Training in progress, step 41, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd04adbe77dbe6813a12ca97b409c519b77706d3aa433abf879a8dc935fdf9b4
+oid sha256:51a529649c6832f78e94eced0b32832256eb166bcbf5032c92c9259d62f3fb3f
 size 578923560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:100c2de73484443c011643029f2f87e283c59fc2676e75c2a282e0b542996c65
+oid sha256:22ac5f61d50ed11d9329ad64f7bd427c1a0db3f768adcaaa9d9b00b90f0830f9
 size 1158239442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3150de4bed3de95ed28cf01f9d24095bf2894a8a78049d9ed8076b91c124367
+oid sha256:515f56214e49d8a27320c334fe37aa631fe9fd3c83d9c58f47fb2992ccfde394
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd90cff89c6cac8f8e01ee930e1b8fcd3533088466b4d7d3d6d52cbfffcb34c
+oid sha256:2c61a4978c849f00b536f95ff0ea1db22a6b5d31ecd734461055b1e0c6cac7c0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89106ce7ebabad159b850fa269973d8e7d61f69ea1549855600e75d9bd12bb22
+oid sha256:0ea8cf10a2365ff8f1db6e7b3bf12581e73d211b15e9426de5e532cf86f20d33
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:212b51d1e68a947a68392e4a0ff68595dcccc3861180e13e8db36dab190034ab
+oid sha256:417f646fa2dcf994f5bbea6d3abc010bd2164f4c6f26ce161717a4bde0542f7b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6b77c0cbcc35c1c43ee60e2766b6027d2e111edae589e45f75af1b1040b32d
+oid sha256:84fc982e8229d2121603832a24f4c07bbdbf63985ed1d38e11762164a04dad3b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.336300015449524,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8691588785046729,
+  "epoch": 3.0654205607476634,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 41,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,118 @@
       "eval_samples_per_second": 15.58,
       "eval_steps_per_second": 2.077,
       "step": 25
+    },
+    {
+      "epoch": 1.9439252336448598,
+      "grad_norm": 0.7272557616233826,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 1.2889,
+      "step": 26
+    },
+    {
+      "epoch": 2.0186915887850465,
+      "grad_norm": 0.5690138936042786,
+      "learning_rate": 2.8565371929847284e-05,
+      "loss": 2.5088,
+      "step": 27
+    },
+    {
+      "epoch": 2.0934579439252334,
+      "grad_norm": 0.3526255488395691,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2991,
+      "step": 28
+    },
+    {
+      "epoch": 2.1682242990654204,
+      "grad_norm": 0.47234588861465454,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 1.1887,
+      "step": 29
+    },
+    {
+      "epoch": 2.2429906542056073,
+      "grad_norm": 0.384577214717865,
+      "learning_rate": 1.837773122023114e-05,
+      "loss": 0.7942,
+      "step": 30
+    },
+    {
+      "epoch": 2.317757009345794,
+      "grad_norm": 0.3493711054325104,
+      "learning_rate": 1.536378232452003e-05,
+      "loss": 2.081,
+      "step": 31
+    },
+    {
+      "epoch": 2.392523364485981,
+      "grad_norm": 0.4692765176296234,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 1.1978,
+      "step": 32
+    },
+    {
+      "epoch": 2.467289719626168,
+      "grad_norm": 0.31681570410728455,
+      "learning_rate": 1.0027861829824952e-05,
+      "loss": 0.9036,
+      "step": 33
+    },
+    {
+      "epoch": 2.542056074766355,
+      "grad_norm": 0.36259856820106506,
+      "learning_rate": 7.740495722810271e-06,
+      "loss": 1.9976,
+      "step": 34
+    },
+    {
+      "epoch": 2.616822429906542,
+      "grad_norm": 0.384077787399292,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 1.332,
+      "step": 35
+    },
+    {
+      "epoch": 2.691588785046729,
+      "grad_norm": 0.27743789553642273,
+      "learning_rate": 4.001027817058789e-06,
+      "loss": 0.7633,
+      "step": 36
+    },
+    {
+      "epoch": 2.7663551401869158,
+      "grad_norm": 0.32165083289146423,
+      "learning_rate": 2.573177902642726e-06,
+      "loss": 2.0513,
+      "step": 37
+    },
+    {
+      "epoch": 2.8411214953271027,
+      "grad_norm": 0.39092400670051575,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 1.1744,
+      "step": 38
+    },
+    {
+      "epoch": 2.9158878504672896,
+      "grad_norm": 0.47860899567604065,
+      "learning_rate": 6.474868681043578e-07,
+      "loss": 1.1507,
+      "step": 39
+    },
+    {
+      "epoch": 2.9906542056074765,
+      "grad_norm": 1.0024253129959106,
+      "learning_rate": 1.6213459328950352e-07,
+      "loss": 1.9473,
+      "step": 40
+    },
+    {
+      "epoch": 3.0654205607476634,
+      "grad_norm": 0.37559443712234497,
+      "learning_rate": 0.0,
+      "loss": 1.7136,
+      "step": 41
     }
   ],
   "logging_steps": 1,
@@ -221,12 +333,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.250798609728799e+17,
+  "total_flos": 8.614183290158449e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null