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:e45b1d7e515495198296bde0ee7b0a68a87f674034e5aa1d0656c90ff75a8fe9
+oid sha256:e6f2b70b62b5ef5d8e83844a57cbedf3c4de0c6fb181a12d86c6905669b80694
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d93c5a2ae3d8656decca54f489881ed9fe897c849cc6da82d1b04f057bad0a5
+oid sha256:c84eff89f1d9b75df5de35040e459cb97404bac08726e72d560422b67eb5750c
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8359638a9195be3f961387224ca71cbc471337955358a3df7f7b8397aada4154
+oid sha256:c67365a17cb1ad0eeb544c2879ff1ea5bf4a8b38a8d47c89565f64e9dbfa1e37
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292a9250be8e2fcf4c65d94b73a21c162a046a64a3c4eda698a8fab8f0a71545
+oid sha256:e7add88461cc7ad2c66afbd922ef934dea42d6eec82bc6e8ab61ff3d0102efb9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494fcb5afe38d080380c162be5aadca7610b9172465aa560859ecb1f1bb623dc
+oid sha256:72b9f09d9e208dbdaea300d0e13149c4999ebbf3899111c9edd45d33581d0c3b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ef0a5b2e9909144beff9fa07ed5f24ad11df11058e5ffc71ac7c7f5e6b8fb2
+oid sha256:f85c5afa9a9346dfc706dea27bfd70a0eba4d62bcb75b9efe62e2ee870ab9e73
 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": 0.9880382418632507,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1299545159194282,
+  "best_metric": 0.9067763090133667,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2599090318388564,
   "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": 15.606,
       "eval_steps_per_second": 1.961,
       "step": 25
+    },
+    {
+      "epoch": 0.13515269655620532,
+      "grad_norm": 0.8514086604118347,
+      "learning_rate": 5e-05,
+      "loss": 1.3471,
+      "step": 26
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 0.9503392577171326,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1386,
+      "step": 27
+    },
+    {
+      "epoch": 0.14554905782975958,
+      "grad_norm": 1.0655407905578613,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1386,
+      "step": 28
+    },
+    {
+      "epoch": 0.1507472384665367,
+      "grad_norm": 1.0771244764328003,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9845,
+      "step": 29
+    },
+    {
+      "epoch": 0.15594541910331383,
+      "grad_norm": 1.106429100036621,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9568,
+      "step": 30
+    },
+    {
+      "epoch": 0.16114359974009096,
+      "grad_norm": 0.99420565366745,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9367,
+      "step": 31
+    },
+    {
+      "epoch": 0.1663417803768681,
+      "grad_norm": 0.8913936614990234,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8778,
+      "step": 32
+    },
+    {
+      "epoch": 0.17153996101364521,
+      "grad_norm": 0.686725378036499,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8467,
+      "step": 33
+    },
+    {
+      "epoch": 0.17673814165042234,
+      "grad_norm": 0.5283013582229614,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8317,
+      "step": 34
+    },
+    {
+      "epoch": 0.18193632228719947,
+      "grad_norm": 0.43462270498275757,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8101,
+      "step": 35
+    },
+    {
+      "epoch": 0.1871345029239766,
+      "grad_norm": 0.4682368338108063,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8112,
+      "step": 36
+    },
+    {
+      "epoch": 0.19233268356075373,
+      "grad_norm": 0.4088591933250427,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7954,
+      "step": 37
+    },
+    {
+      "epoch": 0.19753086419753085,
+      "grad_norm": 0.3308998942375183,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1745,
+      "step": 38
+    },
+    {
+      "epoch": 0.20272904483430798,
+      "grad_norm": 0.358073353767395,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1004,
+      "step": 39
+    },
+    {
+      "epoch": 0.2079272254710851,
+      "grad_norm": 0.39678260684013367,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0453,
+      "step": 40
+    },
+    {
+      "epoch": 0.21312540610786224,
+      "grad_norm": 0.2794766128063202,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9391,
+      "step": 41
+    },
+    {
+      "epoch": 0.21832358674463936,
+      "grad_norm": 0.2508675158023834,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9462,
+      "step": 42
+    },
+    {
+      "epoch": 0.2235217673814165,
+      "grad_norm": 0.3554503321647644,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.86,
+      "step": 43
+    },
+    {
+      "epoch": 0.22871994801819362,
+      "grad_norm": 0.3546721041202545,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.832,
+      "step": 44
+    },
+    {
+      "epoch": 0.23391812865497075,
+      "grad_norm": 0.3285796344280243,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7794,
+      "step": 45
+    },
+    {
+      "epoch": 0.23911630929174787,
+      "grad_norm": 0.2986137270927429,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8368,
+      "step": 46
+    },
+    {
+      "epoch": 0.244314489928525,
+      "grad_norm": 0.3100530207157135,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8195,
+      "step": 47
+    },
+    {
+      "epoch": 0.24951267056530213,
+      "grad_norm": 0.2815369963645935,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8356,
+      "step": 48
+    },
+    {
+      "epoch": 0.25471085120207926,
+      "grad_norm": 0.3508853316307068,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7923,
+      "step": 49
+    },
+    {
+      "epoch": 0.2599090318388564,
+      "grad_norm": 0.39119306206703186,
+      "learning_rate": 0.0,
+      "loss": 0.787,
+      "step": 50
+    },
+    {
+      "epoch": 0.2599090318388564,
+      "eval_loss": 0.9067763090133667,
+      "eval_runtime": 83.1189,
+      "eval_samples_per_second": 15.604,
+      "eval_steps_per_second": 1.961,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null