Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbcaca8840337168c6fb1365586ab4cc6c45273e5b7f6aee2942efeec21e8fc8
+oid sha256:11480ef8804c4194f451ca3c4d24fedac999fe76f0817a1fb1377c94ed10942c
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c1e937737ece50a913702878179084a8a9850cda38397d0768cc682343f27d
+oid sha256:9f7903586f005f3ef11331f8b7dde6e6474eaf4b0075f069b4244c16331fba5b
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c33f142f4bf30060b7232b49c1b160aa340f064e73b6e37e36f8cfd297cf6a2e
+oid sha256:450ad260815d8adbfbcb61dc0a10c2d8b4f2317f1b04f28007e57428123786f1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b282cf6bf914223139ecf1933e85ed1bcb63fd6e6e58dbad8ec4f655f1d7fdff
+oid sha256:aba3c10f1a14a3cc07e0f93fa0804fa58267d2b387df5cd06118b4c4d6834e32
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe9b0abc7bd3bf99e65c6b5f377db1af206a10dd09071c1abb1ce50f1cdbbd4f
+oid sha256:4cba5691777483dacc99d88408571842fc49cf545a75eba0fcaed127af2c8d7e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83935d895e9bded32b8b7dc59a41740dca2d73bbee3336e67faece4b32207be9
+oid sha256:e279858de81e623b84481903cb0e58cfb15e42622edeb9907ac4b612088a25e1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09947774185525989,
+  "epoch": 0.19895548371051977,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 35.107,
       "eval_steps_per_second": 4.396,
       "step": 25
+    },
+    {
+      "epoch": 0.10345685152947028,
+      "grad_norm": 0.6516526937484741,
+      "learning_rate": 5e-05,
+      "loss": 1.0348,
+      "step": 26
+    },
+    {
+      "epoch": 0.10743596120368068,
+      "grad_norm": 0.789240837097168,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0676,
+      "step": 27
+    },
+    {
+      "epoch": 0.11141507087789107,
+      "grad_norm": 0.8339486718177795,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1012,
+      "step": 28
+    },
+    {
+      "epoch": 0.11539418055210146,
+      "grad_norm": 0.896287739276886,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1229,
+      "step": 29
+    },
+    {
+      "epoch": 0.11937329022631187,
+      "grad_norm": 0.9912587404251099,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1645,
+      "step": 30
+    },
+    {
+      "epoch": 0.12335239990052226,
+      "grad_norm": 0.889596164226532,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0521,
+      "step": 31
+    },
+    {
+      "epoch": 0.12733150957473266,
+      "grad_norm": 0.9579912424087524,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1043,
+      "step": 32
+    },
+    {
+      "epoch": 0.13131061924894305,
+      "grad_norm": 1.0357494354248047,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0756,
+      "step": 33
+    },
+    {
+      "epoch": 0.13528972892315344,
+      "grad_norm": 1.0748677253723145,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.058,
+      "step": 34
+    },
+    {
+      "epoch": 0.13926883859736383,
+      "grad_norm": 1.1622072458267212,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.963,
+      "step": 35
+    },
+    {
+      "epoch": 0.14324794827157422,
+      "grad_norm": 1.2325820922851562,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0536,
+      "step": 36
+    },
+    {
+      "epoch": 0.14722705794578464,
+      "grad_norm": 1.3320115804672241,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0085,
+      "step": 37
+    },
+    {
+      "epoch": 0.15120616761999503,
+      "grad_norm": 0.662959635257721,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9924,
+      "step": 38
+    },
+    {
+      "epoch": 0.15518527729420542,
+      "grad_norm": 0.5767291188240051,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0112,
+      "step": 39
+    },
+    {
+      "epoch": 0.1591643869684158,
+      "grad_norm": 0.6378970742225647,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0152,
+      "step": 40
+    },
+    {
+      "epoch": 0.1631434966426262,
+      "grad_norm": 0.671429455280304,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0604,
+      "step": 41
+    },
+    {
+      "epoch": 0.16712260631683662,
+      "grad_norm": 0.7947982549667358,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1157,
+      "step": 42
+    },
+    {
+      "epoch": 0.171101715991047,
+      "grad_norm": 0.8399484753608704,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2089,
+      "step": 43
+    },
+    {
+      "epoch": 0.1750808256652574,
+      "grad_norm": 0.9737657904624939,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1138,
+      "step": 44
+    },
+    {
+      "epoch": 0.1790599353394678,
+      "grad_norm": 0.9923420548439026,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1005,
+      "step": 45
+    },
+    {
+      "epoch": 0.18303904501367818,
+      "grad_norm": 1.116300106048584,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0755,
+      "step": 46
+    },
+    {
+      "epoch": 0.18701815468788857,
+      "grad_norm": 1.0894296169281006,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0124,
+      "step": 47
+    },
+    {
+      "epoch": 0.190997264362099,
+      "grad_norm": 1.2329972982406616,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0821,
+      "step": 48
+    },
+    {
+      "epoch": 0.19497637403630938,
+      "grad_norm": 1.27621591091156,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.023,
+      "step": 49
+    },
+    {
+      "epoch": 0.19895548371051977,
+      "grad_norm": 1.7285157442092896,
+      "learning_rate": 0.0,
+      "loss": 1.0262,
+      "step": 50
+    },
+    {
+      "epoch": 0.19895548371051977,
+      "eval_loss": NaN,
+      "eval_runtime": 48.3094,
+      "eval_samples_per_second": 35.045,
+      "eval_steps_per_second": 4.388,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null