Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eb0b684288821f7c474a95e338e6bcd6f6cac2752ce491405102333c18b94f2
+oid sha256:f2e49c0f8f3e5587ddabf952908d9565adc7e92c8455934d52a66e71e5f2e875
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f3f7a34d4d7c6d0f8532499a6687a665d373480d7b741eaaee8ca47b6ee0b6
+oid sha256:7c80deb9847d37d3c1d902321dfd9ac333b913c5a7730f17c12061734954129c
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199679a5570b3d80f9db1dfc78253b48a1d25d424c271593a6f684591c55fa32
+oid sha256:8307a95a445c6c3c6d6adb7b5b8947346e970925bf6c1cd8b1c2d7beaaf0724e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8e018497765191234cf8f999553a28bc532ed6d7325704e76b730904c5db91a
+oid sha256:c055cb833c212667b3e2137da59a37b08ee962420d9be2660fc4bed42687741c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:837de1c9255ec92e3b09332834b3d8de162c220ab144602b1535e30f09cd1751
+oid sha256:cad60c58c63c48dd0c8620abf6ce86c5d9b66a313dbc02f34b5d38e56911ba0e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8032617815a85e397318d53089fda2129ec6e3f822bebd8a66aec29af8f51f6
+oid sha256:53e6b43dd868ebd6c8af86705f0098f65e03aee940c7b06fa24133a252adba01
 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": 1.208978295326233,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03390405153415833,
+  "best_metric": 1.1890357732772827,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06780810306831667,
   "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": 60.105,
       "eval_steps_per_second": 7.513,
       "step": 25
+    },
+    {
+      "epoch": 0.03526021359552466,
+      "grad_norm": 0.389554500579834,
+      "learning_rate": 5e-05,
+      "loss": 1.2252,
+      "step": 26
+    },
+    {
+      "epoch": 0.036616375656891,
+      "grad_norm": 0.384280264377594,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2031,
+      "step": 27
+    },
+    {
+      "epoch": 0.03797253771825733,
+      "grad_norm": 0.38361260294914246,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2121,
+      "step": 28
+    },
+    {
+      "epoch": 0.039328699779623666,
+      "grad_norm": 0.36062079668045044,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.231,
+      "step": 29
+    },
+    {
+      "epoch": 0.040684861840989996,
+      "grad_norm": 0.38161206245422363,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1932,
+      "step": 30
+    },
+    {
+      "epoch": 0.04204102390235633,
+      "grad_norm": 0.3707989454269409,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2412,
+      "step": 31
+    },
+    {
+      "epoch": 0.04339718596372266,
+      "grad_norm": 0.3845455050468445,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1926,
+      "step": 32
+    },
+    {
+      "epoch": 0.044753348025089,
+      "grad_norm": 0.37922942638397217,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2045,
+      "step": 33
+    },
+    {
+      "epoch": 0.04610951008645533,
+      "grad_norm": 0.3843218684196472,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2378,
+      "step": 34
+    },
+    {
+      "epoch": 0.047465672147821665,
+      "grad_norm": 0.4299803376197815,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1565,
+      "step": 35
+    },
+    {
+      "epoch": 0.048821834209187995,
+      "grad_norm": 0.3997567296028137,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1827,
+      "step": 36
+    },
+    {
+      "epoch": 0.05017799627055433,
+      "grad_norm": 0.41545793414115906,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2315,
+      "step": 37
+    },
+    {
+      "epoch": 0.05153415833192066,
+      "grad_norm": 0.4381093382835388,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2169,
+      "step": 38
+    },
+    {
+      "epoch": 0.052890320393287,
+      "grad_norm": 0.40602096915245056,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2269,
+      "step": 39
+    },
+    {
+      "epoch": 0.054246482454653334,
+      "grad_norm": 0.40004175901412964,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.2234,
+      "step": 40
+    },
+    {
+      "epoch": 0.055602644516019664,
+      "grad_norm": 0.3891931176185608,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2178,
+      "step": 41
+    },
+    {
+      "epoch": 0.056958806577386,
+      "grad_norm": 0.3980973958969116,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1764,
+      "step": 42
+    },
+    {
+      "epoch": 0.05831496863875233,
+      "grad_norm": 0.35641881823539734,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1581,
+      "step": 43
+    },
+    {
+      "epoch": 0.05967113070011867,
+      "grad_norm": 0.38389772176742554,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1908,
+      "step": 44
+    },
+    {
+      "epoch": 0.061027292761485,
+      "grad_norm": 0.37814661860466003,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.178,
+      "step": 45
+    },
+    {
+      "epoch": 0.062383454822851334,
+      "grad_norm": 0.37529122829437256,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2016,
+      "step": 46
+    },
+    {
+      "epoch": 0.06373961688421767,
+      "grad_norm": 0.37107303738594055,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1675,
+      "step": 47
+    },
+    {
+      "epoch": 0.06509577894558399,
+      "grad_norm": 0.374933123588562,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1817,
+      "step": 48
+    },
+    {
+      "epoch": 0.06645194100695033,
+      "grad_norm": 0.4079557955265045,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1845,
+      "step": 49
+    },
+    {
+      "epoch": 0.06780810306831667,
+      "grad_norm": 0.4347075819969177,
+      "learning_rate": 0.0,
+      "loss": 1.2665,
+      "step": 50
+    },
+    {
+      "epoch": 0.06780810306831667,
+      "eval_loss": 1.1890357732772827,
+      "eval_runtime": 82.6203,
+      "eval_samples_per_second": 60.13,
+      "eval_steps_per_second": 7.516,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null