Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b5b8ebcb8a9eb668a191524108014bea6b78903179f15d70ac72cb0727624ff
+oid sha256:ec48d36f2169a508006b3bdc933cbfb7df8e45318b5132e053ef72f787c8dd50
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c21676087884a01b78a3eb4257ffcc748fa7838b4cb46a209ec548be68d493
+oid sha256:7c4e950038cd56b1f9d7983813905b64ac2abf944065fd1f5dd638ef1faccb0f
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dee3d034d2b28adb9079c42a0e2c9ee0011677d5f956111648713b096dc1b88
+oid sha256:687e73972eb802e3d4bbeba7e62bae79dd4f023a2175b66ccf0374619e177fdf
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af48938b0302cf28b8e7c07a85b53f66aeede0bd69ac3d5d99e7fbe3da353a02
+oid sha256:57a92615f9fbc2191c662ab65e942cfb74d876117b307d66f927cfed99ce56f1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ac40ac2526cf3a8598bb70e0308c236d3ca41446f8d6f3e9454ac11d1956cbc
+oid sha256:482e041274bdf2a6c0a680401818514c9a0cf0ede4d7372b670da6e2633829c8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148c6bd2b24901b353dcaffdd9bdae4076c0c3975d0061c530875144ac70d099
+oid sha256:90fb824c6a5d846ac868de289ad31d38380b3b1f75986d4821752f5f6cebaa89
 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": 2.152416944503784,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006735027192672291,
+  "best_metric": 2.1415767669677734,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013470054385344581,
   "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": 86.868,
       "eval_steps_per_second": 10.859,
       "step": 25
+    },
+    {
+      "epoch": 0.007004428280379182,
+      "grad_norm": 0.12296074628829956,
+      "learning_rate": 5e-05,
+      "loss": 1.7179,
+      "step": 26
+    },
+    {
+      "epoch": 0.007273829368086074,
+      "grad_norm": 0.1352420449256897,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.8508,
+      "step": 27
+    },
+    {
+      "epoch": 0.007543230455792966,
+      "grad_norm": 0.14206938445568085,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.9431,
+      "step": 28
+    },
+    {
+      "epoch": 0.007812631543499857,
+      "grad_norm": 0.1531849354505539,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.0376,
+      "step": 29
+    },
+    {
+      "epoch": 0.008082032631206748,
+      "grad_norm": 0.17265917360782623,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.1185,
+      "step": 30
+    },
+    {
+      "epoch": 0.00835143371891364,
+      "grad_norm": 0.1766246110200882,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1605,
+      "step": 31
+    },
+    {
+      "epoch": 0.008620834806620532,
+      "grad_norm": 0.17309987545013428,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1793,
+      "step": 32
+    },
+    {
+      "epoch": 0.008890235894327423,
+      "grad_norm": 0.20584042370319366,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.285,
+      "step": 33
+    },
+    {
+      "epoch": 0.009159636982034315,
+      "grad_norm": 0.22178272902965546,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3379,
+      "step": 34
+    },
+    {
+      "epoch": 0.009429038069741207,
+      "grad_norm": 0.2220696061849594,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.3039,
+      "step": 35
+    },
+    {
+      "epoch": 0.009698439157448098,
+      "grad_norm": 0.25546637177467346,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.408,
+      "step": 36
+    },
+    {
+      "epoch": 0.00996784024515499,
+      "grad_norm": 0.24715134501457214,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.3815,
+      "step": 37
+    },
+    {
+      "epoch": 0.010237241332861882,
+      "grad_norm": 0.13599006831645966,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6916,
+      "step": 38
+    },
+    {
+      "epoch": 0.010506642420568773,
+      "grad_norm": 0.13048195838928223,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.7807,
+      "step": 39
+    },
+    {
+      "epoch": 0.010776043508275665,
+      "grad_norm": 0.1338452249765396,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.8669,
+      "step": 40
+    },
+    {
+      "epoch": 0.011045444595982556,
+      "grad_norm": 0.13688980042934418,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.9812,
+      "step": 41
+    },
+    {
+      "epoch": 0.011314845683689448,
+      "grad_norm": 0.1470724195241928,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.065,
+      "step": 42
+    },
+    {
+      "epoch": 0.01158424677139634,
+      "grad_norm": 0.1516406238079071,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.1349,
+      "step": 43
+    },
+    {
+      "epoch": 0.011853647859103231,
+      "grad_norm": 0.15423178672790527,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1353,
+      "step": 44
+    },
+    {
+      "epoch": 0.012123048946810122,
+      "grad_norm": 0.16444306075572968,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.27,
+      "step": 45
+    },
+    {
+      "epoch": 0.012392450034517014,
+      "grad_norm": 0.17130832374095917,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.2999,
+      "step": 46
+    },
+    {
+      "epoch": 0.012661851122223906,
+      "grad_norm": 0.1853959560394287,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.3348,
+      "step": 47
+    },
+    {
+      "epoch": 0.012931252209930797,
+      "grad_norm": 0.20296545326709747,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.4142,
+      "step": 48
+    },
+    {
+      "epoch": 0.013200653297637688,
+      "grad_norm": 0.23544824123382568,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.4167,
+      "step": 49
+    },
+    {
+      "epoch": 0.013470054385344581,
+      "grad_norm": 0.3853051960468292,
+      "learning_rate": 0.0,
+      "loss": 2.3263,
+      "step": 50
+    },
+    {
+      "epoch": 0.013470054385344581,
+      "eval_loss": 2.1415767669677734,
+      "eval_runtime": 287.9217,
+      "eval_samples_per_second": 86.853,
+      "eval_steps_per_second": 10.857,
+      "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": 5.300992813406618e+16,
+  "total_flos": 1.0598674582837658e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null