Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ebd7a4efca289bf36c72efe875a2ea280297467dcfd6bf69635ec7b94d72d53
+oid sha256:f8c859b519f5e4f4d46e95ba68b78140587e83650f2d4bc5c12f6920b6a02203
 size 239135488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23192612ae85146dceb0b20f6d8343311a7043faa26d3eaca737e5e255104c09
+oid sha256:6d7a79894d8c1a87cd351c4c891e33c8fb82ecde5d0d7373434b0c2f6dab8134
 size 478528978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a207b6b10df5f1241a278d6723b220b1325d43f572c2bd63a2cc2180b6f7d1c
+oid sha256:f53d40f1c87355aa225b0fc34310e496ea85335c80752e222b93c1aabb29895b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:031f56f78309ff0c22e6d244db7e23fbf0ef95d6aa367733535213f7be891ac1
+oid sha256:5b6eddc9a16ba93223d97dfa7c8dd5538b246e49556eb5315be3348f6d1f7dd1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb009596f27d1ec9ec633a6aaf8d2aaac704b2468f862724616621b1ffaa1b9
+oid sha256:be032e729b40e1721ceb580dd6aa85703f0248fc4efd9ea681b87619510ef3b8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c34cc12f4c190e2193d82433bee95fb967ca27610b17ba067a4f6e2d38c0cf32
+oid sha256:3d652fecf86c19f9081d5e735bb1c00245a8f9e58b6c647ea7022dee85768d5c
 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": 15.784210205078125,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11412268188302425,
+  "best_metric": 15.69967269897461,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2282453637660485,
   "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": 46.415,
       "eval_steps_per_second": 5.818,
       "step": 25
+    },
+    {
+      "epoch": 0.11868758915834522,
+      "grad_norm": Infinity,
+      "learning_rate": 5e-05,
+      "loss": 16.8711,
+      "step": 26
+    },
+    {
+      "epoch": 0.12325249643366619,
+      "grad_norm": Infinity,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 16.7578,
+      "step": 27
+    },
+    {
+      "epoch": 0.12781740370898717,
+      "grad_norm": Infinity,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 16.7029,
+      "step": 28
+    },
+    {
+      "epoch": 0.13238231098430814,
+      "grad_norm": 5.27922536617345e+18,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 16.5378,
+      "step": 29
+    },
+    {
+      "epoch": 0.1369472182596291,
+      "grad_norm": 6.708468986247381e+18,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 16.1224,
+      "step": 30
+    },
+    {
+      "epoch": 0.14151212553495007,
+      "grad_norm": 2683090229002240.0,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 15.8674,
+      "step": 31
+    },
+    {
+      "epoch": 0.14607703281027104,
+      "grad_norm": 3340606772346880.0,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 15.854,
+      "step": 32
+    },
+    {
+      "epoch": 0.150641940085592,
+      "grad_norm": 20492406751232.0,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 15.0143,
+      "step": 33
+    },
+    {
+      "epoch": 0.15520684736091298,
+      "grad_norm": 34113855488.0,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 15.5429,
+      "step": 34
+    },
+    {
+      "epoch": 0.15977175463623394,
+      "grad_norm": 21085825024.0,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 15.3274,
+      "step": 35
+    },
+    {
+      "epoch": 0.1643366619115549,
+      "grad_norm": 363076768.0,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 15.033,
+      "step": 36
+    },
+    {
+      "epoch": 0.1689015691868759,
+      "grad_norm": 78258952.0,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 14.8023,
+      "step": 37
+    },
+    {
+      "epoch": 0.17346647646219687,
+      "grad_norm": Infinity,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 15.6378,
+      "step": 38
+    },
+    {
+      "epoch": 0.17803138373751784,
+      "grad_norm": Infinity,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 17.1524,
+      "step": 39
+    },
+    {
+      "epoch": 0.1825962910128388,
+      "grad_norm": Infinity,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 16.9398,
+      "step": 40
+    },
+    {
+      "epoch": 0.18716119828815977,
+      "grad_norm": 8.890011656185184e+18,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 16.5318,
+      "step": 41
+    },
+    {
+      "epoch": 0.19172610556348074,
+      "grad_norm": 9.98518735985705e+17,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 16.1866,
+      "step": 42
+    },
+    {
+      "epoch": 0.1962910128388017,
+      "grad_norm": 1.2888339579823718e+17,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 16.0467,
+      "step": 43
+    },
+    {
+      "epoch": 0.20085592011412268,
+      "grad_norm": 1114067540377600.0,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 15.3093,
+      "step": 44
+    },
+    {
+      "epoch": 0.20542082738944364,
+      "grad_norm": 13566930321408.0,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 15.424,
+      "step": 45
+    },
+    {
+      "epoch": 0.2099857346647646,
+      "grad_norm": 246276662755328.0,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 15.2233,
+      "step": 46
+    },
+    {
+      "epoch": 0.21455064194008558,
+      "grad_norm": 4525861376.0,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 15.4909,
+      "step": 47
+    },
+    {
+      "epoch": 0.21911554921540657,
+      "grad_norm": 2824147200.0,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 15.2904,
+      "step": 48
+    },
+    {
+      "epoch": 0.22368045649072754,
+      "grad_norm": 143129056.0,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 15.2153,
+      "step": 49
+    },
+    {
+      "epoch": 0.2282453637660485,
+      "grad_norm": 30752916.0,
+      "learning_rate": 0.0,
+      "loss": 14.4523,
+      "step": 50
+    },
+    {
+      "epoch": 0.2282453637660485,
+      "eval_loss": 15.69967269897461,
+      "eval_runtime": 31.7913,
+      "eval_samples_per_second": 46.428,
+      "eval_steps_per_second": 5.819,
+      "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": 1.487279663087616e+17,
+  "total_flos": 2.974559326175232e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null