Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f610f59dd113c878919b2852417456c8aade40c6a964d1e53eda826cd05db07
+oid sha256:34a294f9f631f1668faaefb13e182122fa2cbaa290c86dc007587b18bbed489a
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe88636ca9485a1d25b9ec6c685235f4bdc57d8b108c483370b9967e1ee53b7c
+oid sha256:c6500276761b3590196bcb8ee001f4a7e3279f9ffaf84c14d68cd661a3a8677c
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed99a13c6fad0f3bfc2711f3a09d74be1371eea7a3664944c1e31b4d134a94ad
+oid sha256:31219084b467b97768d0c2266a9ac1fa136aa77e7a456c5fe811bd8a008c304d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3813de28a115e58309f0fdbd484c8709fa2daf3049d6fb53def40c5e363e1085
+oid sha256:e364602b08d6e7bce980ac532681b92b90e8573a99149b3bfe3fc9c168a42778
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e028239fed62af78822eed5d9893175e8d7ae96b7f1c6861f0d0314db33159b2
+oid sha256:465a00ab0425765e7347a156c4b8feff78bd094df0231f37892a2473663631ec
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31353de36fb8e94dc0a01f50a320de6e0d50070de2f10bd47fdfa2e740bd3356
+oid sha256:9913e481e3398d89683d00a3e7aebbd363947d2c1209e74fa33e7051afbfb940
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
+oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4773844480514526,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.12424289485945023,
+  "best_metric": 1.4348056316375732,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.18636434228917534,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 99.704,
       "eval_steps_per_second": 25.923,
       "step": 50
+    },
+    {
+      "epoch": 0.12672775275663922,
+      "grad_norm": 0.20560088753700256,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 1.1799,
+      "step": 51
+    },
+    {
+      "epoch": 0.12921261065382825,
+      "grad_norm": 0.23120570182800293,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 1.2372,
+      "step": 52
+    },
+    {
+      "epoch": 0.13169746855101724,
+      "grad_norm": 0.23276279866695404,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 1.1809,
+      "step": 53
+    },
+    {
+      "epoch": 0.13418232644820624,
+      "grad_norm": 0.24758167564868927,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 1.2471,
+      "step": 54
+    },
+    {
+      "epoch": 0.13666718434539524,
+      "grad_norm": 0.27665722370147705,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 1.3109,
+      "step": 55
+    },
+    {
+      "epoch": 0.13915204224258426,
+      "grad_norm": 0.3292866051197052,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 1.3299,
+      "step": 56
+    },
+    {
+      "epoch": 0.14163690013977326,
+      "grad_norm": 0.33890780806541443,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 1.3129,
+      "step": 57
+    },
+    {
+      "epoch": 0.14412175803696226,
+      "grad_norm": 0.4250866174697876,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 1.5612,
+      "step": 58
+    },
+    {
+      "epoch": 0.14660661593415125,
+      "grad_norm": 0.624860942363739,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 1.5192,
+      "step": 59
+    },
+    {
+      "epoch": 0.14909147383134028,
+      "grad_norm": 0.8327329754829407,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 1.5965,
+      "step": 60
+    },
+    {
+      "epoch": 0.15157633172852927,
+      "grad_norm": 1.0322227478027344,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 1.7066,
+      "step": 61
+    },
+    {
+      "epoch": 0.15406118962571827,
+      "grad_norm": 1.6692428588867188,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 1.9786,
+      "step": 62
+    },
+    {
+      "epoch": 0.1565460475229073,
+      "grad_norm": 0.21098101139068604,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 1.1647,
+      "step": 63
+    },
+    {
+      "epoch": 0.1590309054200963,
+      "grad_norm": 0.19633238017559052,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 1.1685,
+      "step": 64
+    },
+    {
+      "epoch": 0.1615157633172853,
+      "grad_norm": 0.2040661871433258,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 1.1929,
+      "step": 65
+    },
+    {
+      "epoch": 0.16400062121447428,
+      "grad_norm": 0.2036914974451065,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 1.2412,
+      "step": 66
+    },
+    {
+      "epoch": 0.1664854791116633,
+      "grad_norm": 0.21338950097560883,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 1.273,
+      "step": 67
+    },
+    {
+      "epoch": 0.1689703370088523,
+      "grad_norm": 0.26673391461372375,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 1.3177,
+      "step": 68
+    },
+    {
+      "epoch": 0.1714551949060413,
+      "grad_norm": 0.3049785792827606,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 1.3569,
+      "step": 69
+    },
+    {
+      "epoch": 0.17394005280323033,
+      "grad_norm": 0.3914351463317871,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 1.4214,
+      "step": 70
+    },
+    {
+      "epoch": 0.17642491070041932,
+      "grad_norm": 0.4944564998149872,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 1.4842,
+      "step": 71
+    },
+    {
+      "epoch": 0.17890976859760832,
+      "grad_norm": 0.7299094200134277,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 1.607,
+      "step": 72
+    },
+    {
+      "epoch": 0.18139462649479732,
+      "grad_norm": 0.9269328713417053,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 1.7074,
+      "step": 73
+    },
+    {
+      "epoch": 0.18387948439198634,
+      "grad_norm": 1.1799345016479492,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 1.6967,
+      "step": 74
+    },
+    {
+      "epoch": 0.18636434228917534,
+      "grad_norm": 2.2998039722442627,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 2.2813,
+      "step": 75
+    },
+    {
+      "epoch": 0.18636434228917534,
+      "eval_loss": 1.4348056316375732,
+      "eval_runtime": 0.5016,
+      "eval_samples_per_second": 99.679,
+      "eval_steps_per_second": 25.917,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.33416392081408e+16,
+  "total_flos": 1.250124588122112e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null