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:d7bbded54307be40990ea487c5eac800e3087a2245a2b1700185ef0bd5e0f73b
+oid sha256:c1363fec6362fa74c0d189fe0945d4f69c1214505d1a9fde238d768a50f51a22
 size 445688440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5c50eecf8c78f5359366e33ee583356ec6e498c80c8932cf0dcddf146b5e9d
+oid sha256:f0a4dc1a3919b9e2e11746234281d36d4ce4b705a32c6392c20b2729350027ee
 size 891559354

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038591e05425c5ee3d032e22556c8d9e6b7cfbf8693226f951165908253a3766
+oid sha256:5a0b61bacbcfad36547997f9a8f03e220466e7d35157caaa3c2be46d41625682
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:132e2f60555ba1229db21ebf2d3a71296a8fc4335e0fd320065596df9e5f9ccb
+oid sha256:ff3f4828df15ad683b0286f6ba2f51c72543ae417540f3ac8d77b036ea95cd28
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3323e6d6f5646b1b87bbfa64ef611bed7add4a0b388eddd0e87f4c4f33b7d3
+oid sha256:9d48d442f2976bc6de2527cd00f432fdc70638d7d9eaa3f797f0b2f911e5bf48
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d78b2900720c5d01f1ef555176b3aa49b0cdb5adcd3561d40b834831f8ddc25
+oid sha256:2376e08faa7685985c1fab00105926cd8e1b0d98127f8e2f6890b93128716208
 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": 0.5269150733947754,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2828854314002829,
+  "best_metric": 0.5200080275535583,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5657708628005658,
   "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": 13.202,
       "eval_steps_per_second": 1.664,
       "step": 25
+    },
+    {
+      "epoch": 0.2942008486562942,
+      "grad_norm": 0.8682360053062439,
+      "learning_rate": 5e-05,
+      "loss": 7.2005,
+      "step": 26
+    },
+    {
+      "epoch": 0.3055162659123055,
+      "grad_norm": 0.9563512802124023,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 7.9264,
+      "step": 27
+    },
+    {
+      "epoch": 0.31683168316831684,
+      "grad_norm": 1.096703052520752,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 8.04,
+      "step": 28
+    },
+    {
+      "epoch": 0.32814710042432815,
+      "grad_norm": 1.0564768314361572,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 8.4954,
+      "step": 29
+    },
+    {
+      "epoch": 0.33946251768033947,
+      "grad_norm": 1.1875149011611938,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 8.2755,
+      "step": 30
+    },
+    {
+      "epoch": 0.3507779349363508,
+      "grad_norm": 1.1350054740905762,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 8.7413,
+      "step": 31
+    },
+    {
+      "epoch": 0.3620933521923621,
+      "grad_norm": 1.2498562335968018,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 9.1359,
+      "step": 32
+    },
+    {
+      "epoch": 0.3734087694483734,
+      "grad_norm": 1.4139655828475952,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 8.9738,
+      "step": 33
+    },
+    {
+      "epoch": 0.38472418670438474,
+      "grad_norm": 1.4577665328979492,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 8.6911,
+      "step": 34
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 1.629506230354309,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 9.1795,
+      "step": 35
+    },
+    {
+      "epoch": 0.4073550212164074,
+      "grad_norm": 1.74530029296875,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 9.2998,
+      "step": 36
+    },
+    {
+      "epoch": 0.4186704384724187,
+      "grad_norm": 2.077608346939087,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 8.95,
+      "step": 37
+    },
+    {
+      "epoch": 0.42998585572843,
+      "grad_norm": 1.909153699874878,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.992,
+      "step": 38
+    },
+    {
+      "epoch": 0.44130127298444133,
+      "grad_norm": 0.8186285495758057,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 7.3094,
+      "step": 39
+    },
+    {
+      "epoch": 0.4526166902404526,
+      "grad_norm": 0.9286304116249084,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 7.8571,
+      "step": 40
+    },
+    {
+      "epoch": 0.4639321074964639,
+      "grad_norm": 0.9646059274673462,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 8.4043,
+      "step": 41
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 0.9747306108474731,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 7.5189,
+      "step": 42
+    },
+    {
+      "epoch": 0.48656294200848654,
+      "grad_norm": 1.110140323638916,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 8.197,
+      "step": 43
+    },
+    {
+      "epoch": 0.49787835926449786,
+      "grad_norm": 1.2244906425476074,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.6932,
+      "step": 44
+    },
+    {
+      "epoch": 0.5091937765205092,
+      "grad_norm": 1.2957104444503784,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 9.1472,
+      "step": 45
+    },
+    {
+      "epoch": 0.5205091937765205,
+      "grad_norm": 1.3898643255233765,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 9.3223,
+      "step": 46
+    },
+    {
+      "epoch": 0.5318246110325319,
+      "grad_norm": 1.5572975873947144,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 8.9785,
+      "step": 47
+    },
+    {
+      "epoch": 0.5431400282885431,
+      "grad_norm": 1.7228946685791016,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 8.6731,
+      "step": 48
+    },
+    {
+      "epoch": 0.5544554455445545,
+      "grad_norm": 2.0071144104003906,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 9.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.5657708628005658,
+      "grad_norm": 2.848938226699829,
+      "learning_rate": 0.0,
+      "loss": 7.8565,
+      "step": 50
+    },
+    {
+      "epoch": 0.5657708628005658,
+      "eval_loss": 0.5200080275535583,
+      "eval_runtime": 43.7314,
+      "eval_samples_per_second": 13.606,
+      "eval_steps_per_second": 1.715,
+      "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": 5.478898116591616e+17,
+  "total_flos": 1.0954378319683912e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null