Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131491bb60ef99ec0b760ada6f77b1379433640d5f3bf4ebedbca1f3ac5c57de
+oid sha256:f90702c85a01e2a0dc8e044037dcfc901c277bd9fce605cca1a7871c0c09646c
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675d49ae696c9109c9ebaf6be07d4f2f5b92a16f088fb0b9818014c1cf268c57
+oid sha256:a582002767c4bfea39e392372d83ccec0f16087cf72246c0190d336aa07a5b4f
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a38df876b2b389fd6693cc70f0dc30c8a3a49514ac5fc6ead3a817c19d72fe
+oid sha256:bff0acf65586d103ce05ae8c1b491c16ff3e115244bf792c03db0294b0af37bb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d050929cd9286328ac91bd927ed2c1b67cb51f86e84e8b5f7939d6d6d2f600
+oid sha256:31d82f337bd5aa22621efb6f652593f5498941d6dee7c9594d0c19f30c79df4c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65c216bd33509855545e18e2a8b5070499e56ecfcf56986e12df0c1177c6a88
+oid sha256:7ee67a284952e3cecac0f6ffb7c763406d82e59c94282792ca93edad1f51daee
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:842402ac1cd2749731dc4a329f672c78857071278a39da39cf12c697870923db
+oid sha256:5bb371b6162ed442088dfd428748aa6ac3d6e354b259d77ba23fd095725a5607
 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": 11.732650756835938,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5263157894736842,
+  "best_metric": 11.723119735717773,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0526315789473684,
   "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": 283.5,
       "eval_steps_per_second": 35.438,
       "step": 25
+    },
+    {
+      "epoch": 0.5473684210526316,
+      "grad_norm": 0.2345844805240631,
+      "learning_rate": 5e-05,
+      "loss": 11.7376,
+      "step": 26
+    },
+    {
+      "epoch": 0.5684210526315789,
+      "grad_norm": 0.264325350522995,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 11.7337,
+      "step": 27
+    },
+    {
+      "epoch": 0.5894736842105263,
+      "grad_norm": 0.26752516627311707,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 11.7351,
+      "step": 28
+    },
+    {
+      "epoch": 0.6105263157894737,
+      "grad_norm": 0.2887979745864868,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 11.7339,
+      "step": 29
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.2962575852870941,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 11.7316,
+      "step": 30
+    },
+    {
+      "epoch": 0.6526315789473685,
+      "grad_norm": 0.30820557475090027,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 11.7315,
+      "step": 31
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 0.3171234130859375,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.7301,
+      "step": 32
+    },
+    {
+      "epoch": 0.6947368421052632,
+      "grad_norm": 0.38728827238082886,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 11.7244,
+      "step": 33
+    },
+    {
+      "epoch": 0.7157894736842105,
+      "grad_norm": 0.42645493149757385,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.7229,
+      "step": 34
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.5456458330154419,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 11.7222,
+      "step": 35
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 0.3445981442928314,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 11.7354,
+      "step": 36
+    },
+    {
+      "epoch": 0.7789473684210526,
+      "grad_norm": 0.2860390543937683,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 11.7311,
+      "step": 37
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.27807894349098206,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.7312,
+      "step": 38
+    },
+    {
+      "epoch": 0.8210526315789474,
+      "grad_norm": 0.30254852771759033,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 11.7317,
+      "step": 39
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.2956697642803192,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 11.7283,
+      "step": 40
+    },
+    {
+      "epoch": 0.8631578947368421,
+      "grad_norm": 0.3198343813419342,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 11.7265,
+      "step": 41
+    },
+    {
+      "epoch": 0.8842105263157894,
+      "grad_norm": 0.3181462585926056,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 11.7275,
+      "step": 42
+    },
+    {
+      "epoch": 0.9052631578947369,
+      "grad_norm": 0.34188899397850037,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 11.7252,
+      "step": 43
+    },
+    {
+      "epoch": 0.9263157894736842,
+      "grad_norm": 0.3721233010292053,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.7256,
+      "step": 44
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.4120519757270813,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 11.7205,
+      "step": 45
+    },
+    {
+      "epoch": 0.968421052631579,
+      "grad_norm": 0.44379058480262756,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 11.7199,
+      "step": 46
+    },
+    {
+      "epoch": 0.9894736842105263,
+      "grad_norm": 0.714651882648468,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 11.7239,
+      "step": 47
+    },
+    {
+      "epoch": 1.0105263157894737,
+      "grad_norm": 0.5324737429618835,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 17.8497,
+      "step": 48
+    },
+    {
+      "epoch": 1.0315789473684212,
+      "grad_norm": 0.27828526496887207,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 11.5501,
+      "step": 49
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.28052791953086853,
+      "learning_rate": 0.0,
+      "loss": 11.8054,
+      "step": 50
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "eval_loss": 11.723119735717773,
+      "eval_runtime": 1.1344,
+      "eval_samples_per_second": 282.075,
+      "eval_steps_per_second": 35.259,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 81943068672000.0,
+  "total_flos": 163886137344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null