Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803744d39dc53ddf7f40b3cf0cfefc0de726b74a5399552e6dacd539cd64c8e7
+oid sha256:9a18058083e7336288689b5045bca3afef9febb3cb26d0163cf7e2495ff79bbe
 size 116744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d07aa544a62fa7499c39b9ee9df61d64381b99994a0fe5f59f2306e0b5234990
+oid sha256:c400dacb6aa49de9c4190acab68d809ef0a20d40de838821696214989ceb833a
 size 243310

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8638a4afd4bdde26f3a21fa07f565bc3da38a5f6b2e47f3779d24269c54864b
+oid sha256:e61c05d0677f76413ee55325b16b5101fb7ec1ef12defe5e0b2ec118fe605dd5
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd9693696f3930f7b15fae986948fb2c3a37ec32782bf81431543081120ed45
+oid sha256:d1d18bbf18c69543eede75b23600a9c2da38dac6b7c991fe3bf8e58fcf5143e8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40f3e62ecc06db16609542e03f44ae1616bc73efbbe2429016e4956db0f72f44
+oid sha256:7f16309aeb35a0d6debd78a42eaa828d895db9f37d2bd07b7e644da353e25e9f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c921986cec9c241564cd61ad0c21e59bbbd73adadecdb8b84f1e16efbee5ee67
+oid sha256:b2346a543c4074d9e7c4908b5f2b847ee103a5db548d9b1dc5ca9e949ff7447b
 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": 10.376715660095215,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03007518796992481,
+  "best_metric": 10.374860763549805,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06015037593984962,
   "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": 1162.389,
       "eval_steps_per_second": 145.299,
       "step": 25
+    },
+    {
+      "epoch": 0.03127819548872181,
+      "grad_norm": 0.188450425863266,
+      "learning_rate": 5e-05,
+      "loss": 10.3677,
+      "step": 26
+    },
+    {
+      "epoch": 0.0324812030075188,
+      "grad_norm": 0.1014418974518776,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3741,
+      "step": 27
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 0.06390609592199326,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3749,
+      "step": 28
+    },
+    {
+      "epoch": 0.03488721804511278,
+      "grad_norm": 0.06750831753015518,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3781,
+      "step": 29
+    },
+    {
+      "epoch": 0.03609022556390978,
+      "grad_norm": 0.052159812301397324,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3768,
+      "step": 30
+    },
+    {
+      "epoch": 0.03729323308270677,
+      "grad_norm": 0.07348703593015671,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3756,
+      "step": 31
+    },
+    {
+      "epoch": 0.03849624060150376,
+      "grad_norm": 0.06757855415344238,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3782,
+      "step": 32
+    },
+    {
+      "epoch": 0.039699248120300755,
+      "grad_norm": 0.06782123446464539,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.378,
+      "step": 33
+    },
+    {
+      "epoch": 0.040902255639097745,
+      "grad_norm": 0.06930963695049286,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3763,
+      "step": 34
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 0.08735895156860352,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3796,
+      "step": 35
+    },
+    {
+      "epoch": 0.043308270676691726,
+      "grad_norm": 0.08168835937976837,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.379,
+      "step": 36
+    },
+    {
+      "epoch": 0.044511278195488724,
+      "grad_norm": 0.10469164699316025,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3799,
+      "step": 37
+    },
+    {
+      "epoch": 0.045714285714285714,
+      "grad_norm": 0.18160542845726013,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3644,
+      "step": 38
+    },
+    {
+      "epoch": 0.046917293233082705,
+      "grad_norm": 0.13455776870250702,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3691,
+      "step": 39
+    },
+    {
+      "epoch": 0.0481203007518797,
+      "grad_norm": 0.08988126367330551,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3727,
+      "step": 40
+    },
+    {
+      "epoch": 0.04932330827067669,
+      "grad_norm": 0.07319313287734985,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3758,
+      "step": 41
+    },
+    {
+      "epoch": 0.05052631578947368,
+      "grad_norm": 0.06437268853187561,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3747,
+      "step": 42
+    },
+    {
+      "epoch": 0.051729323308270674,
+      "grad_norm": 0.058004025369882584,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3783,
+      "step": 43
+    },
+    {
+      "epoch": 0.05293233082706767,
+      "grad_norm": 0.06401561945676804,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3742,
+      "step": 44
+    },
+    {
+      "epoch": 0.05413533834586466,
+      "grad_norm": 0.0757477805018425,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3734,
+      "step": 45
+    },
+    {
+      "epoch": 0.05533834586466165,
+      "grad_norm": 0.07375133037567139,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3783,
+      "step": 46
+    },
+    {
+      "epoch": 0.05654135338345865,
+      "grad_norm": 0.08306660503149033,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3792,
+      "step": 47
+    },
+    {
+      "epoch": 0.05774436090225564,
+      "grad_norm": 0.08625657111406326,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3759,
+      "step": 48
+    },
+    {
+      "epoch": 0.05894736842105263,
+      "grad_norm": 0.09709803760051727,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3772,
+      "step": 49
+    },
+    {
+      "epoch": 0.06015037593984962,
+      "grad_norm": 0.1422736793756485,
+      "learning_rate": 0.0,
+      "loss": 10.3807,
+      "step": 50
+    },
+    {
+      "epoch": 0.06015037593984962,
+      "eval_loss": 10.374860763549805,
+      "eval_runtime": 4.8174,
+      "eval_samples_per_second": 1162.461,
+      "eval_steps_per_second": 145.308,
+      "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": 42311303823360.0,
+  "total_flos": 84622607646720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null