Training in progress, step 29, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:410121c8e601ef0a99ea5d8f461f7f2794cdfda06b9d212796ffa3a837d10179
+oid sha256:ae7b75a6bf3720146e20c25f9dc557cdbc6da10f534e688afe4a7792b059c0db
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dced737a4509d1b110c3b41ffbcc4f87aee1ad0f25d431a473a6f1e287444d3f
+oid sha256:ab63345dd6a56c870036e412d931593969c65b7011c6e921a4648cb6744564a0
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d859345bfee055a9d8661c2efc906250fcf70268778286a7225556cae64e829c
+oid sha256:9d18cde0e28e0d89f8554694b3e71e560b0d9922151a18bfde6c8505592ac469
 size 15024

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": 0.719613790512085,
   "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": 50.145,
       "eval_steps_per_second": 6.943,
       "step": 25
+    },
+    {
+      "epoch": 2.8129032258064517,
+      "grad_norm": 1.9881534576416016,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7991,
+      "step": 26
+    },
+    {
+      "epoch": 2.9161290322580644,
+      "grad_norm": 1.4184935092926025,
+      "learning_rate": 1.3477564710088098e-06,
+      "loss": 0.7739,
+      "step": 27
+    },
+    {
+      "epoch": 3.0838709677419356,
+      "grad_norm": 3.0023298263549805,
+      "learning_rate": 3.380821129028489e-07,
+      "loss": 1.3348,
+      "step": 28
+    },
+    {
+      "epoch": 3.1870967741935483,
+      "grad_norm": 2.5828163623809814,
+      "learning_rate": 0.0,
+      "loss": 0.8249,
+      "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