8772491989154547,
+      "grad_norm": 0.18256083130836487,
+      "learning_rate": 1e-05,
+      "loss": 0.8543,
+      "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