Training in progress, step 163, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b23c3ed9ca3d367f819e5e0f976976bb29715d12f77fa36cfba3fd2762ee1e5a
+oid sha256:f18043fdd8c36ac71fdd58bde02479000547faeb16a8aa60df2df3061f7267aa
 size 113284112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a49d8e9467d8a819ee53f6d9a03675427ed30a69bb7eb5e261c6723ffb9ff15d
+oid sha256:0cf2b7d5f1432e60a03110a2e17c4d730a72fe828144d9475bede562ac06c4fd
 size 226735226

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1ec9fb851d792b3ae9928a38b2567f210c5b94d339efe990abf35259dbcb2e
+oid sha256:0bf343d44a04013b3ab623bb04d8748cf1fb1296f3a24c7edc32c421137ed54e
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf844ee36bd05503fd0e310aa60493ab65687b1b06ef091d72b007ed27e51cc
+oid sha256:71d733608e7147affc4bb257789d4d3ee6847974683a496b513031a205dfc8fe
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db00be51153759083358211ad6f93250d612f1c9e4b3b3ec9316cf4b3c92302
+oid sha256:fd00f90a0abf48d91437e86f937449b61287de4595369a15b076a69313313fb3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f6396d021957a0847ecc2baee755a89d2dcebe7d8a2ae38471a216faa3f28d
+oid sha256:308922c9791cf368d171ea9bfe4696c89d23a5f6ee2eb4c9f898354b111c66f8
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b780cd0b27f7b98fad14003d4e9569b153f787a5a1a687c28143f19bea8e8a3b
+oid sha256:d9584b990eb1d762133ca744b2d560c00d1b8e953f0c718d599b13b400bf125a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.625535011291504,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 3.7147806004618937,
+  "epoch": 4.041570438799076,
   "eval_steps": 25,
-  "global_step": 150,
+  "global_step": 163,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1113,6 +1113,97 @@
       "eval_samples_per_second": 76.899,
       "eval_steps_per_second": 19.994,
       "step": 150
+    },
+    {
+      "epoch": 3.7394149345650503,
+      "grad_norm": 1.3795236349105835,
+      "learning_rate": 1.1324461613022928e-05,
+      "loss": 0.5866,
+      "step": 151
+    },
+    {
+      "epoch": 3.7640492686682063,
+      "grad_norm": 1.1751108169555664,
+      "learning_rate": 1.1113793087267173e-05,
+      "loss": 2.1343,
+      "step": 152
+    },
+    {
+      "epoch": 3.7886836027713624,
+      "grad_norm": 1.213850736618042,
+      "learning_rate": 1.092115264363775e-05,
+      "loss": 2.0515,
+      "step": 153
+    },
+    {
+      "epoch": 3.813317936874519,
+      "grad_norm": 1.2193846702575684,
+      "learning_rate": 1.0746619417197435e-05,
+      "loss": 1.9269,
+      "step": 154
+    },
+    {
+      "epoch": 3.837952270977675,
+      "grad_norm": 1.266520619392395,
+      "learning_rate": 1.0590265104717518e-05,
+      "loss": 1.8284,
+      "step": 155
+    },
+    {
+      "epoch": 3.8625866050808315,
+      "grad_norm": 1.2946449518203735,
+      "learning_rate": 1.045215393522539e-05,
+      "loss": 1.6426,
+      "step": 156
+    },
+    {
+      "epoch": 3.8872209391839876,
+      "grad_norm": 1.5318657159805298,
+      "learning_rate": 1.0332342643619824e-05,
+      "loss": 1.7901,
+      "step": 157
+    },
+    {
+      "epoch": 3.911855273287144,
+      "grad_norm": 1.4870713949203491,
+      "learning_rate": 1.023088044736472e-05,
+      "loss": 1.6923,
+      "step": 158
+    },
+    {
+      "epoch": 3.9364896073903,
+      "grad_norm": 1.6788103580474854,
+      "learning_rate": 1.0147809026271016e-05,
+      "loss": 1.5306,
+      "step": 159
+    },
+    {
+      "epoch": 3.9611239414934563,
+      "grad_norm": 1.869388461112976,
+      "learning_rate": 1.0083162505374962e-05,
+      "loss": 1.43,
+      "step": 160
+    },
+    {
+      "epoch": 3.9857582755966128,
+      "grad_norm": 1.462508201599121,
+      "learning_rate": 1.0036967440919847e-05,
+      "loss": 0.7244,
+      "step": 161
+    },
+    {
+      "epoch": 4.01693610469592,
+      "grad_norm": 2.254340648651123,
+      "learning_rate": 1.0009242809446925e-05,
+      "loss": 3.4942,
+      "step": 162
+    },
+    {
+      "epoch": 4.041570438799076,
+      "grad_norm": 1.1474640369415283,
+      "learning_rate": 1e-05,
+      "loss": 1.8964,
+      "step": 163
     }
   ],
   "logging_steps": 1,
@@ -1136,12 +1227,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.331051303501824e+17,
+  "total_flos": 6.879742416471982e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null