Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98417269b3fe4b81dada47f4b5cec605bfe3f1d66bedc4a7bc717d43d0da4ad2
+oid sha256:fbab810f0f9ad2fb5a6e9baf0c39bb1c649cc86cc228b511a2670822d5488eb4
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab8625b831f338106b91487162dcfbcb18300d521e8ac044000a400fbd40ef68
+oid sha256:8926404e1b3ce33dc99ce6f9591e6df1d07dbef6f3f09f9beadbc858cb7eed4e
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f752f0ad1d1377223fb5a0829bd728362ac6378e3b46c55021c0fc9235444a57
+oid sha256:52d2962e7addbea2ceae75f2abcb3fd4e4273b5182d31996533fa59a383899d8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:493f967577fe669a13615e58500bb11cf36367f5aadd60a2175c1ba7ba9ccd70
+oid sha256:cc9456beac904b59541e41b468c018a368e070a36e670c0399e4fa1287f597f9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e2c2be701709a9bc6719681dcb2d93511c54e52f0e104ddb4b620ec34f4a8cd
+oid sha256:c977a0eb6b4fb83f3690313761c4237a725ccaac272041911ddb5da12fccfc3b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6c47be62cb27ceca59fbd7d2683f2e6d1730269129017f1281d93684c881d2f
+oid sha256:e6809c01da345aec5c7ec6ae340edb56f52661ec5c0bf41d8dc104a81097a016
 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": 10.358575820922852,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.272108843537415,
+  "best_metric": 10.349431037902832,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.54421768707483,
   "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": 957.305,
       "eval_steps_per_second": 120.63,
       "step": 25
+    },
+    {
+      "epoch": 0.2829931972789116,
+      "grad_norm": 0.42081892490386963,
+      "learning_rate": 5e-05,
+      "loss": 10.3586,
+      "step": 26
+    },
+    {
+      "epoch": 0.2938775510204082,
+      "grad_norm": 0.40955573320388794,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3587,
+      "step": 27
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.4053417146205902,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3575,
+      "step": 28
+    },
+    {
+      "epoch": 0.31564625850340133,
+      "grad_norm": 0.4076749384403229,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3567,
+      "step": 29
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.40912002325057983,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3548,
+      "step": 30
+    },
+    {
+      "epoch": 0.33741496598639453,
+      "grad_norm": 0.41830697655677795,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3538,
+      "step": 31
+    },
+    {
+      "epoch": 0.34829931972789113,
+      "grad_norm": 0.41212475299835205,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3551,
+      "step": 32
+    },
+    {
+      "epoch": 0.35918367346938773,
+      "grad_norm": 0.4229467809200287,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3524,
+      "step": 33
+    },
+    {
+      "epoch": 0.37006802721088433,
+      "grad_norm": 0.40772733092308044,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3524,
+      "step": 34
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.41412273049354553,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3522,
+      "step": 35
+    },
+    {
+      "epoch": 0.39183673469387753,
+      "grad_norm": 0.41297608613967896,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3526,
+      "step": 36
+    },
+    {
+      "epoch": 0.40272108843537413,
+      "grad_norm": 0.38842713832855225,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3519,
+      "step": 37
+    },
+    {
+      "epoch": 0.41360544217687073,
+      "grad_norm": 0.4429492652416229,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3524,
+      "step": 38
+    },
+    {
+      "epoch": 0.42448979591836733,
+      "grad_norm": 0.44514551758766174,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3516,
+      "step": 39
+    },
+    {
+      "epoch": 0.43537414965986393,
+      "grad_norm": 0.4472653865814209,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3509,
+      "step": 40
+    },
+    {
+      "epoch": 0.44625850340136053,
+      "grad_norm": 0.44553062319755554,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3499,
+      "step": 41
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.433199018239975,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3501,
+      "step": 42
+    },
+    {
+      "epoch": 0.46802721088435373,
+      "grad_norm": 0.4309545159339905,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3486,
+      "step": 43
+    },
+    {
+      "epoch": 0.47891156462585033,
+      "grad_norm": 0.43892306089401245,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3485,
+      "step": 44
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 0.43471524119377136,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.35,
+      "step": 45
+    },
+    {
+      "epoch": 0.5006802721088436,
+      "grad_norm": 0.4365433156490326,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3491,
+      "step": 46
+    },
+    {
+      "epoch": 0.5115646258503401,
+      "grad_norm": 0.40179312229156494,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3504,
+      "step": 47
+    },
+    {
+      "epoch": 0.5224489795918368,
+      "grad_norm": 0.4212394654750824,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3486,
+      "step": 48
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.4362102150917053,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.348,
+      "step": 49
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 0.4109918475151062,
+      "learning_rate": 0.0,
+      "loss": 10.3504,
+      "step": 50
+    },
+    {
+      "epoch": 0.54421768707483,
+      "eval_loss": 10.349431037902832,
+      "eval_runtime": 0.6456,
+      "eval_samples_per_second": 958.852,
+      "eval_steps_per_second": 120.825,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null