Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f8a10163e1c607a1a57a28fee73c74a357f6e49581438c04af56f50fc5fe3a4
+oid sha256:ea0d7c1fc94de016f44936f18b0fdaffe6c2528de2fb0193eb5410389b1e38d6
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd68db2baa28803163b4919db4e440dfa82c3f140c9f35a91a6ad2ea02d27e51
+oid sha256:f80246fbf1f02377d9fd7317139b6ba742ca111c370c8455543506587948ceb9
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fd7e3cd478533769c0e9a79727aa3cf8a8fd40c805e6e934326a1898badebd7
+oid sha256:4b30a349dd88a6ccfcdbb3669462d1e5c566e5160fa6a5a3ee86e779808bae0d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eccb4d87266b4d019fd8f93bf25f2008b05a4f8389fb122cc39d8cdb143aca4
+oid sha256:92ae41baba07dde15f1d4cc1e8df93b8024f468ef4e1692e1b95c86311390e60
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a36978706a0afcad59f063b1485a0fe82014d33a1332bf4c8e643d094776c7
+oid sha256:f2be44f4be1818b48b5f521752676c4b1f04a779835fd48af3fe9c65a283653a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32ba2048215b3d493b5e3163f2d6c6ed36ca3f268d04d3c893f8a0626a84d478
+oid sha256:fda57b7dd862a2d239559b7bf6d73c02064b735484548022dfb0c712ba69465c
 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": 10.375017166137695,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06305170239596469,
+  "best_metric": 10.373420715332031,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12610340479192939,
   "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": 941.231,
       "eval_steps_per_second": 117.654,
       "step": 25
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 0.04510338976979256,
+      "learning_rate": 5e-05,
+      "loss": 10.3746,
+      "step": 26
+    },
+    {
+      "epoch": 0.06809583858764187,
+      "grad_norm": 0.045711468905210495,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3747,
+      "step": 27
+    },
+    {
+      "epoch": 0.07061790668348046,
+      "grad_norm": 0.04386696591973305,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3759,
+      "step": 28
+    },
+    {
+      "epoch": 0.07313997477931904,
+      "grad_norm": 0.045891132205724716,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3753,
+      "step": 29
+    },
+    {
+      "epoch": 0.07566204287515763,
+      "grad_norm": 0.04793156683444977,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.374,
+      "step": 30
+    },
+    {
+      "epoch": 0.07818411097099622,
+      "grad_norm": 0.05221310257911682,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3743,
+      "step": 31
+    },
+    {
+      "epoch": 0.0807061790668348,
+      "grad_norm": 0.051459524780511856,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.3736,
+      "step": 32
+    },
+    {
+      "epoch": 0.0832282471626734,
+      "grad_norm": 0.05057171732187271,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3746,
+      "step": 33
+    },
+    {
+      "epoch": 0.08575031525851198,
+      "grad_norm": 0.05461611598730087,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3743,
+      "step": 34
+    },
+    {
+      "epoch": 0.08827238335435057,
+      "grad_norm": 0.05995216593146324,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3727,
+      "step": 35
+    },
+    {
+      "epoch": 0.09079445145018916,
+      "grad_norm": 0.061333104968070984,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3725,
+      "step": 36
+    },
+    {
+      "epoch": 0.09331651954602774,
+      "grad_norm": 0.07217469811439514,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3731,
+      "step": 37
+    },
+    {
+      "epoch": 0.09583858764186633,
+      "grad_norm": 0.05127323046326637,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3735,
+      "step": 38
+    },
+    {
+      "epoch": 0.09836065573770492,
+      "grad_norm": 0.04944981634616852,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3738,
+      "step": 39
+    },
+    {
+      "epoch": 0.1008827238335435,
+      "grad_norm": 0.05343186855316162,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3733,
+      "step": 40
+    },
+    {
+      "epoch": 0.1034047919293821,
+      "grad_norm": 0.05616803839802742,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3744,
+      "step": 41
+    },
+    {
+      "epoch": 0.10592686002522068,
+      "grad_norm": 0.0577423982322216,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3737,
+      "step": 42
+    },
+    {
+      "epoch": 0.10844892812105927,
+      "grad_norm": 0.06030035391449928,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3739,
+      "step": 43
+    },
+    {
+      "epoch": 0.11097099621689786,
+      "grad_norm": 0.05783156305551529,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3731,
+      "step": 44
+    },
+    {
+      "epoch": 0.11349306431273644,
+      "grad_norm": 0.06098296493291855,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3737,
+      "step": 45
+    },
+    {
+      "epoch": 0.11601513240857503,
+      "grad_norm": 0.06156492978334427,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.372,
+      "step": 46
+    },
+    {
+      "epoch": 0.11853720050441362,
+      "grad_norm": 0.06359221786260605,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3731,
+      "step": 47
+    },
+    {
+      "epoch": 0.1210592686002522,
+      "grad_norm": 0.06486078351736069,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3731,
+      "step": 48
+    },
+    {
+      "epoch": 0.1235813366960908,
+      "grad_norm": 0.0683504045009613,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3725,
+      "step": 49
+    },
+    {
+      "epoch": 0.12610340479192939,
+      "grad_norm": 0.07451239973306656,
+      "learning_rate": 0.0,
+      "loss": 10.3729,
+      "step": 50
+    },
+    {
+      "epoch": 0.12610340479192939,
+      "eval_loss": 10.373420715332031,
+      "eval_runtime": 2.8358,
+      "eval_samples_per_second": 942.245,
+      "eval_steps_per_second": 117.781,
+      "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": 21450854891520.0,
+  "total_flos": 42888344764416.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null