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:aa0def5f16addb82a5a9b75a33de02b3c186c2db82411a7709757b8eda86ec1b
+oid sha256:6dd850a18afccaa529cf98b2df170e915d71f9369bfeae6d6cfdaf3ab5135ca7
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75850c966935add01a60303ee1b1c1f20e34dcfa88b4cdf05cec6a08157a11ad
+oid sha256:5ce641f999a769f55273622c66bc50404112671a8d32ce05cfd1a0ba60d0e19f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d988051728d71c74a8c332eba1986332099f3ed387881d69e3104ce0f2b1bb6c
+oid sha256:9c0b1edf44f04c82cde44de2405936579289589f305471277ffd724d507bc5d2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ecfc3a041c0688775b538f6b81680e72ffb716972e8dba3ce9db11781e845d
+oid sha256:7e852869bbaca40a86ad28930e0aba983faee5b5e3e383eaf14a0d2a42059869
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9dbf8b50ba76cb96cfa64966e20c5f35155d910743f77ee5e951a434537e84c
+oid sha256:7cbe8190e34901cbf2959cd5e9602853dc62c61bb1756a0bcf68c2bdf115ecd4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:694969a7fcbe5dbca862e8be32625f155e456a90c53bbbfbb086a9462a688a96
+oid sha256:ac97e334ddc5b92dbaa0e87302d33830a41c950df581bc238118c49885ece0e8
 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": 0.5535266995429993,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3917727717923604,
+  "best_metric": 0.536442756652832,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7835455435847208,
   "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": 14.726,
       "eval_steps_per_second": 1.849,
       "step": 25
+    },
+    {
+      "epoch": 0.40744368266405484,
+      "grad_norm": 0.23766404390335083,
+      "learning_rate": 5e-05,
+      "loss": 0.6234,
+      "step": 26
+    },
+    {
+      "epoch": 0.42311459353574926,
+      "grad_norm": 0.23127883672714233,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6038,
+      "step": 27
+    },
+    {
+      "epoch": 0.4387855044074437,
+      "grad_norm": 0.22502242028713226,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.598,
+      "step": 28
+    },
+    {
+      "epoch": 0.4544564152791381,
+      "grad_norm": 0.23507346212863922,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5594,
+      "step": 29
+    },
+    {
+      "epoch": 0.4701273261508325,
+      "grad_norm": 0.2247634381055832,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5735,
+      "step": 30
+    },
+    {
+      "epoch": 0.48579823702252695,
+      "grad_norm": 0.23326322436332703,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5991,
+      "step": 31
+    },
+    {
+      "epoch": 0.5014691478942214,
+      "grad_norm": 0.2359481155872345,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5303,
+      "step": 32
+    },
+    {
+      "epoch": 0.5171400587659157,
+      "grad_norm": 0.25685980916023254,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5433,
+      "step": 33
+    },
+    {
+      "epoch": 0.5328109696376102,
+      "grad_norm": 0.2492547184228897,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5567,
+      "step": 34
+    },
+    {
+      "epoch": 0.5484818805093046,
+      "grad_norm": 0.2647036910057068,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.551,
+      "step": 35
+    },
+    {
+      "epoch": 0.564152791380999,
+      "grad_norm": 0.26322075724601746,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4919,
+      "step": 36
+    },
+    {
+      "epoch": 0.5798237022526934,
+      "grad_norm": 0.28396323323249817,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4601,
+      "step": 37
+    },
+    {
+      "epoch": 0.5954946131243879,
+      "grad_norm": 0.2058783918619156,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5345,
+      "step": 38
+    },
+    {
+      "epoch": 0.6111655239960823,
+      "grad_norm": 0.19112937152385712,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5964,
+      "step": 39
+    },
+    {
+      "epoch": 0.6268364348677767,
+      "grad_norm": 0.18986861407756805,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5798,
+      "step": 40
+    },
+    {
+      "epoch": 0.6425073457394711,
+      "grad_norm": 0.1978798359632492,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5386,
+      "step": 41
+    },
+    {
+      "epoch": 0.6581782566111655,
+      "grad_norm": 0.19694554805755615,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5607,
+      "step": 42
+    },
+    {
+      "epoch": 0.67384916748286,
+      "grad_norm": 0.21728673577308655,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5868,
+      "step": 43
+    },
+    {
+      "epoch": 0.6895200783545543,
+      "grad_norm": 0.19268789887428284,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5241,
+      "step": 44
+    },
+    {
+      "epoch": 0.7051909892262488,
+      "grad_norm": 0.22148820757865906,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.551,
+      "step": 45
+    },
+    {
+      "epoch": 0.7208619000979432,
+      "grad_norm": 0.21198055148124695,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4969,
+      "step": 46
+    },
+    {
+      "epoch": 0.7365328109696376,
+      "grad_norm": 0.2188008427619934,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5173,
+      "step": 47
+    },
+    {
+      "epoch": 0.752203721841332,
+      "grad_norm": 0.2279113531112671,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4843,
+      "step": 48
+    },
+    {
+      "epoch": 0.7678746327130265,
+      "grad_norm": 0.25976061820983887,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4682,
+      "step": 49
+    },
+    {
+      "epoch": 0.7835455435847208,
+      "grad_norm": 0.33424636721611023,
+      "learning_rate": 0.0,
+      "loss": 0.4384,
+      "step": 50
+    },
+    {
+      "epoch": 0.7835455435847208,
+      "eval_loss": 0.536442756652832,
+      "eval_runtime": 29.191,
+      "eval_samples_per_second": 14.731,
+      "eval_steps_per_second": 1.85,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null