Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c7001055ffd0d426d7e788bd3056cc307b28f2bfc8a69917bc13f23f1961f20
+oid sha256:9bc6a4f39828edc4ffd3f6f6614abb2a41084b35fbb615a5a92496ae2bb2c14a
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7728dfb4b7f063b9126c9f05c7e9099eb76b91d1b5ea7254f06a2207ec6e2269
+oid sha256:384237e6696bfe3db8544a099f5d8ef3105f35808b91d59523b924a73d62c389
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d74760e23a51feb182cd56b7dad3b22cc43cf6a66e9b4f01eb6ea734f83251d
+oid sha256:5f1082f1367e4db75f9481c0954ecd8a71c84d4fefbc84b1c050c22b0ec07b56
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a4075c1a31c7fe9ceca6fb6cb7c7b1468b48dc9b1b4aaa8873cf6416887148
+oid sha256:7c9e3c53a53a0711883ed76c850c958806da422dbe59feab0a44a56d39a458b1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c67b06bf9d8cefe9b72f966dc698d7452ec8e9a228ab9292cf49ed88ed72c8d
+oid sha256:31551953999b990b820f19f75d8cfd3e4fa30d98638be7fce4e4cc70f4e7f12a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85bea8d266f8449bb32599efd72ce36ca95a882f9341f47fe2f84ffc9f3c3e93
+oid sha256:66e8effa30ce650f995d7f5f7f1fc29c7c48303ab7377570dc7594a0e2c310cd
 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": 0.08566731959581375,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.049813200498132,
+  "best_metric": 0.07000692188739777,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.099626400996264,
   "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": 18.982,
       "eval_steps_per_second": 2.374,
       "step": 25
+    },
+    {
+      "epoch": 0.05180572851805729,
+      "grad_norm": 0.8699737787246704,
+      "learning_rate": 5e-05,
+      "loss": 0.1004,
+      "step": 26
+    },
+    {
+      "epoch": 0.053798256537982564,
+      "grad_norm": 0.8566436767578125,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0937,
+      "step": 27
+    },
+    {
+      "epoch": 0.05579078455790785,
+      "grad_norm": 0.5181081295013428,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0614,
+      "step": 28
+    },
+    {
+      "epoch": 0.057783312577833125,
+      "grad_norm": 0.5177028775215149,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.032,
+      "step": 29
+    },
+    {
+      "epoch": 0.05977584059775841,
+      "grad_norm": 1.0031803846359253,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1306,
+      "step": 30
+    },
+    {
+      "epoch": 0.061768368617683686,
+      "grad_norm": 0.4737119674682617,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0628,
+      "step": 31
+    },
+    {
+      "epoch": 0.06376089663760896,
+      "grad_norm": 0.5609166026115417,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0475,
+      "step": 32
+    },
+    {
+      "epoch": 0.06575342465753424,
+      "grad_norm": 0.5264493227005005,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0483,
+      "step": 33
+    },
+    {
+      "epoch": 0.06774595267745953,
+      "grad_norm": 0.7822133302688599,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0757,
+      "step": 34
+    },
+    {
+      "epoch": 0.06973848069738481,
+      "grad_norm": 0.7832434773445129,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.106,
+      "step": 35
+    },
+    {
+      "epoch": 0.07173100871731009,
+      "grad_norm": 0.5009177327156067,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.055,
+      "step": 36
+    },
+    {
+      "epoch": 0.07372353673723536,
+      "grad_norm": 0.6237021088600159,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0542,
+      "step": 37
+    },
+    {
+      "epoch": 0.07571606475716065,
+      "grad_norm": 0.39433857798576355,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0511,
+      "step": 38
+    },
+    {
+      "epoch": 0.07770859277708593,
+      "grad_norm": 0.3575327694416046,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0488,
+      "step": 39
+    },
+    {
+      "epoch": 0.07970112079701121,
+      "grad_norm": 0.5723154544830322,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0467,
+      "step": 40
+    },
+    {
+      "epoch": 0.08169364881693648,
+      "grad_norm": 1.301767110824585,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0974,
+      "step": 41
+    },
+    {
+      "epoch": 0.08368617683686176,
+      "grad_norm": 0.9579374194145203,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1057,
+      "step": 42
+    },
+    {
+      "epoch": 0.08567870485678705,
+      "grad_norm": 1.0192933082580566,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0922,
+      "step": 43
+    },
+    {
+      "epoch": 0.08767123287671233,
+      "grad_norm": 0.7005112767219543,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0979,
+      "step": 44
+    },
+    {
+      "epoch": 0.0896637608966376,
+      "grad_norm": 0.7229822874069214,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0755,
+      "step": 45
+    },
+    {
+      "epoch": 0.09165628891656288,
+      "grad_norm": 0.5561147928237915,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0575,
+      "step": 46
+    },
+    {
+      "epoch": 0.09364881693648817,
+      "grad_norm": 0.74355149269104,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.114,
+      "step": 47
+    },
+    {
+      "epoch": 0.09564134495641345,
+      "grad_norm": 0.6839411854743958,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0613,
+      "step": 48
+    },
+    {
+      "epoch": 0.09763387297633873,
+      "grad_norm": 0.6341777443885803,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0948,
+      "step": 49
+    },
+    {
+      "epoch": 0.099626400996264,
+      "grad_norm": 0.6757367849349976,
+      "learning_rate": 0.0,
+      "loss": 0.0959,
+      "step": 50
+    },
+    {
+      "epoch": 0.099626400996264,
+      "eval_loss": 0.07000692188739777,
+      "eval_runtime": 178.1865,
+      "eval_samples_per_second": 18.98,
+      "eval_steps_per_second": 2.374,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null