Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6506ba8c450fa25aadaaef4de020b41e62623ef183bab4fea5f16f885d7a8b62
+oid sha256:82eb1ad5ab904437938f924d95582db88c7a2b63613c7e6a51d8398c05d60f2f
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d0bc5bbf500ca4c45ce7e9727d4675e56573877b5c7f563ecd001acd25d3c1
+oid sha256:e5ba72eaa49150b3b8cee902281326130f72b656b8bd7902a2edc52b9d8f8fb9
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78732252ebe2540999734269ea891831ad9be44083715d58b955246a72cafe50
+oid sha256:4ff10cf7359ca24cb1b61f9dd34efeffc00af092b4dcdb9262996112aded0e97
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5132614851b08848810c7eee81acd91c377d6575678abf388c76bbaf178e9086
+oid sha256:45f277c0806946faacd17cc3b40ae08f293c41f9decba0d99c1d73cc513a4082
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a773a14c0d9addb3ac0cac180485a0432a88541eded45cdd1f00d4fc518347f4
+oid sha256:3f4bba1b6733b8421fc645c7a4073b32d2b12d89bb8ea0819d3cdfd7d5906658
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e63d0323f44563eb0a49a200b1b7c56758432093eb766f50fe507e1aa6d75f9
+oid sha256:8abfc416806d21f78083738966cf03248173bd65eeb781e0d7300003ceb1dca8
 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": 0.06240265816450119,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.3535353535353536,
+  "best_metric": 0.035906072705984116,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.707070707070707,
   "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": 56.032,
       "eval_steps_per_second": 7.172,
       "step": 25
+    },
+    {
+      "epoch": 1.4074074074074074,
+      "grad_norm": 0.01792786456644535,
+      "learning_rate": 5e-05,
+      "loss": 0.0014,
+      "step": 26
+    },
+    {
+      "epoch": 1.4612794612794613,
+      "grad_norm": 0.032886262983083725,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0013,
+      "step": 27
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.10226934403181076,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0641,
+      "step": 28
+    },
+    {
+      "epoch": 1.569023569023569,
+      "grad_norm": 0.05436936393380165,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.031,
+      "step": 29
+    },
+    {
+      "epoch": 1.6228956228956228,
+      "grad_norm": 0.026059817522764206,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0036,
+      "step": 30
+    },
+    {
+      "epoch": 1.676767676767677,
+      "grad_norm": 0.010888765566051006,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.001,
+      "step": 31
+    },
+    {
+      "epoch": 1.7306397306397305,
+      "grad_norm": 0.023749791085720062,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0078,
+      "step": 32
+    },
+    {
+      "epoch": 1.7845117845117846,
+      "grad_norm": 0.12674275040626526,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1289,
+      "step": 33
+    },
+    {
+      "epoch": 1.8383838383838382,
+      "grad_norm": 0.02875218726694584,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0042,
+      "step": 34
+    },
+    {
+      "epoch": 1.8922558922558923,
+      "grad_norm": 0.00824170745909214,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0008,
+      "step": 35
+    },
+    {
+      "epoch": 1.9461279461279462,
+      "grad_norm": 0.009677278809249401,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0009,
+      "step": 36
+    },
+    {
+      "epoch": 2.006734006734007,
+      "grad_norm": 0.43559619784355164,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.118,
+      "step": 37
+    },
+    {
+      "epoch": 2.0606060606060606,
+      "grad_norm": 0.10613541305065155,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0728,
+      "step": 38
+    },
+    {
+      "epoch": 2.1144781144781146,
+      "grad_norm": 0.03015502355992794,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0039,
+      "step": 39
+    },
+    {
+      "epoch": 2.1683501683501682,
+      "grad_norm": 0.007468265946954489,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0007,
+      "step": 40
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 0.009618548676371574,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0008,
+      "step": 41
+    },
+    {
+      "epoch": 2.276094276094276,
+      "grad_norm": 0.16929568350315094,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1162,
+      "step": 42
+    },
+    {
+      "epoch": 2.32996632996633,
+      "grad_norm": 0.04619894549250603,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0228,
+      "step": 43
+    },
+    {
+      "epoch": 2.3838383838383836,
+      "grad_norm": 0.015330188907682896,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0021,
+      "step": 44
+    },
+    {
+      "epoch": 2.4377104377104377,
+      "grad_norm": 0.01087284553796053,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0008,
+      "step": 45
+    },
+    {
+      "epoch": 2.4915824915824913,
+      "grad_norm": 0.033908721059560776,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0099,
+      "step": 46
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.08616095781326294,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0797,
+      "step": 47
+    },
+    {
+      "epoch": 2.5993265993265995,
+      "grad_norm": 0.019008614122867584,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0024,
+      "step": 48
+    },
+    {
+      "epoch": 2.653198653198653,
+      "grad_norm": 0.007185245398432016,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0006,
+      "step": 49
+    },
+    {
+      "epoch": 2.707070707070707,
+      "grad_norm": 0.010233094915747643,
+      "learning_rate": 0.0,
+      "loss": 0.0008,
+      "step": 50
+    },
+    {
+      "epoch": 2.707070707070707,
+      "eval_loss": 0.035906072705984116,
+      "eval_runtime": 2.333,
+      "eval_samples_per_second": 53.578,
+      "eval_steps_per_second": 6.858,
+      "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": 6.363840211268403e+16,
+  "total_flos": 1.2542261584094822e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null