Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7960cc1bd077ae8941056a3e8a84f9f327234b9aa743930c8e4e166882c9ddaa
+oid sha256:f9813dcda2c4b07bf42508cd4b45c5d7fbabffdf5d62cddf5d3e8cd089b3fdaa
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a24dda9e50cbdcf8b11300dc95c09fa8422fac9d1fb50558a38b8f9fd0d0f13
+oid sha256:8907e39cb62c1be71d4e341c74e39294f0c02a12bd3ecd676fdc549f5c74509b
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d655597b6493194b48a516399e938b97d9c561d8de804c11dcc5eb582c18f090
+oid sha256:158530d8687d19bb7ac1190ed5b1ce5644af446198f79b479b8b67d17de7f3b2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ead1cc142ab71eb1307c7ca80ca8231def0a6e797b9f45e0c09b00ebe82197
+oid sha256:c7260a16ba81411eee4e514500694da415d210a4cb96656c714816df867189d7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e75dfa0220de44b06e228308bd77992edf46c7082d5a39a893820f6e74aa8290
+oid sha256:47557b830a801c959dceb8c5765a24db25cf5de1232f089e77436cf98832069b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a93111b56adaa73fd0d99f73975afc52b6b89456991d53e49ea9adadfdf98c93
+oid sha256:4569cec8ffc71ab9e26d4788266e3857bdb6a8c75c945d1dd2d31dcbe753c23c
 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": 1.325190544128418,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.0526315789473684,
+  "best_metric": 1.3032262325286865,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.1052631578947367,
   "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": 13.7,
       "eval_steps_per_second": 1.712,
       "step": 25
+    },
+    {
+      "epoch": 1.0947368421052632,
+      "grad_norm": 1.974260926246643,
+      "learning_rate": 5e-05,
+      "loss": 1.148,
+      "step": 26
+    },
+    {
+      "epoch": 1.1368421052631579,
+      "grad_norm": 1.4720616340637207,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0633,
+      "step": 27
+    },
+    {
+      "epoch": 1.1789473684210527,
+      "grad_norm": 1.7669459581375122,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.048,
+      "step": 28
+    },
+    {
+      "epoch": 1.2210526315789474,
+      "grad_norm": 1.6160643100738525,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9753,
+      "step": 29
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 1.6384661197662354,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1493,
+      "step": 30
+    },
+    {
+      "epoch": 1.305263157894737,
+      "grad_norm": 2.024684190750122,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2016,
+      "step": 31
+    },
+    {
+      "epoch": 1.3473684210526315,
+      "grad_norm": 1.9289146661758423,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1616,
+      "step": 32
+    },
+    {
+      "epoch": 1.3894736842105262,
+      "grad_norm": 1.6927998065948486,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0759,
+      "step": 33
+    },
+    {
+      "epoch": 1.431578947368421,
+      "grad_norm": 2.006455183029175,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0973,
+      "step": 34
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 1.6544878482818604,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9614,
+      "step": 35
+    },
+    {
+      "epoch": 1.5157894736842106,
+      "grad_norm": 1.626354455947876,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1881,
+      "step": 36
+    },
+    {
+      "epoch": 1.5578947368421052,
+      "grad_norm": 2.013545036315918,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1426,
+      "step": 37
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.9105583429336548,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0589,
+      "step": 38
+    },
+    {
+      "epoch": 1.6421052631578947,
+      "grad_norm": 2.017082929611206,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0208,
+      "step": 39
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 1.7792869806289673,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9717,
+      "step": 40
+    },
+    {
+      "epoch": 1.7263157894736842,
+      "grad_norm": 1.467813491821289,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.72,
+      "step": 41
+    },
+    {
+      "epoch": 1.768421052631579,
+      "grad_norm": 1.8371200561523438,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3269,
+      "step": 42
+    },
+    {
+      "epoch": 1.8105263157894735,
+      "grad_norm": 2.0505716800689697,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2772,
+      "step": 43
+    },
+    {
+      "epoch": 1.8526315789473684,
+      "grad_norm": 1.8300319910049438,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0593,
+      "step": 44
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 1.950974941253662,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.0374,
+      "step": 45
+    },
+    {
+      "epoch": 1.936842105263158,
+      "grad_norm": 1.9078106880187988,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9833,
+      "step": 46
+    },
+    {
+      "epoch": 1.9789473684210526,
+      "grad_norm": 2.3406636714935303,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.2057,
+      "step": 47
+    },
+    {
+      "epoch": 2.0210526315789474,
+      "grad_norm": 1.7886607646942139,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1742,
+      "step": 48
+    },
+    {
+      "epoch": 2.0631578947368423,
+      "grad_norm": 1.9798243045806885,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0736,
+      "step": 49
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 1.969590187072754,
+      "learning_rate": 0.0,
+      "loss": 0.9799,
+      "step": 50
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "eval_loss": 1.3032262325286865,
+      "eval_runtime": 11.6161,
+      "eval_samples_per_second": 13.774,
+      "eval_steps_per_second": 1.722,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null