Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e7dad5721839cd5390e48a91174b8e1586fd578cad01dcaf7c7ee98c68a0d6
+oid sha256:7ee64195cfaf692f9c28a7508259f7fff6fc223a804268a5ebdae140db14a544
 size 239135488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a01a86fd60467da555bbadec0635d0d796d3e9463da670d42787fd644873f3
+oid sha256:353dee1a902ea5733b8bf420a7b86077f24aaafaeab4839d82db9135ee094822
 size 478528978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f260aeffb4795a139068a0bf9eb0ebd7c453119a27783c0b844808429f6950f
+oid sha256:f79efd772aa1af31819eba4424cdc008f5e537ada64f3a13d7a29a3d4a8fb763
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1115bf3bbec98f87277336798a37dde25164b93185a039220533c78542d491cf
+oid sha256:884b970b6d70979d1f23edb2046cdccb1a9355c4f96f11f445dfff839599e9ca
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0cf339998451b7e32f7f4543ede6f1766156f701801bba5b81b914422bcec01
+oid sha256:ed903819a80e94a8371a6bfead58c7f73c36673ff95f7431e730e4b9b8b5769a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27339fec5b8524d1225d8028097d7f961ceb597dae5630f635b46ec02c5ff56
+oid sha256:d10d81585b037e622bc51cc178587d37f6147f4495450dd412c12fbb4e14db64
 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": 1.222367763519287,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3436426116838488,
+  "best_metric": 1.1700222492218018,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6872852233676976,
   "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": 20.635,
       "eval_steps_per_second": 2.611,
       "step": 25
+    },
+    {
+      "epoch": 0.35738831615120276,
+      "grad_norm": 8.447471618652344,
+      "learning_rate": 5e-05,
+      "loss": 1.3699,
+      "step": 26
+    },
+    {
+      "epoch": 0.3711340206185567,
+      "grad_norm": 6.330043315887451,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2511,
+      "step": 27
+    },
+    {
+      "epoch": 0.3848797250859107,
+      "grad_norm": 4.982043266296387,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1805,
+      "step": 28
+    },
+    {
+      "epoch": 0.39862542955326463,
+      "grad_norm": 5.331606864929199,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1521,
+      "step": 29
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 3.5054099559783936,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1404,
+      "step": 30
+    },
+    {
+      "epoch": 0.4261168384879725,
+      "grad_norm": 4.3697614669799805,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1858,
+      "step": 31
+    },
+    {
+      "epoch": 0.43986254295532645,
+      "grad_norm": 3.5054900646209717,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1712,
+      "step": 32
+    },
+    {
+      "epoch": 0.4536082474226804,
+      "grad_norm": 2.989226818084717,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0911,
+      "step": 33
+    },
+    {
+      "epoch": 0.46735395189003437,
+      "grad_norm": 3.1136281490325928,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1126,
+      "step": 34
+    },
+    {
+      "epoch": 0.48109965635738833,
+      "grad_norm": 3.8040785789489746,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.2245,
+      "step": 35
+    },
+    {
+      "epoch": 0.4948453608247423,
+      "grad_norm": 4.323892116546631,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.111,
+      "step": 36
+    },
+    {
+      "epoch": 0.5085910652920962,
+      "grad_norm": 4.997296333312988,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1923,
+      "step": 37
+    },
+    {
+      "epoch": 0.5223367697594502,
+      "grad_norm": 5.276499271392822,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4023,
+      "step": 38
+    },
+    {
+      "epoch": 0.5360824742268041,
+      "grad_norm": 3.8192012310028076,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2573,
+      "step": 39
+    },
+    {
+      "epoch": 0.5498281786941581,
+      "grad_norm": 3.393066883087158,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.2258,
+      "step": 40
+    },
+    {
+      "epoch": 0.563573883161512,
+      "grad_norm": 2.6232097148895264,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0416,
+      "step": 41
+    },
+    {
+      "epoch": 0.5773195876288659,
+      "grad_norm": 2.9142274856567383,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9755,
+      "step": 42
+    },
+    {
+      "epoch": 0.5910652920962199,
+      "grad_norm": 3.119406223297119,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1864,
+      "step": 43
+    },
+    {
+      "epoch": 0.6048109965635738,
+      "grad_norm": 2.5969648361206055,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.132,
+      "step": 44
+    },
+    {
+      "epoch": 0.6185567010309279,
+      "grad_norm": 2.6044764518737793,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1857,
+      "step": 45
+    },
+    {
+      "epoch": 0.6323024054982818,
+      "grad_norm": 2.9976484775543213,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1866,
+      "step": 46
+    },
+    {
+      "epoch": 0.6460481099656358,
+      "grad_norm": 3.2721643447875977,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1646,
+      "step": 47
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 4.761203289031982,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2401,
+      "step": 48
+    },
+    {
+      "epoch": 0.6735395189003437,
+      "grad_norm": 4.534084796905518,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.129,
+      "step": 49
+    },
+    {
+      "epoch": 0.6872852233676976,
+      "grad_norm": 8.279170036315918,
+      "learning_rate": 0.0,
+      "loss": 1.2175,
+      "step": 50
+    },
+    {
+      "epoch": 0.6872852233676976,
+      "eval_loss": 1.1700222492218018,
+      "eval_runtime": 23.7368,
+      "eval_samples_per_second": 20.643,
+      "eval_steps_per_second": 2.612,
+      "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": 1.48820921749078e+17,
+  "total_flos": 2.975488880578396e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null