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:e97dcd265e0ef1809cec84781a48938d71375f9fd3d71f03e7045cd1fafe0d38
+oid sha256:33c90abe66eeadcaf358d9fed5f8e68011b996c69f75db55597ca00142368514
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:931f9aa8dd128492fd2cc126ff60636681a2b37222db5e80c36d8e2ec943f162
+oid sha256:1d05641099aa6ca29db080b6675eaa117ecf518faf2ed58b7278a5f2b5b76c28
 size 389352298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e8777f5a4aabc0d8ac1efd3a6e33c92dec1d063a3f29117c64acd0a42b5973e
+oid sha256:415c810aebb61771d3acb8d3ed59f542f36852ded9b9987c705e4576801c8af9
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9efc6d27ebcecf56aefd1c24b29b0cb61d28f11d7a76dd255d4acbedb809181
+oid sha256:15ed8de7effcaf059b770c3038cc4480b65454a28666c4626ba403df78f9e6ee
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b31720f40247d5e3cf9fed02e3f19f9aea2aae89903264531d7eda2fa736b033
+oid sha256:255130f0f3cc23b9e5a4a08e74ca02c4e717ae9d810814b9abae63bf91957994
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4afc5ce36dd06331a909f3eba9520efe079a6ffbb96df4f70ac474501b673e00
+oid sha256:554d5542be24120b616d529ae468107d508278766965acea0209c82ac9b35de7
 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": 0.5813907384872437,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.27229407760381213,
+  "best_metric": 0.25502192974090576,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5445881552076243,
   "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": 55.61,
       "eval_steps_per_second": 7.007,
       "step": 25
+    },
+    {
+      "epoch": 0.2831858407079646,
+      "grad_norm": 2.464270830154419,
+      "learning_rate": 5e-05,
+      "loss": 0.5738,
+      "step": 26
+    },
+    {
+      "epoch": 0.29407760381211706,
+      "grad_norm": 2.69157338142395,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5481,
+      "step": 27
+    },
+    {
+      "epoch": 0.3049693669162696,
+      "grad_norm": 1.5113294124603271,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5112,
+      "step": 28
+    },
+    {
+      "epoch": 0.31586113002042204,
+      "grad_norm": 1.6194149255752563,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4175,
+      "step": 29
+    },
+    {
+      "epoch": 0.32675289312457456,
+      "grad_norm": 2.4440693855285645,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.417,
+      "step": 30
+    },
+    {
+      "epoch": 0.337644656228727,
+      "grad_norm": 2.4268813133239746,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.3865,
+      "step": 31
+    },
+    {
+      "epoch": 0.3485364193328795,
+      "grad_norm": 2.906593084335327,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4172,
+      "step": 32
+    },
+    {
+      "epoch": 0.359428182437032,
+      "grad_norm": 1.8728927373886108,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2971,
+      "step": 33
+    },
+    {
+      "epoch": 0.37031994554118447,
+      "grad_norm": 3.3725411891937256,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3505,
+      "step": 34
+    },
+    {
+      "epoch": 0.381211708645337,
+      "grad_norm": 2.383547067642212,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3038,
+      "step": 35
+    },
+    {
+      "epoch": 0.39210347174948945,
+      "grad_norm": 2.2084460258483887,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3124,
+      "step": 36
+    },
+    {
+      "epoch": 0.4029952348536419,
+      "grad_norm": 2.340491771697998,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2721,
+      "step": 37
+    },
+    {
+      "epoch": 0.41388699795779443,
+      "grad_norm": 2.8425796031951904,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3493,
+      "step": 38
+    },
+    {
+      "epoch": 0.4247787610619469,
+      "grad_norm": 1.770458698272705,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2772,
+      "step": 39
+    },
+    {
+      "epoch": 0.43567052416609936,
+      "grad_norm": 2.0324440002441406,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3137,
+      "step": 40
+    },
+    {
+      "epoch": 0.4465622872702519,
+      "grad_norm": 1.6991618871688843,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2973,
+      "step": 41
+    },
+    {
+      "epoch": 0.45745405037440434,
+      "grad_norm": 1.9309918880462646,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3162,
+      "step": 42
+    },
+    {
+      "epoch": 0.46834581347855686,
+      "grad_norm": 1.798869252204895,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2602,
+      "step": 43
+    },
+    {
+      "epoch": 0.4792375765827093,
+      "grad_norm": 1.7334697246551514,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2819,
+      "step": 44
+    },
+    {
+      "epoch": 0.4901293396868618,
+      "grad_norm": 2.004193067550659,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3022,
+      "step": 45
+    },
+    {
+      "epoch": 0.5010211027910143,
+      "grad_norm": 1.3644194602966309,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2163,
+      "step": 46
+    },
+    {
+      "epoch": 0.5119128658951668,
+      "grad_norm": 1.6829291582107544,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3081,
+      "step": 47
+    },
+    {
+      "epoch": 0.5228046289993192,
+      "grad_norm": 1.201421856880188,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2756,
+      "step": 48
+    },
+    {
+      "epoch": 0.5336963921034718,
+      "grad_norm": 1.3379050493240356,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2207,
+      "step": 49
+    },
+    {
+      "epoch": 0.5445881552076243,
+      "grad_norm": 1.5710933208465576,
+      "learning_rate": 0.0,
+      "loss": 0.2275,
+      "step": 50
+    },
+    {
+      "epoch": 0.5445881552076243,
+      "eval_loss": 0.25502192974090576,
+      "eval_runtime": 11.1383,
+      "eval_samples_per_second": 55.574,
+      "eval_steps_per_second": 7.003,
+      "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": 1.127497768894464e+17,
+  "total_flos": 2.254995537788928e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null