Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b40432c492ec8e2a59a0be889bdaf37153fbf08095c3c99610cf62d6549aaa
+oid sha256:4650b8ef015295bd21cd24517444db8eaa2b553b98429c193e9ec2f0a7f0d5ee
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad211d4761c92ec7459e7902d22d60c74a63130e0669b3cf034414093044273
+oid sha256:20af234dc4d99a63738fd6e333f17176758d1204fc73ce4839f13fb98e65815a
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be0584c16dc8aba368680c24a9bbb0050e5cb002f2beed5dc472e7e1f06ab37
+oid sha256:0fc836ce604718c2676256fbfcd3df4c6d401f53c630f087aeab04e3b59705af
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5710b059af52f033114ee682c37e0faaae69e7543050d6179f4652d3b956f615
+oid sha256:535d92f5e4627c3f9ee29df004b41b11681ce828d33bf6ab7382bd386aea9ead
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08986106e4790b1fa36ef4a5bd608d5fb3805c6525c11e80daf924cb7165f955
+oid sha256:a222ddf127e8f07944a721d57b508314059341f47648f9df5403136920b2f918
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2561101772c10d5689f9744af35e34e05cd6db2f391f8ce5439b1042a35973b9
+oid sha256:6393c2d23091ea326bccd22162b0aea280983c522db343f1eb0290767a9e1b95
 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": 1.358454704284668,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07636502481863307,
+  "best_metric": 1.1396163702011108,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15273004963726614,
   "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": 38.936,
       "eval_steps_per_second": 4.871,
       "step": 25
+    },
+    {
+      "epoch": 0.07941962581137839,
+      "grad_norm": 102.45426177978516,
+      "learning_rate": 5e-05,
+      "loss": 22.9259,
+      "step": 26
+    },
+    {
+      "epoch": 0.08247422680412371,
+      "grad_norm": 90.15953826904297,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 21.9522,
+      "step": 27
+    },
+    {
+      "epoch": 0.08552882779686903,
+      "grad_norm": 92.5013427734375,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 22.2064,
+      "step": 28
+    },
+    {
+      "epoch": 0.08858342878961435,
+      "grad_norm": 72.16334533691406,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 18.7869,
+      "step": 29
+    },
+    {
+      "epoch": 0.09163802978235967,
+      "grad_norm": 81.92129516601562,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 15.8735,
+      "step": 30
+    },
+    {
+      "epoch": 0.09469263077510501,
+      "grad_norm": 101.18927764892578,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 19.6555,
+      "step": 31
+    },
+    {
+      "epoch": 0.09774723176785033,
+      "grad_norm": 81.10553741455078,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 19.2793,
+      "step": 32
+    },
+    {
+      "epoch": 0.10080183276059565,
+      "grad_norm": 72.74671936035156,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 18.6,
+      "step": 33
+    },
+    {
+      "epoch": 0.10385643375334097,
+      "grad_norm": 86.57416534423828,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 18.3163,
+      "step": 34
+    },
+    {
+      "epoch": 0.10691103474608629,
+      "grad_norm": 91.92635345458984,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 19.9557,
+      "step": 35
+    },
+    {
+      "epoch": 0.10996563573883161,
+      "grad_norm": 120.62100982666016,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 20.4593,
+      "step": 36
+    },
+    {
+      "epoch": 0.11302023673157693,
+      "grad_norm": 102.29236602783203,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 21.8171,
+      "step": 37
+    },
+    {
+      "epoch": 0.11607483772432226,
+      "grad_norm": 94.89315032958984,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 23.6319,
+      "step": 38
+    },
+    {
+      "epoch": 0.11912943871706758,
+      "grad_norm": 80.66189575195312,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 18.8452,
+      "step": 39
+    },
+    {
+      "epoch": 0.12218403970981291,
+      "grad_norm": 89.5391616821289,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 20.5874,
+      "step": 40
+    },
+    {
+      "epoch": 0.12523864070255822,
+      "grad_norm": 81.86558532714844,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 20.799,
+      "step": 41
+    },
+    {
+      "epoch": 0.12829324169530354,
+      "grad_norm": 89.75981140136719,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 19.7842,
+      "step": 42
+    },
+    {
+      "epoch": 0.13134784268804886,
+      "grad_norm": 89.26224517822266,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 17.2257,
+      "step": 43
+    },
+    {
+      "epoch": 0.1344024436807942,
+      "grad_norm": 84.56063842773438,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 17.7931,
+      "step": 44
+    },
+    {
+      "epoch": 0.13745704467353953,
+      "grad_norm": 77.53307342529297,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 19.046,
+      "step": 45
+    },
+    {
+      "epoch": 0.14051164566628485,
+      "grad_norm": 71.67435455322266,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 16.1301,
+      "step": 46
+    },
+    {
+      "epoch": 0.14356624665903017,
+      "grad_norm": 72.81458282470703,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 17.1189,
+      "step": 47
+    },
+    {
+      "epoch": 0.1466208476517755,
+      "grad_norm": 105.62673950195312,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 17.1779,
+      "step": 48
+    },
+    {
+      "epoch": 0.14967544864452081,
+      "grad_norm": 95.08515167236328,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 20.9969,
+      "step": 49
+    },
+    {
+      "epoch": 0.15273004963726614,
+      "grad_norm": 113.62215423583984,
+      "learning_rate": 0.0,
+      "loss": 27.1015,
+      "step": 50
+    },
+    {
+      "epoch": 0.15273004963726614,
+      "eval_loss": 1.1396163702011108,
+      "eval_runtime": 56.656,
+      "eval_samples_per_second": 38.937,
+      "eval_steps_per_second": 4.872,
+      "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": 2.829062208749568e+17,
+  "total_flos": 5.658124417499136e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null