Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75313295a7e78f100c76db026f88418db671ddb532f10a3fc934ff7894ecd2d5
+oid sha256:452a3da5db7780674879090968504400fb095ccc4fe81689923de9106ae943d1
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b947b720b44cd4ce6a465bc4e100279afc1ca2ec250d8ead7793efdced5e4f
+oid sha256:b01088f0447c950e362c4192708919517d3fff181da3534bab71cd9a60d381b0
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d46c533fbbadffda7cf2e4871fe20fe5394acf5fe351e3934043cb90b1a8b1a
+oid sha256:f55ad541480f48d35a2cebaa482739c586432858898c4bded05f88967e532486
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2235c14f701759b6b0f08a6e0de0a570e466f6822a3ee80cdccfb2b04f23c2ca
+oid sha256:abb74b145cf51d0bf1c4306ae0d189283f2eb53c21ad1d627e03d18d5b7d0a52
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2077c86a8905d7840a51fd86cb6b55cc37574cc3d1728da237e3188b9b85bde8
+oid sha256:41530e6bba8f323346821bd5699db5516bc0aa308a323a986136466de87b3235
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9863cefadd876f08959f5c3e3a6c0916f19c8459e361e0fb541bb4c1ddbda1bf
+oid sha256:be22341f2de8a2eef0c350feb5cf9cd2bbeec3c9fea3109ddd2328d1da1a9bd8
 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": 3.814847469329834,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8639308855291576,
+  "best_metric": 3.7166805267333984,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.7516198704103672,
   "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": 85.567,
       "eval_steps_per_second": 10.97,
       "step": 25
+    },
+    {
+      "epoch": 0.8984881209503239,
+      "grad_norm": 2.3841733932495117,
+      "learning_rate": 5e-05,
+      "loss": 3.7094,
+      "step": 26
+    },
+    {
+      "epoch": 0.9330453563714903,
+      "grad_norm": 2.165337324142456,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.9942,
+      "step": 27
+    },
+    {
+      "epoch": 0.9676025917926566,
+      "grad_norm": 7.546828746795654,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 4.3582,
+      "step": 28
+    },
+    {
+      "epoch": 1.0259179265658747,
+      "grad_norm": 1.986472249031067,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 5.6933,
+      "step": 29
+    },
+    {
+      "epoch": 1.060475161987041,
+      "grad_norm": 1.5792019367218018,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.3252,
+      "step": 30
+    },
+    {
+      "epoch": 1.0950323974082075,
+      "grad_norm": 1.5796281099319458,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.3205,
+      "step": 31
+    },
+    {
+      "epoch": 1.1295896328293737,
+      "grad_norm": 1.7154875993728638,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.4918,
+      "step": 32
+    },
+    {
+      "epoch": 1.16414686825054,
+      "grad_norm": 2.2885804176330566,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.6606,
+      "step": 33
+    },
+    {
+      "epoch": 1.1987041036717063,
+      "grad_norm": 3.100572347640991,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.7339,
+      "step": 34
+    },
+    {
+      "epoch": 1.2332613390928726,
+      "grad_norm": 7.583836078643799,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.1832,
+      "step": 35
+    },
+    {
+      "epoch": 1.267818574514039,
+      "grad_norm": 1.4905058145523071,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.4948,
+      "step": 36
+    },
+    {
+      "epoch": 1.3023758099352052,
+      "grad_norm": 1.3239670991897583,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.2022,
+      "step": 37
+    },
+    {
+      "epoch": 1.3369330453563715,
+      "grad_norm": 1.6314467191696167,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.3676,
+      "step": 38
+    },
+    {
+      "epoch": 1.3714902807775378,
+      "grad_norm": 2.0681777000427246,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.4819,
+      "step": 39
+    },
+    {
+      "epoch": 1.406047516198704,
+      "grad_norm": 2.430373430252075,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.6413,
+      "step": 40
+    },
+    {
+      "epoch": 1.4406047516198703,
+      "grad_norm": 3.5118353366851807,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.7818,
+      "step": 41
+    },
+    {
+      "epoch": 1.4751619870410368,
+      "grad_norm": 4.599954605102539,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.1105,
+      "step": 42
+    },
+    {
+      "epoch": 1.509719222462203,
+      "grad_norm": 3.1489386558532715,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.3242,
+      "step": 43
+    },
+    {
+      "epoch": 1.5442764578833694,
+      "grad_norm": 1.399327039718628,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.1605,
+      "step": 44
+    },
+    {
+      "epoch": 1.5788336933045355,
+      "grad_norm": 2.1838557720184326,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.3349,
+      "step": 45
+    },
+    {
+      "epoch": 1.613390928725702,
+      "grad_norm": 1.7547966241836548,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.3238,
+      "step": 46
+    },
+    {
+      "epoch": 1.6479481641468683,
+      "grad_norm": 4.076164245605469,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.4109,
+      "step": 47
+    },
+    {
+      "epoch": 1.6825053995680346,
+      "grad_norm": 7.376658916473389,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.7638,
+      "step": 48
+    },
+    {
+      "epoch": 1.7170626349892009,
+      "grad_norm": 19.589956283569336,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.2819,
+      "step": 49
+    },
+    {
+      "epoch": 1.7516198704103672,
+      "grad_norm": 1.4673881530761719,
+      "learning_rate": 0.0,
+      "loss": 3.3217,
+      "step": 50
+    },
+    {
+      "epoch": 1.7516198704103672,
+      "eval_loss": 3.7166805267333984,
+      "eval_runtime": 2.2813,
+      "eval_samples_per_second": 85.477,
+      "eval_steps_per_second": 10.959,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null