Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc426d58f8cbaa88ce780b1eba5c99536c1aba4f12b1aaef5a7b080f21b0a06
+oid sha256:9cd2f3798114738fbb7b4d33feca0786668da0dee8627b9b271f48d96716a66f
 size 493712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe237c6edb55b4e9963d7f3e16d5ff60e896d79e7091106eabdadf97ffdf0fce
+oid sha256:14d6759e3ae0e1554a54d29d194325801ebef576130ea85a24ba5868cf6bbe6d
 size 997038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3054f131890c3e8f7fc99a5736982df20f222680c7a6f4ce24128ff3d5de7035
+oid sha256:03d21f8ada139e0d94cbdf41120e680d98cd52de64379b35746887cf7665808f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:153fd614be4b3925e9bcb30b1632ba48f8ba1f8c2c50bb830325911f5230d75e
+oid sha256:3ff2e853122eca61229ff1f4bcc10ca2cf1b155f2d0e0054ab9b24ab4df2f6ba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71d8514b945c4b1a14efeb05e4fb55f156c984a2e9b46ac5585ff3fe509e6718
+oid sha256:7a9b6c635f887cd494d9a0f751ffbe9aea8d01c067ddb04605984bd93caea282
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11669ac18ef0736467fd2443e4cc6860914461da1b231b13bb8e24ca0f6280e0
+oid sha256:95e69fade7a9f64af8819819829be029cdec8a8ac8ac32633852ed516176250b
 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": 10.954909324645996,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.059889204970804015,
+  "best_metric": 10.908712387084961,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11977840994160803,
   "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": 884.535,
       "eval_steps_per_second": 110.685,
       "step": 25
+    },
+    {
+      "epoch": 0.062284773169636175,
+      "grad_norm": 9.46205997467041,
+      "learning_rate": 5e-05,
+      "loss": 175.2977,
+      "step": 26
+    },
+    {
+      "epoch": 0.06468034136846833,
+      "grad_norm": 9.183752059936523,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 175.2801,
+      "step": 27
+    },
+    {
+      "epoch": 0.06707590956730049,
+      "grad_norm": 8.558121681213379,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 175.2166,
+      "step": 28
+    },
+    {
+      "epoch": 0.06947147776613266,
+      "grad_norm": 8.484734535217285,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 174.8744,
+      "step": 29
+    },
+    {
+      "epoch": 0.07186704596496482,
+      "grad_norm": 8.714923858642578,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 175.0211,
+      "step": 30
+    },
+    {
+      "epoch": 0.07426261416379698,
+      "grad_norm": 8.488415718078613,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 174.8316,
+      "step": 31
+    },
+    {
+      "epoch": 0.07665818236262914,
+      "grad_norm": 8.18109130859375,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 175.0143,
+      "step": 32
+    },
+    {
+      "epoch": 0.0790537505614613,
+      "grad_norm": 8.661060333251953,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 174.7379,
+      "step": 33
+    },
+    {
+      "epoch": 0.08144931876029346,
+      "grad_norm": 8.508981704711914,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 174.9346,
+      "step": 34
+    },
+    {
+      "epoch": 0.08384488695912562,
+      "grad_norm": 9.159597396850586,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 174.6507,
+      "step": 35
+    },
+    {
+      "epoch": 0.08624045515795778,
+      "grad_norm": 8.949252128601074,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 174.7154,
+      "step": 36
+    },
+    {
+      "epoch": 0.08863602335678994,
+      "grad_norm": 9.569437980651855,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 174.7043,
+      "step": 37
+    },
+    {
+      "epoch": 0.0910315915556221,
+      "grad_norm": 10.044833183288574,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 174.1966,
+      "step": 38
+    },
+    {
+      "epoch": 0.09342715975445426,
+      "grad_norm": 9.590546607971191,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 174.6522,
+      "step": 39
+    },
+    {
+      "epoch": 0.09582272795328642,
+      "grad_norm": 9.014169692993164,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 174.4888,
+      "step": 40
+    },
+    {
+      "epoch": 0.09821829615211858,
+      "grad_norm": 8.86300277709961,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 174.5956,
+      "step": 41
+    },
+    {
+      "epoch": 0.10061386435095074,
+      "grad_norm": 8.651285171508789,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 174.5091,
+      "step": 42
+    },
+    {
+      "epoch": 0.1030094325497829,
+      "grad_norm": 8.819639205932617,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 174.5733,
+      "step": 43
+    },
+    {
+      "epoch": 0.10540500074861506,
+      "grad_norm": 8.909255027770996,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 174.4541,
+      "step": 44
+    },
+    {
+      "epoch": 0.10780056894744722,
+      "grad_norm": 8.350724220275879,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 174.5568,
+      "step": 45
+    },
+    {
+      "epoch": 0.11019613714627938,
+      "grad_norm": 8.798490524291992,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 174.4877,
+      "step": 46
+    },
+    {
+      "epoch": 0.11259170534511154,
+      "grad_norm": 8.335972785949707,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 174.7281,
+      "step": 47
+    },
+    {
+      "epoch": 0.11498727354394371,
+      "grad_norm": 8.740706443786621,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 174.5383,
+      "step": 48
+    },
+    {
+      "epoch": 0.11738284174277587,
+      "grad_norm": 8.83700942993164,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 174.5981,
+      "step": 49
+    },
+    {
+      "epoch": 0.11977840994160803,
+      "grad_norm": 11.058894157409668,
+      "learning_rate": 0.0,
+      "loss": 174.0668,
+      "step": 50
+    },
+    {
+      "epoch": 0.11977840994160803,
+      "eval_loss": 10.908712387084961,
+      "eval_runtime": 3.1797,
+      "eval_samples_per_second": 884.671,
+      "eval_steps_per_second": 110.702,
+      "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": 19055561932800.0,
+  "total_flos": 38111123865600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null