Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377ba0dd29e1db1a03909902421f3bb6bbb57334e3e57cbb47e40c29aea9b7ed
+oid sha256:b73c710cce659d08f62ecddd7fca19a5d6a0e662b31fbe37873e7d68bdfac674
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d5361a1da2d4164603fe6c5a46ee74e9628514dc1e8a7be041c50b4515b3300
+oid sha256:215e00a58c32a18f3ace15c01c6e04b98e86bfa101b74b960314025be5999d1b
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe45e2e21bc1f91d0760418821d9ba7961745069802f2efee08fe069b707c0f
+oid sha256:940378b54e35ae6faeaaf7b773f94571af9d5134d8a9921d02bdc8818b8119e5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4b00e058dd311fdbfc7257ab541ebd4c55cd0b30a63712efb06b33d20ab566
+oid sha256:97595095d759cdffb38aae4b97e342c92798ae57eaee8debc17764ff07c98b50
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d7bc4acff8d9a2d001a2745d804b33347d5de21dc45cdd63eba9005144c3fe
+oid sha256:a1654e28837e5f8a7c4f11b123046f942e303c7c53cc4dedd341368c0e49a799
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5329483aad642618b8adedf9b87f871ed29bf582b8f127436fd3b505ae5601b2
+oid sha256:7237e577bf04d9f4a69682b6134a7fac6179e2492f50df173003f5573d52623b
 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": 1.4687479734420776,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1784121320249777,
+  "best_metric": 1.4106714725494385,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3568242640499554,
   "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": 30.695,
       "eval_steps_per_second": 3.837,
       "step": 25
+    },
+    {
+      "epoch": 0.1855486173059768,
+      "grad_norm": 0.3600711226463318,
+      "learning_rate": 5e-05,
+      "loss": 1.5342,
+      "step": 26
+    },
+    {
+      "epoch": 0.1926851025869759,
+      "grad_norm": 0.3504575490951538,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5703,
+      "step": 27
+    },
+    {
+      "epoch": 0.19982158786797502,
+      "grad_norm": 0.3406086266040802,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4813,
+      "step": 28
+    },
+    {
+      "epoch": 0.20695807314897413,
+      "grad_norm": 0.32979071140289307,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4443,
+      "step": 29
+    },
+    {
+      "epoch": 0.21409455842997324,
+      "grad_norm": 0.32950469851493835,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3329,
+      "step": 30
+    },
+    {
+      "epoch": 0.22123104371097235,
+      "grad_norm": 0.293745219707489,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3487,
+      "step": 31
+    },
+    {
+      "epoch": 0.22836752899197146,
+      "grad_norm": 0.2850325107574463,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2256,
+      "step": 32
+    },
+    {
+      "epoch": 0.23550401427297057,
+      "grad_norm": 0.3074958920478821,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3394,
+      "step": 33
+    },
+    {
+      "epoch": 0.24264049955396966,
+      "grad_norm": 0.3559531569480896,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4278,
+      "step": 34
+    },
+    {
+      "epoch": 0.24977698483496877,
+      "grad_norm": 0.3970128297805786,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4543,
+      "step": 35
+    },
+    {
+      "epoch": 0.2569134701159679,
+      "grad_norm": 0.4422309994697571,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4932,
+      "step": 36
+    },
+    {
+      "epoch": 0.264049955396967,
+      "grad_norm": 0.5918712019920349,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.6008,
+      "step": 37
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 0.37357911467552185,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5213,
+      "step": 38
+    },
+    {
+      "epoch": 0.2783229259589652,
+      "grad_norm": 0.25279656052589417,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5196,
+      "step": 39
+    },
+    {
+      "epoch": 0.2854594112399643,
+      "grad_norm": 0.2838667333126068,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5639,
+      "step": 40
+    },
+    {
+      "epoch": 0.2925958965209634,
+      "grad_norm": 0.3013131022453308,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4475,
+      "step": 41
+    },
+    {
+      "epoch": 0.29973238180196254,
+      "grad_norm": 0.25624337792396545,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3707,
+      "step": 42
+    },
+    {
+      "epoch": 0.3068688670829616,
+      "grad_norm": 0.27869874238967896,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2227,
+      "step": 43
+    },
+    {
+      "epoch": 0.31400535236396077,
+      "grad_norm": 0.2727345824241638,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2668,
+      "step": 44
+    },
+    {
+      "epoch": 0.32114183764495985,
+      "grad_norm": 0.2815842628479004,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2812,
+      "step": 45
+    },
+    {
+      "epoch": 0.328278322925959,
+      "grad_norm": 0.3167998790740967,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2754,
+      "step": 46
+    },
+    {
+      "epoch": 0.33541480820695807,
+      "grad_norm": 0.3581273853778839,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.426,
+      "step": 47
+    },
+    {
+      "epoch": 0.34255129348795715,
+      "grad_norm": 0.3858048617839813,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4207,
+      "step": 48
+    },
+    {
+      "epoch": 0.3496877787689563,
+      "grad_norm": 0.470745325088501,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5814,
+      "step": 49
+    },
+    {
+      "epoch": 0.3568242640499554,
+      "grad_norm": 0.8137080073356628,
+      "learning_rate": 0.0,
+      "loss": 1.751,
+      "step": 50
+    },
+    {
+      "epoch": 0.3568242640499554,
+      "eval_loss": 1.4106714725494385,
+      "eval_runtime": 30.5549,
+      "eval_samples_per_second": 30.895,
+      "eval_steps_per_second": 3.862,
+      "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": 2.7465491653695898e+17,
+  "total_flos": 5.498086011835515e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null