Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9343486b7c8cf8f067e378095bbc25b482c952be301d98c4c8ba89f97ea2bc
+oid sha256:a0774f6da9dc070528147c58986d22881ec9929d61f43c0b49b07a266c8999bb
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:545b39fe7ee6de4dbf03a5fec3bfcb3eee135870c7d066382c7d106def7cae3a
+oid sha256:8058c3c7a681577547e46061b99d804cb2a8c8fbf0b6343160b8e4ccb7cc9587
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a24577a68a9527e94039e13d23e5c8a7c8b5ee145566bb72c30f820671ee4cd
+oid sha256:2e1047c4d666842501fbc8cc2ba2a91b15a21e7aebc6e63cfd0c372e41fed1e5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a9783a85a76af3855bba35e5afaa380245753fb0338f726ba1b58d948262402
+oid sha256:a5aa105df214d068ac7ab2ce4fbdd4db70b4217d338883e8934368a0c11055ea
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9abad523426db24bc6016f85b12ed9b4dccdd637ba13bc196721533012f80ac
+oid sha256:9797e7efab3bdd97bd4967edf2b27afa96dd720d2c7d3150db45b7e135f3a4e8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b5d5d1489dfb93ec1aa3663343dcf538b4ae0794712da9c02ec68eca3bad0c
+oid sha256:64e4a802001e7ecda4b8c611660a63a6f88ebf07e0bb80c56c7bd4d12613a80f
 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": 0.9185070395469666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6606110652353427,
+  "best_metric": 0.9007372856140137,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.328654004954583,
   "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": 35.113,
       "eval_steps_per_second": 4.406,
       "step": 25
+    },
+    {
+      "epoch": 0.6870355078447564,
+      "grad_norm": 0.4967907667160034,
+      "learning_rate": 5e-05,
+      "loss": 0.9383,
+      "step": 26
+    },
+    {
+      "epoch": 0.7134599504541701,
+      "grad_norm": 0.3578830063343048,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.906,
+      "step": 27
+    },
+    {
+      "epoch": 0.7398843930635838,
+      "grad_norm": 0.40701600909233093,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9408,
+      "step": 28
+    },
+    {
+      "epoch": 0.7663088356729976,
+      "grad_norm": 0.4491502046585083,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9597,
+      "step": 29
+    },
+    {
+      "epoch": 0.7927332782824112,
+      "grad_norm": 0.2592903673648834,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9551,
+      "step": 30
+    },
+    {
+      "epoch": 0.8191577208918249,
+      "grad_norm": 0.1899711787700653,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.9402,
+      "step": 31
+    },
+    {
+      "epoch": 0.8455821635012386,
+      "grad_norm": 0.33069103956222534,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9352,
+      "step": 32
+    },
+    {
+      "epoch": 0.8720066061106524,
+      "grad_norm": 0.4107014834880829,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9186,
+      "step": 33
+    },
+    {
+      "epoch": 0.8984310487200661,
+      "grad_norm": 0.3768468201160431,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9166,
+      "step": 34
+    },
+    {
+      "epoch": 0.9248554913294798,
+      "grad_norm": 0.1930578052997589,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8981,
+      "step": 35
+    },
+    {
+      "epoch": 0.9512799339388934,
+      "grad_norm": 0.2350042760372162,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8844,
+      "step": 36
+    },
+    {
+      "epoch": 0.9777043765483072,
+      "grad_norm": 0.6842407584190369,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8483,
+      "step": 37
+    },
+    {
+      "epoch": 1.0115606936416186,
+      "grad_norm": 0.49989911913871765,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4444,
+      "step": 38
+    },
+    {
+      "epoch": 1.0379851362510322,
+      "grad_norm": 0.23442403972148895,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8976,
+      "step": 39
+    },
+    {
+      "epoch": 1.064409578860446,
+      "grad_norm": 0.2569376230239868,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9354,
+      "step": 40
+    },
+    {
+      "epoch": 1.0908340214698595,
+      "grad_norm": 0.31655338406562805,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9327,
+      "step": 41
+    },
+    {
+      "epoch": 1.1172584640792733,
+      "grad_norm": 0.27351218461990356,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9258,
+      "step": 42
+    },
+    {
+      "epoch": 1.143682906688687,
+      "grad_norm": 0.3348250389099121,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9264,
+      "step": 43
+    },
+    {
+      "epoch": 1.1701073492981007,
+      "grad_norm": 0.303664892911911,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8842,
+      "step": 44
+    },
+    {
+      "epoch": 1.1965317919075145,
+      "grad_norm": 0.44823157787323,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9372,
+      "step": 45
+    },
+    {
+      "epoch": 1.2229562345169283,
+      "grad_norm": 0.31823575496673584,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9131,
+      "step": 46
+    },
+    {
+      "epoch": 1.2493806771263418,
+      "grad_norm": 0.2725352942943573,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7334,
+      "step": 47
+    },
+    {
+      "epoch": 1.2758051197357556,
+      "grad_norm": 0.12976203858852386,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0483,
+      "step": 48
+    },
+    {
+      "epoch": 1.3022295623451692,
+      "grad_norm": 0.139130100607872,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9324,
+      "step": 49
+    },
+    {
+      "epoch": 1.328654004954583,
+      "grad_norm": 0.1179971992969513,
+      "learning_rate": 0.0,
+      "loss": 0.9317,
+      "step": 50
+    },
+    {
+      "epoch": 1.328654004954583,
+      "eval_loss": 0.9007372856140137,
+      "eval_runtime": 22.3252,
+      "eval_samples_per_second": 22.844,
+      "eval_steps_per_second": 2.867,
+      "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": 5.259104775831552e+17,
+  "total_flos": 1.0518209551663104e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null