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:d5c6a0d40172250387a3e204fecd2b2af89ea26c58077ea9d064d1bd40530227
+oid sha256:b8e2a7f392d7183b2beadd2111d4336a195a4f83e3538e1f7e36dfd91c21e769
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3eedd636830bfc3d5e17924507d219eed1a009a64d6953582b3d0adb91d306f
+oid sha256:4e8f73361a4466729b57a41934e9dd4e70071e0f919d32dbd4865528e87abf50
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bab98cfc3c5efb1383858359881a0f6cb5c9b67d4b0dfc379181138c575bd27
+oid sha256:163e8503fc985f6d90d499d215757a65b477b075027ca8ca4b2a60db49f719ba
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:123b8d9c132fbe7981b103ecbe457900afb5a1f7eb99f3509859bc10a45642b0
+oid sha256:74bff842ae305a9ac38af398c2ef6d35f5071c6efb991b594008a2d1fefddfba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0aa9600d1c1b682380bd728e158faf1ce6bb4530fec7ebc3fb4d020728f57cc
+oid sha256:d3cc0c1f56865d75a03aae7b8d75c0a9dadcb7979ce35193ac3d8a919c49b8b8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9e4bcc93f6cd15eed630b412f72804f17d30d765c8f8c7300d100ca745b6d6
+oid sha256:a60a695c4e5b250791155daac836ae6f717aae73bcfa56bbae580757071adad5
 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": 0.6730909943580627,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5934718100890207,
+  "best_metric": 0.5104753375053406,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1869436201780414,
   "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": 32.459,
       "eval_steps_per_second": 4.114,
       "step": 25
+    },
+    {
+      "epoch": 0.6172106824925816,
+      "grad_norm": 1.8642336130142212,
+      "learning_rate": 5e-05,
+      "loss": 0.5677,
+      "step": 26
+    },
+    {
+      "epoch": 0.6409495548961425,
+      "grad_norm": 1.8692430257797241,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5663,
+      "step": 27
+    },
+    {
+      "epoch": 0.6646884272997032,
+      "grad_norm": 2.416127920150757,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5687,
+      "step": 28
+    },
+    {
+      "epoch": 0.6884272997032641,
+      "grad_norm": 1.7100437879562378,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5918,
+      "step": 29
+    },
+    {
+      "epoch": 0.712166172106825,
+      "grad_norm": 1.4614720344543457,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.6241,
+      "step": 30
+    },
+    {
+      "epoch": 0.7359050445103857,
+      "grad_norm": 2.4405622482299805,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8421,
+      "step": 31
+    },
+    {
+      "epoch": 0.7596439169139466,
+      "grad_norm": 1.6119067668914795,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5922,
+      "step": 32
+    },
+    {
+      "epoch": 0.7833827893175074,
+      "grad_norm": 1.8556543588638306,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4792,
+      "step": 33
+    },
+    {
+      "epoch": 0.8071216617210683,
+      "grad_norm": 1.4979634284973145,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4877,
+      "step": 34
+    },
+    {
+      "epoch": 0.8308605341246291,
+      "grad_norm": 1.6719619035720825,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4963,
+      "step": 35
+    },
+    {
+      "epoch": 0.8545994065281899,
+      "grad_norm": 1.8531289100646973,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4981,
+      "step": 36
+    },
+    {
+      "epoch": 0.8783382789317508,
+      "grad_norm": 2.033458709716797,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5206,
+      "step": 37
+    },
+    {
+      "epoch": 0.9020771513353115,
+      "grad_norm": 1.2323706150054932,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5143,
+      "step": 38
+    },
+    {
+      "epoch": 0.9258160237388724,
+      "grad_norm": 1.3141870498657227,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5161,
+      "step": 39
+    },
+    {
+      "epoch": 0.9495548961424333,
+      "grad_norm": 0.759944498538971,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5678,
+      "step": 40
+    },
+    {
+      "epoch": 0.973293768545994,
+      "grad_norm": 1.223227858543396,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6341,
+      "step": 41
+    },
+    {
+      "epoch": 0.9970326409495549,
+      "grad_norm": 4.528719902038574,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2729,
+      "step": 42
+    },
+    {
+      "epoch": 1.0207715133531157,
+      "grad_norm": 3.4317986965179443,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8869,
+      "step": 43
+    },
+    {
+      "epoch": 1.0445103857566767,
+      "grad_norm": 1.5157424211502075,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3913,
+      "step": 44
+    },
+    {
+      "epoch": 1.0682492581602374,
+      "grad_norm": 1.3632839918136597,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4234,
+      "step": 45
+    },
+    {
+      "epoch": 1.0919881305637982,
+      "grad_norm": 1.201500654220581,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4253,
+      "step": 46
+    },
+    {
+      "epoch": 1.115727002967359,
+      "grad_norm": 0.8647660613059998,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4257,
+      "step": 47
+    },
+    {
+      "epoch": 1.13946587537092,
+      "grad_norm": 1.1541858911514282,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4601,
+      "step": 48
+    },
+    {
+      "epoch": 1.1632047477744807,
+      "grad_norm": 1.447519302368164,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4637,
+      "step": 49
+    },
+    {
+      "epoch": 1.1869436201780414,
+      "grad_norm": 1.8496657609939575,
+      "learning_rate": 0.0,
+      "loss": 0.5039,
+      "step": 50
+    },
+    {
+      "epoch": 1.1869436201780414,
+      "eval_loss": 0.5104753375053406,
+      "eval_runtime": 8.7309,
+      "eval_samples_per_second": 32.528,
+      "eval_steps_per_second": 4.123,
+      "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