Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:186ac800f44954ef4d542c73531800a46e02815660f968032ef5c4d47f4a3d18
+oid sha256:28ab23742f582f200ee4159d7e8d43253642d6d6da864c3d79c5cd38057bb1a5
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7407a9d676e4dfd7ee21ab1a262367c736b81d74c45db0bb4d2a80714c98a36
+oid sha256:c99a206669a59070ca153f4e7d0616e5c8ea41b59938228dda10506718f06147
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30bc5a248fd783686bff9c91de44ab3a09fdb074020a16fb27cb757f55c1a7ca
+oid sha256:3509f9b273831bcf2f3b7e0bf387ac994433c069765fa009d72c985f9257fd92
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8185df3d1810c3fedc47dd8945e56be79a564e695069d03afce18eb0ea4b146c
+oid sha256:860738b9285355f639b8ab206327071da89aef6c4f2743e226b63ef5b2c172e3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b281cd06cbb97f0387a9fac0f936a2011ca3e75dfa9213447f431ba7153ce5
+oid sha256:e4c4baa767e87b56e8d6169e463b6b4df7c98af370700ae0ae451a50afb1e3c1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe459f0fbfd2d3a487fcf34164f6d915a42c95f6538ca1b8dbc316c34c8543e
+oid sha256:17b8da959edd02f7a6d7a910e069f4cf41809351ea486d6a13a5295f00f008dc
 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": 0.7877915501594543,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008217602103706138,
+  "best_metric": 0.7489719390869141,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.016435204207412277,
   "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": 11.297,
       "eval_steps_per_second": 1.412,
       "step": 25
+    },
+    {
+      "epoch": 0.008546306187854385,
+      "grad_norm": 1.6266748905181885,
+      "learning_rate": 5e-05,
+      "loss": 0.7129,
+      "step": 26
+    },
+    {
+      "epoch": 0.00887501027200263,
+      "grad_norm": 1.2160279750823975,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7406,
+      "step": 27
+    },
+    {
+      "epoch": 0.009203714356150874,
+      "grad_norm": 1.0015685558319092,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7597,
+      "step": 28
+    },
+    {
+      "epoch": 0.009532418440299121,
+      "grad_norm": 0.55552738904953,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.737,
+      "step": 29
+    },
+    {
+      "epoch": 0.009861122524447366,
+      "grad_norm": 0.5415008664131165,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7192,
+      "step": 30
+    },
+    {
+      "epoch": 0.010189826608595612,
+      "grad_norm": 1.0667164325714111,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.738,
+      "step": 31
+    },
+    {
+      "epoch": 0.010518530692743857,
+      "grad_norm": 1.0163336992263794,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7654,
+      "step": 32
+    },
+    {
+      "epoch": 0.010847234776892103,
+      "grad_norm": 0.5743635296821594,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7435,
+      "step": 33
+    },
+    {
+      "epoch": 0.011175938861040348,
+      "grad_norm": 0.6187846660614014,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7465,
+      "step": 34
+    },
+    {
+      "epoch": 0.011504642945188595,
+      "grad_norm": 0.5016359686851501,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7376,
+      "step": 35
+    },
+    {
+      "epoch": 0.01183334702933684,
+      "grad_norm": 0.46876969933509827,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7177,
+      "step": 36
+    },
+    {
+      "epoch": 0.012162051113485084,
+      "grad_norm": 0.546317458152771,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6776,
+      "step": 37
+    },
+    {
+      "epoch": 0.01249075519763333,
+      "grad_norm": 0.6002888083457947,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6374,
+      "step": 38
+    },
+    {
+      "epoch": 0.012819459281781576,
+      "grad_norm": 0.9599287509918213,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6531,
+      "step": 39
+    },
+    {
+      "epoch": 0.013148163365929822,
+      "grad_norm": 0.32457417249679565,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7018,
+      "step": 40
+    },
+    {
+      "epoch": 0.013476867450078067,
+      "grad_norm": 0.39083102345466614,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7042,
+      "step": 41
+    },
+    {
+      "epoch": 0.013805571534226313,
+      "grad_norm": 0.38013777136802673,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7211,
+      "step": 42
+    },
+    {
+      "epoch": 0.014134275618374558,
+      "grad_norm": 0.7130141258239746,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7401,
+      "step": 43
+    },
+    {
+      "epoch": 0.014462979702522805,
+      "grad_norm": 0.433555006980896,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6968,
+      "step": 44
+    },
+    {
+      "epoch": 0.01479168378667105,
+      "grad_norm": 0.5339280366897583,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6373,
+      "step": 45
+    },
+    {
+      "epoch": 0.015120387870819294,
+      "grad_norm": 0.5228230357170105,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7326,
+      "step": 46
+    },
+    {
+      "epoch": 0.01544909195496754,
+      "grad_norm": 0.8945353031158447,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7346,
+      "step": 47
+    },
+    {
+      "epoch": 0.015777796039115787,
+      "grad_norm": 0.7894071340560913,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7375,
+      "step": 48
+    },
+    {
+      "epoch": 0.01610650012326403,
+      "grad_norm": 0.5900431275367737,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6634,
+      "step": 49
+    },
+    {
+      "epoch": 0.016435204207412277,
+      "grad_norm": 0.824525773525238,
+      "learning_rate": 0.0,
+      "loss": 0.6322,
+      "step": 50
+    },
+    {
+      "epoch": 0.016435204207412277,
+      "eval_loss": 0.7489719390869141,
+      "eval_runtime": 981.6847,
+      "eval_samples_per_second": 20.877,
+      "eval_steps_per_second": 2.61,
+      "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": 5.114180768104448e+17,
+  "total_flos": 1.0228361536208896e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null