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:a600207cfb58c3b063c9bf1583c63ada6d58c5a35a139625e660fee08add432e
+oid sha256:5e2eab7a6c17c18fc2fb5ed2be351af824a252e67f9434dfbab1ecc11800bb57
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2324a34105151f1ef1bcdee61cdeb871111f4809d26dc07ddf11d9f30dd82e46
+oid sha256:68c5ca5455d30f34bb6bb7378a840a1c5c53e9f95adf5b846da6a50a463c9335
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d91db45a01f858fc874d7f5ce5397871b8a4d732242c5b4154ec2b85018dd99
+oid sha256:95e3f3710b780bee372b16efcd4faa59dc53649fac5ae23a2eec2484d8a71550
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be341029818f6de9a246e99376f151952ef574e5d6288db5a2e81204d51649de
+oid sha256:db45180d36355f4148ae43cbe7713d9c0c43cf3bdf1707b8e6457abfd573a55e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4f99418c23b6e6ba60b9fa7ac40e24c4c0eac50fb623ddb636f983a8882dc2
+oid sha256:eb065b89c1772cbbbe10d2fb92a1d279633642bfdd31f69b94eb917c53aec646
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ad4174958854b38f1ea45caf998c7a8deb59f8719595d5a7ec1308613a31da
+oid sha256:d1dfc8a3cbe907f4381d17b2a69933991bf9310d9fcb915fc0935d6ef3b03d6d
 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": 2.101926326751709,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0756000756000756,
+  "best_metric": 2.0979692935943604,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1512001512001512,
   "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": 20.826,
       "eval_steps_per_second": 2.608,
       "step": 25
+    },
+    {
+      "epoch": 0.07862407862407862,
+      "grad_norm": 0.053373731672763824,
+      "learning_rate": 5e-05,
+      "loss": 2.0909,
+      "step": 26
+    },
+    {
+      "epoch": 0.08164808164808164,
+      "grad_norm": 0.056285835802555084,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0645,
+      "step": 27
+    },
+    {
+      "epoch": 0.08467208467208467,
+      "grad_norm": 0.057410020381212234,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.0809,
+      "step": 28
+    },
+    {
+      "epoch": 0.0876960876960877,
+      "grad_norm": 0.058530259877443314,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.113,
+      "step": 29
+    },
+    {
+      "epoch": 0.09072009072009073,
+      "grad_norm": 0.05941487103700638,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.0706,
+      "step": 30
+    },
+    {
+      "epoch": 0.09374409374409375,
+      "grad_norm": 0.05782806873321533,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.123,
+      "step": 31
+    },
+    {
+      "epoch": 0.09676809676809676,
+      "grad_norm": 0.05750083178281784,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.1479,
+      "step": 32
+    },
+    {
+      "epoch": 0.0997920997920998,
+      "grad_norm": 0.055824633687734604,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.1368,
+      "step": 33
+    },
+    {
+      "epoch": 0.10281610281610282,
+      "grad_norm": 0.058026283979415894,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.2183,
+      "step": 34
+    },
+    {
+      "epoch": 0.10584010584010584,
+      "grad_norm": 0.060771435499191284,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.0711,
+      "step": 35
+    },
+    {
+      "epoch": 0.10886410886410887,
+      "grad_norm": 0.0712975412607193,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.0645,
+      "step": 36
+    },
+    {
+      "epoch": 0.11188811188811189,
+      "grad_norm": 0.0783361941576004,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.0429,
+      "step": 37
+    },
+    {
+      "epoch": 0.11491211491211491,
+      "grad_norm": 0.06469312310218811,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0662,
+      "step": 38
+    },
+    {
+      "epoch": 0.11793611793611794,
+      "grad_norm": 0.05340993404388428,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.1214,
+      "step": 39
+    },
+    {
+      "epoch": 0.12096012096012096,
+      "grad_norm": 0.053653616458177567,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0972,
+      "step": 40
+    },
+    {
+      "epoch": 0.12398412398412398,
+      "grad_norm": 0.05478423088788986,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.0812,
+      "step": 41
+    },
+    {
+      "epoch": 0.127008127008127,
+      "grad_norm": 0.05282788723707199,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1001,
+      "step": 42
+    },
+    {
+      "epoch": 0.13003213003213004,
+      "grad_norm": 0.05366608500480652,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0913,
+      "step": 43
+    },
+    {
+      "epoch": 0.13305613305613306,
+      "grad_norm": 0.05308716371655464,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0958,
+      "step": 44
+    },
+    {
+      "epoch": 0.13608013608013608,
+      "grad_norm": 0.0528181716799736,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0964,
+      "step": 45
+    },
+    {
+      "epoch": 0.1391041391041391,
+      "grad_norm": 0.05563020333647728,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1072,
+      "step": 46
+    },
+    {
+      "epoch": 0.14212814212814212,
+      "grad_norm": 0.05598459765315056,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2237,
+      "step": 47
+    },
+    {
+      "epoch": 0.14515214515214514,
+      "grad_norm": 0.06569921225309372,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.1504,
+      "step": 48
+    },
+    {
+      "epoch": 0.1481761481761482,
+      "grad_norm": 0.07752805203199387,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.0868,
+      "step": 49
+    },
+    {
+      "epoch": 0.1512001512001512,
+      "grad_norm": 0.10505488514900208,
+      "learning_rate": 0.0,
+      "loss": 2.0318,
+      "step": 50
+    },
+    {
+      "epoch": 0.1512001512001512,
+      "eval_loss": 2.0979692935943604,
+      "eval_runtime": 106.985,
+      "eval_samples_per_second": 20.825,
+      "eval_steps_per_second": 2.608,
+      "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": 9.0954574235435e+16,
+  "total_flos": 1.821740327942226e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null