Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6469a69fe3f8cad6d23bde3d6f52d50b1243c17e14cf863f1fdebcb8dfe8fc
+oid sha256:ca1c7f4ffb681b777ef6d364cbb21e82e5f3e7f2003d9d317cc519f15f6a76b0
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443aab6072abdf94f93db01f38293cc83780c2cafc746d53ff9f0cbf88c75a05
+oid sha256:fe8f335b80754c7c00cf1cb267c25c59bc2de603fc8d3aa5c656202222a56c8d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daba3676f224ae48b3991e02a5a56a936486230e25bdb2e4d899f7b824d1f26c
+oid sha256:ccbf6332bee62bc7fcff4caf8d1e3d2af6ca2eeb2c56bc5d35e99bde15309222
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c6f95220f73e616813aaf4a168f87f4de1dc6f424d08d552dfc4c1d8ea14cfe
+oid sha256:a9ed1b3c1faa887dd978c194cf164a021f08be3563cf731b97b26806d380b1d0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0a13cfddd70db7a0a2cdecdd8aae6d751582d9d20487f96b55f60133d576a3
+oid sha256:a18fdbcae753f934249281b2425f1668de4dd07ed135f3c5a3e880a6f6740e01
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487e83793cb892e5b1a3a341612c8448d2229db95811f17a2f121126f829b320
+oid sha256:455ffd3643264702a4c2afcb6f13750d8ed0a70c758347e08e4f6dbc048d9e52
 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": 3.0949742794036865,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02981736861721953,
+  "best_metric": 3.0359787940979004,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05963473723443906,
   "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": 18.131,
       "eval_steps_per_second": 2.269,
       "step": 25
+    },
+    {
+      "epoch": 0.031010063361908313,
+      "grad_norm": 1.1664888858795166,
+      "learning_rate": 5e-05,
+      "loss": 2.389,
+      "step": 26
+    },
+    {
+      "epoch": 0.03220275810659709,
+      "grad_norm": 1.0403869152069092,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.5,
+      "step": 27
+    },
+    {
+      "epoch": 0.033395452851285874,
+      "grad_norm": 0.9833716750144958,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.4967,
+      "step": 28
+    },
+    {
+      "epoch": 0.03458814759597466,
+      "grad_norm": 0.8450362086296082,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.5095,
+      "step": 29
+    },
+    {
+      "epoch": 0.035780842340663435,
+      "grad_norm": 0.8933276534080505,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.552,
+      "step": 30
+    },
+    {
+      "epoch": 0.03697353708535222,
+      "grad_norm": 0.835259735584259,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.6166,
+      "step": 31
+    },
+    {
+      "epoch": 0.038166231830040996,
+      "grad_norm": 1.05070960521698,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.7404,
+      "step": 32
+    },
+    {
+      "epoch": 0.03935892657472978,
+      "grad_norm": 0.9418009519577026,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.8333,
+      "step": 33
+    },
+    {
+      "epoch": 0.040551621319418564,
+      "grad_norm": 1.1310828924179077,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.1375,
+      "step": 34
+    },
+    {
+      "epoch": 0.04174431606410734,
+      "grad_norm": 1.0786144733428955,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.4092,
+      "step": 35
+    },
+    {
+      "epoch": 0.042937010808796125,
+      "grad_norm": 1.7499446868896484,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.7281,
+      "step": 36
+    },
+    {
+      "epoch": 0.0441297055534849,
+      "grad_norm": 3.1457748413085938,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.5446,
+      "step": 37
+    },
+    {
+      "epoch": 0.045322400298173686,
+      "grad_norm": 0.8917385935783386,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6249,
+      "step": 38
+    },
+    {
+      "epoch": 0.04651509504286247,
+      "grad_norm": 0.6350715756416321,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.2615,
+      "step": 39
+    },
+    {
+      "epoch": 0.04770778978755125,
+      "grad_norm": 0.5872529745101929,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3732,
+      "step": 40
+    },
+    {
+      "epoch": 0.04890048453224003,
+      "grad_norm": 0.5899565815925598,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.485,
+      "step": 41
+    },
+    {
+      "epoch": 0.05009317927692881,
+      "grad_norm": 0.593927800655365,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.4474,
+      "step": 42
+    },
+    {
+      "epoch": 0.05128587402161759,
+      "grad_norm": 0.620150089263916,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.5545,
+      "step": 43
+    },
+    {
+      "epoch": 0.052478568766306376,
+      "grad_norm": 0.5872986316680908,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.7247,
+      "step": 44
+    },
+    {
+      "epoch": 0.05367126351099515,
+      "grad_norm": 0.6523360013961792,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.7153,
+      "step": 45
+    },
+    {
+      "epoch": 0.05486395825568394,
+      "grad_norm": 0.7106797099113464,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.9149,
+      "step": 46
+    },
+    {
+      "epoch": 0.056056653000372714,
+      "grad_norm": 0.9088175892829895,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.0845,
+      "step": 47
+    },
+    {
+      "epoch": 0.0572493477450615,
+      "grad_norm": 1.1141997575759888,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.4583,
+      "step": 48
+    },
+    {
+      "epoch": 0.05844204248975028,
+      "grad_norm": 1.7017822265625,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.964,
+      "step": 49
+    },
+    {
+      "epoch": 0.05963473723443906,
+      "grad_norm": 4.411134719848633,
+      "learning_rate": 0.0,
+      "loss": 5.3205,
+      "step": 50
+    },
+    {
+      "epoch": 0.05963473723443906,
+      "eval_loss": 3.0359787940979004,
+      "eval_runtime": 311.3843,
+      "eval_samples_per_second": 18.142,
+      "eval_steps_per_second": 2.271,
+      "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