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:b5d237330c41ba80cdcf8f6fee20084eb9b73a15e8fefd0af5f20a4b1cb1ece0
+oid sha256:7b743c8b02459433701996d3fea8395707450581713e984a337e0e8baefa6afb
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1b8a91a722f6c1917267eaffb3b3480ec4b95a1dc0674da9234ca4b9b29cf9a
+oid sha256:4bda138f438bbf17d2268b6eb56a016e98c5ebbf75ff631ba8aea287a46a974f
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f0faae5b8b22e50797059a1efc3f7990b8022a1909ecb1793699dd2e91bcba
+oid sha256:46342187f4dc75c9e6c39a7b1878f43e0ec716b87dd40a756912014fb7ab4fe0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f7d3c581dec20c2d3cf2e53a92b7aac68e8d7e6f0e6bbe328ef5cfb93d519b
+oid sha256:465716345b10469c5253861a2558865d7131ff7c526453a498941870d32e3baa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c536cb67fa848be4a5a4f4c90ef69a306a2e02d2e814a55ce472c5c40f87bacc
+oid sha256:8647dbf034b9ef56d9c9724cba9f0dc9efe2ec86060c11c290af874fcb737722
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4588c484fddacc3a16dba0daaa2ff946e376af439352880a42cf840893baf7d6
+oid sha256:2528df0f1c0d578da727283d5c1a0808f95ecc1dbeefb25dcf5ab37d8b6f0256
 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": 3.267822504043579,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09918175055789735,
+  "best_metric": 3.218653678894043,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1983635011157947,
   "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": 147.295,
       "eval_steps_per_second": 18.466,
       "step": 25
+    },
+    {
+      "epoch": 0.10314902058021325,
+      "grad_norm": 1.0147478580474854,
+      "learning_rate": 5e-05,
+      "loss": 3.2645,
+      "step": 26
+    },
+    {
+      "epoch": 0.10711629060252914,
+      "grad_norm": 1.2164422273635864,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.1775,
+      "step": 27
+    },
+    {
+      "epoch": 0.11108356062484503,
+      "grad_norm": 1.3750309944152832,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.2619,
+      "step": 28
+    },
+    {
+      "epoch": 0.11505083064716093,
+      "grad_norm": 1.3229867219924927,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.2809,
+      "step": 29
+    },
+    {
+      "epoch": 0.11901810066947682,
+      "grad_norm": 1.0716197490692139,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.2646,
+      "step": 30
+    },
+    {
+      "epoch": 0.12298537069179272,
+      "grad_norm": 0.9642243385314941,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.2412,
+      "step": 31
+    },
+    {
+      "epoch": 0.1269526407141086,
+      "grad_norm": 0.8288385272026062,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.2419,
+      "step": 32
+    },
+    {
+      "epoch": 0.1309199107364245,
+      "grad_norm": 0.8620959520339966,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.3797,
+      "step": 33
+    },
+    {
+      "epoch": 0.1348871807587404,
+      "grad_norm": 0.8693250417709351,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.218,
+      "step": 34
+    },
+    {
+      "epoch": 0.1388544507810563,
+      "grad_norm": 0.9725481271743774,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.2733,
+      "step": 35
+    },
+    {
+      "epoch": 0.1428217208033722,
+      "grad_norm": 0.9870604276657104,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.2407,
+      "step": 36
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 1.25055992603302,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.301,
+      "step": 37
+    },
+    {
+      "epoch": 0.15075626084800398,
+      "grad_norm": 0.8020516633987427,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.2486,
+      "step": 38
+    },
+    {
+      "epoch": 0.15472353087031987,
+      "grad_norm": 0.6509931087493896,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.2495,
+      "step": 39
+    },
+    {
+      "epoch": 0.15869080089263576,
+      "grad_norm": 0.6136582493782043,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.2264,
+      "step": 40
+    },
+    {
+      "epoch": 0.16265807091495166,
+      "grad_norm": 0.575463056564331,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.1638,
+      "step": 41
+    },
+    {
+      "epoch": 0.16662534093726755,
+      "grad_norm": 0.5796473026275635,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.2206,
+      "step": 42
+    },
+    {
+      "epoch": 0.17059261095958345,
+      "grad_norm": 0.6185922622680664,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.2557,
+      "step": 43
+    },
+    {
+      "epoch": 0.17455988098189934,
+      "grad_norm": 0.648368239402771,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.2409,
+      "step": 44
+    },
+    {
+      "epoch": 0.17852715100421523,
+      "grad_norm": 0.7235672473907471,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.2006,
+      "step": 45
+    },
+    {
+      "epoch": 0.18249442102653113,
+      "grad_norm": 0.8252574801445007,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.2917,
+      "step": 46
+    },
+    {
+      "epoch": 0.18646169104884702,
+      "grad_norm": 0.9163631796836853,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.2976,
+      "step": 47
+    },
+    {
+      "epoch": 0.19042896107116292,
+      "grad_norm": 0.9612374901771545,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.1845,
+      "step": 48
+    },
+    {
+      "epoch": 0.1943962310934788,
+      "grad_norm": 1.0789424180984497,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.1664,
+      "step": 49
+    },
+    {
+      "epoch": 0.1983635011157947,
+      "grad_norm": 1.5217560529708862,
+      "learning_rate": 0.0,
+      "loss": 3.2755,
+      "step": 50
+    },
+    {
+      "epoch": 0.1983635011157947,
+      "eval_loss": 3.218653678894043,
+      "eval_runtime": 11.5312,
+      "eval_samples_per_second": 147.339,
+      "eval_steps_per_second": 18.472,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null