Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09e9c5f105510a23cc0aa2d80c517f777dbe1f544c75b1dd87f31efb31083a21
+oid sha256:8ecd385d5f80bea477b6ef0bf0a7b44a55a2b8cf0f9b42d3e2a8071737605c5e
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b75248810781dce592da826c0d604f08b427bb442da5778a8b2084f707fd8e36
+oid sha256:2fa04b9847d925537be1cab13285382ecaaf31386f6665ea8a0f1b6d1af0b0ee
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:393537bde649a7471201f231f427d348be0bedc69e89ff06c56dc3bbf6335973
+oid sha256:d94b7bbf8783a0aae1ba84fa48a1d4977c38e874ef1e60520e674a4bded6dc46
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7808d9b73f3ac91a73ccd7e092d2b3221aa25cf6a5c99876ef75fda2b09908db
+oid sha256:88ca0fa750bab542343a58e543a0108e2b89b42b47ed224049b10bd06232e653
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae47d80c8d3eba746fa9cd48f5aabe40ef6afdb203089bc00e7db904c9d16c7
+oid sha256:93cdf3b927baec2b53f29582b579b2df3b7fb848d34370bcb21ce9b8df1471f2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a3c94a132b16a1c63173e5e5862c03d5534cdb9009230f5f5d0a9d6762b4bb
+oid sha256:3a8eebe555bfcbd6d9354c7ffcbabccf0c134bdbc821e7d873884d0bc6d8b416
 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": 1.5458736419677734,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03374957813027337,
+  "best_metric": 1.5239598751068115,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06749915626054674,
   "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": 82.81,
       "eval_steps_per_second": 10.355,
       "step": 25
+    },
+    {
+      "epoch": 0.03509956125548431,
+      "grad_norm": 0.1637115478515625,
+      "learning_rate": 5e-05,
+      "loss": 1.5338,
+      "step": 26
+    },
+    {
+      "epoch": 0.03644954438069524,
+      "grad_norm": 0.15709365904331207,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6281,
+      "step": 27
+    },
+    {
+      "epoch": 0.03779952750590618,
+      "grad_norm": 0.1496843695640564,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.5876,
+      "step": 28
+    },
+    {
+      "epoch": 0.03914951063111711,
+      "grad_norm": 0.1532595306634903,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6034,
+      "step": 29
+    },
+    {
+      "epoch": 0.040499493756328046,
+      "grad_norm": 0.17774361371994019,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6162,
+      "step": 30
+    },
+    {
+      "epoch": 0.041849476881538984,
+      "grad_norm": 0.20477358996868134,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6262,
+      "step": 31
+    },
+    {
+      "epoch": 0.043199460006749915,
+      "grad_norm": 0.2279857099056244,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.6413,
+      "step": 32
+    },
+    {
+      "epoch": 0.04454944313196085,
+      "grad_norm": 0.26761552691459656,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.6181,
+      "step": 33
+    },
+    {
+      "epoch": 0.045899426257171784,
+      "grad_norm": 0.2836780548095703,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.661,
+      "step": 34
+    },
+    {
+      "epoch": 0.04724940938238272,
+      "grad_norm": 0.28761908411979675,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4622,
+      "step": 35
+    },
+    {
+      "epoch": 0.04859939250759365,
+      "grad_norm": 0.2977994382381439,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4873,
+      "step": 36
+    },
+    {
+      "epoch": 0.04994937563280459,
+      "grad_norm": 0.35102325677871704,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.3988,
+      "step": 37
+    },
+    {
+      "epoch": 0.05129935875801552,
+      "grad_norm": 0.14832736551761627,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6195,
+      "step": 38
+    },
+    {
+      "epoch": 0.05264934188322646,
+      "grad_norm": 0.12129808962345123,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6259,
+      "step": 39
+    },
+    {
+      "epoch": 0.0539993250084374,
+      "grad_norm": 0.12143447995185852,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5587,
+      "step": 40
+    },
+    {
+      "epoch": 0.05534930813364833,
+      "grad_norm": 0.13339225947856903,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.543,
+      "step": 41
+    },
+    {
+      "epoch": 0.056699291258859266,
+      "grad_norm": 0.1377297043800354,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5017,
+      "step": 42
+    },
+    {
+      "epoch": 0.0580492743840702,
+      "grad_norm": 0.1632794588804245,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.5993,
+      "step": 43
+    },
+    {
+      "epoch": 0.059399257509281135,
+      "grad_norm": 0.17088504135608673,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.644,
+      "step": 44
+    },
+    {
+      "epoch": 0.060749240634492066,
+      "grad_norm": 0.1868760585784912,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.645,
+      "step": 45
+    },
+    {
+      "epoch": 0.062099223759703004,
+      "grad_norm": 0.21565905213356018,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5193,
+      "step": 46
+    },
+    {
+      "epoch": 0.06344920688491394,
+      "grad_norm": 0.24631474912166595,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5493,
+      "step": 47
+    },
+    {
+      "epoch": 0.06479919001012488,
+      "grad_norm": 0.2667161226272583,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4677,
+      "step": 48
+    },
+    {
+      "epoch": 0.0661491731353358,
+      "grad_norm": 0.31782612204551697,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.4427,
+      "step": 49
+    },
+    {
+      "epoch": 0.06749915626054674,
+      "grad_norm": 0.36279669404029846,
+      "learning_rate": 0.0,
+      "loss": 1.3635,
+      "step": 50
+    },
+    {
+      "epoch": 0.06749915626054674,
+      "eval_loss": 1.5239598751068115,
+      "eval_runtime": 60.733,
+      "eval_samples_per_second": 82.163,
+      "eval_steps_per_second": 10.274,
+      "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": 4.727621309746381e+16,
+  "total_flos": 9.411196468225638e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null