Training in progress, step 29, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aae03a0ec90c705d6cc8bbf60cf90ba46644477b28340697e2ceb3c43aa30de2
+oid sha256:9e4fdb7067849a4c464668852c635bc461c590a24325a406d7d9fb1945ce921e
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06d314e6f5460b02fa97e6dbd816b17c781cbfcb4a96255a7a6280497f98fa3
+oid sha256:a4d24bf17d5ab97591019b37cb44f79afe3e47dfd02162862a8bda0860138074
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee72bea148b353b64b0e2c9cd3f4da7b5e20246177a123a02f22cd4b0cde72f
+oid sha256:614714b3e86980d626ed5bb91ec370b5c4c594311cc1a24f20a23f4bd23df084
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc83099c8b2d1424f7b0bc498524dfa56c0846e5540fa7d047be58cba370c80
+oid sha256:01468a262529a447c856ce160b15a9647a19c8d96a43698fdfc8e1ddc8447661
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4b9f5b19fc1f1f0df895da12b0b15e1214abe35770b300a2cee9db96b4a21ec
+oid sha256:d416fd5646fea1d436dfdb19b6e134890b1c9b3625ef41b6e8cc540bff208d80
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f1549e4a25f9ce1c7037fdc2d1e8de7bd1fb5a2957997e47faf382eb1478fb
+oid sha256:116635eab115b8ddfa54680c0f6d827b6ed844f1290ac05b52a40223acf16528
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c358afaa27e49311ba3af0bc45fb097f71b7e94dd7d620cdb9c2ef0a37a7463
+oid sha256:77b1cd5ec232ad7fc4a8bf29290c170002b5e29b256da7fe912039052d43ab0b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7201225757598877,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.709677419354839,
+  "epoch": 3.1870967741935483,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 29,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,34 @@
       "eval_samples_per_second": 22.319,
       "eval_steps_per_second": 3.09,
       "step": 25
+    },
+    {
+      "epoch": 2.8129032258064517,
+      "grad_norm": 1.8182753324508667,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7967,
+      "step": 26
+    },
+    {
+      "epoch": 2.9161290322580644,
+      "grad_norm": 1.4322144985198975,
+      "learning_rate": 1.3477564710088098e-06,
+      "loss": 0.7748,
+      "step": 27
+    },
+    {
+      "epoch": 3.0838709677419356,
+      "grad_norm": 3.2206716537475586,
+      "learning_rate": 3.380821129028489e-07,
+      "loss": 1.3338,
+      "step": 28
+    },
+    {
+      "epoch": 3.1870967741935483,
+      "grad_norm": 2.47102427482605,
+      "learning_rate": 0.0,
+      "loss": 0.8182,
+      "step": 29
     }
   ],
   "logging_steps": 1,
@@ -221,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.114626154561536e+17,
+  "total_flos": 1.2929663392913818e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null