Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2dbc9af92618e44ba05ecf9266f2ca6c56f6d54e7c048d98661874030cd557
+oid sha256:29ae7e82601432cd0cf2fcd12eaecebd44ad47eebc9149aebb8e172cc7a9b742
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124a6b934dd5aca5013661811284fae6ca9f3c31e658170ba90c88a860e4de52
+oid sha256:033eb6ba41bb743049b58ba6b8a5897f70d65b029ecbbc51caec45d759ae6f6f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99239d229340ad3da97c9e17664a2ac00da2473edddf7600cee6a8362e64e994
+oid sha256:4a9036a48ee33c44723a55ca00417a8adb2800b69162145bc7f9f12ceaf6331d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c687829b2af827902cfe9a2e746ad7e7839cffcaedf5abc0ec5a74adee4c1d4
+oid sha256:4f0481ff96072168fab2cf5fba949db3498e913da6e37af45da095add02d7239
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c92ed6c1cebae5523517c828b5dc98645245777bef80b839dbbe9dc639f088
+oid sha256:4ba5c75f88ea7636819006304fe45c010fc90f15f12395fbf8323e79071cc1eb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c9dd9b9222f6dd6c3afe83fd1640eb0877218c975be7a14cd00e250ad81b8d8
+oid sha256:ce03d1c81d147e78024b0d03c51e5da350823f876114418cf7f8151fb4c9e287
 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": 0.08177092671394348,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5319148936170213,
+  "best_metric": 0.06177634373307228,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0638297872340425,
   "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": 15.095,
       "eval_steps_per_second": 1.905,
       "step": 25
+    },
+    {
+      "epoch": 0.5531914893617021,
+      "grad_norm": 3.5168380737304688,
+      "learning_rate": 5e-05,
+      "loss": 1.2512,
+      "step": 26
+    },
+    {
+      "epoch": 0.574468085106383,
+      "grad_norm": 22.19098663330078,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5594,
+      "step": 27
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 5.936686038970947,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1637,
+      "step": 28
+    },
+    {
+      "epoch": 0.6170212765957447,
+      "grad_norm": 16.02676773071289,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2632,
+      "step": 29
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 14.360878944396973,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1993,
+      "step": 30
+    },
+    {
+      "epoch": 0.6595744680851063,
+      "grad_norm": 27.750530242919922,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1324,
+      "step": 31
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 33.4967041015625,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0415,
+      "step": 32
+    },
+    {
+      "epoch": 0.7021276595744681,
+      "grad_norm": 13.943852424621582,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7634,
+      "step": 33
+    },
+    {
+      "epoch": 0.723404255319149,
+      "grad_norm": 16.322202682495117,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7164,
+      "step": 34
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 14.58661937713623,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.2368,
+      "step": 35
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 12.963841438293457,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.2842,
+      "step": 36
+    },
+    {
+      "epoch": 0.7872340425531915,
+      "grad_norm": 26.34542465209961,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7286,
+      "step": 37
+    },
+    {
+      "epoch": 0.8085106382978723,
+      "grad_norm": 10.058424949645996,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0142,
+      "step": 38
+    },
+    {
+      "epoch": 0.8297872340425532,
+      "grad_norm": 17.854799270629883,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9395,
+      "step": 39
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 14.591531753540039,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6999,
+      "step": 40
+    },
+    {
+      "epoch": 0.8723404255319149,
+      "grad_norm": 18.455177307128906,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9498,
+      "step": 41
+    },
+    {
+      "epoch": 0.8936170212765957,
+      "grad_norm": 25.038835525512695,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.246,
+      "step": 42
+    },
+    {
+      "epoch": 0.9148936170212766,
+      "grad_norm": 14.889090538024902,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0996,
+      "step": 43
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 26.219545364379883,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.508,
+      "step": 44
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 15.979211807250977,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9828,
+      "step": 45
+    },
+    {
+      "epoch": 0.9787234042553191,
+      "grad_norm": 13.021293640136719,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4054,
+      "step": 46
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 15.820076942443848,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9171,
+      "step": 47
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 27.00518226623535,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0428,
+      "step": 48
+    },
+    {
+      "epoch": 1.0425531914893618,
+      "grad_norm": 13.826783180236816,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.661,
+      "step": 49
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 11.46463680267334,
+      "learning_rate": 0.0,
+      "loss": 0.7936,
+      "step": 50
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "eval_loss": 0.06177634373307228,
+      "eval_runtime": 20.9876,
+      "eval_samples_per_second": 15.104,
+      "eval_steps_per_second": 1.906,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null