Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa077d3a355ae1e54df15bd96626e71d61bb2ca082474a315c6715f92cda8b2
+oid sha256:3678ffa4b81e749ccaf9b9cb2dc3671e9b7f93b15037debb91ec12d4f2a06c4f
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc4e5b2855e9d3ab15efbb5fa0c3a2b72f92cb67c15c74a3f06d4bb70917d3b0
+oid sha256:3ea7455a4a2d337bd46d97b55f45ae4d2b8db4c880ddaceca9ed732c6b8744b6
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab0370e635d1eecd0163bfb80471c5f5e2032e5d5b1150b4bfc99d7e8439a16b
+oid sha256:8a3489dc54604ccb1cfb35a29ba09b52477fcef0691778c3e4c5faa4468c0bd4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8860d1d85f1c31b5961671b57b045be0d4d7ede53c6c37ff45c43bbb002938dd
+oid sha256:009592e53ec1c886dce08bb090a407102420601aff3da92b9e8b763beb5775d0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e61691c78667214785bbfe249c6acad52ab9caa1be39b10704e4525979e2b66
+oid sha256:e9464d613bd8def9beb891798396f4cc5a6dec004d4dfc5a35cf46d50f1d23af
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8863a41abfb108d20926abff9b096418adf8e597150e20e729382f9c127bbae5
+oid sha256:54f75b6ce32c7089df83b4118b0d90f5a7b9281aceb52cd3bc3270203b8f4153
 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": 0.47236114740371704,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.057085771371485655,
+  "best_metric": 0.4648851156234741,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11417154274297131,
   "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": 14.739,
       "eval_steps_per_second": 1.843,
       "step": 25
+    },
+    {
+      "epoch": 0.059369202226345084,
+      "grad_norm": 0.11356440931558609,
+      "learning_rate": 5e-05,
+      "loss": 0.2328,
+      "step": 26
+    },
+    {
+      "epoch": 0.06165263308120451,
+      "grad_norm": 0.12556737661361694,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2785,
+      "step": 27
+    },
+    {
+      "epoch": 0.06393606393606394,
+      "grad_norm": 0.13164840638637543,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2977,
+      "step": 28
+    },
+    {
+      "epoch": 0.06621949479092336,
+      "grad_norm": 0.16159792244434357,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4175,
+      "step": 29
+    },
+    {
+      "epoch": 0.0685029256457828,
+      "grad_norm": 0.16275496780872345,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4616,
+      "step": 30
+    },
+    {
+      "epoch": 0.07078635650064222,
+      "grad_norm": 0.16565589606761932,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4595,
+      "step": 31
+    },
+    {
+      "epoch": 0.07306978735550164,
+      "grad_norm": 0.18394418060779572,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5079,
+      "step": 32
+    },
+    {
+      "epoch": 0.07535321821036106,
+      "grad_norm": 0.1702607125043869,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3712,
+      "step": 33
+    },
+    {
+      "epoch": 0.0776366490652205,
+      "grad_norm": 0.2136932760477066,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6439,
+      "step": 34
+    },
+    {
+      "epoch": 0.07992007992007992,
+      "grad_norm": 0.23648518323898315,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5586,
+      "step": 35
+    },
+    {
+      "epoch": 0.08220351077493934,
+      "grad_norm": 0.27319836616516113,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7303,
+      "step": 36
+    },
+    {
+      "epoch": 0.08448694162979878,
+      "grad_norm": 0.35524117946624756,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9086,
+      "step": 37
+    },
+    {
+      "epoch": 0.0867703724846582,
+      "grad_norm": 0.2031528353691101,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3624,
+      "step": 38
+    },
+    {
+      "epoch": 0.08905380333951762,
+      "grad_norm": 0.0991303101181984,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2811,
+      "step": 39
+    },
+    {
+      "epoch": 0.09133723419437705,
+      "grad_norm": 0.10457004606723785,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3733,
+      "step": 40
+    },
+    {
+      "epoch": 0.09362066504923648,
+      "grad_norm": 0.11494916677474976,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3843,
+      "step": 41
+    },
+    {
+      "epoch": 0.0959040959040959,
+      "grad_norm": 0.12473290413618088,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.434,
+      "step": 42
+    },
+    {
+      "epoch": 0.09818752675895533,
+      "grad_norm": 0.1304829865694046,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4221,
+      "step": 43
+    },
+    {
+      "epoch": 0.10047095761381476,
+      "grad_norm": 0.1233222633600235,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3852,
+      "step": 44
+    },
+    {
+      "epoch": 0.10275438846867418,
+      "grad_norm": 0.15903952717781067,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5617,
+      "step": 45
+    },
+    {
+      "epoch": 0.10503781932353361,
+      "grad_norm": 0.2569705843925476,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5424,
+      "step": 46
+    },
+    {
+      "epoch": 0.10732125017839303,
+      "grad_norm": 0.1869916319847107,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6157,
+      "step": 47
+    },
+    {
+      "epoch": 0.10960468103325247,
+      "grad_norm": 0.23289279639720917,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7795,
+      "step": 48
+    },
+    {
+      "epoch": 0.11188811188811189,
+      "grad_norm": 0.3144865036010742,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8344,
+      "step": 49
+    },
+    {
+      "epoch": 0.11417154274297131,
+      "grad_norm": 0.4401632845401764,
+      "learning_rate": 0.0,
+      "loss": 0.9783,
+      "step": 50
+    },
+    {
+      "epoch": 0.11417154274297131,
+      "eval_loss": 0.4648851156234741,
+      "eval_runtime": 200.2466,
+      "eval_samples_per_second": 14.737,
+      "eval_steps_per_second": 1.843,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null