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:ca5cd3d63b4903fef286a6694f463d1906db30a2c7560b23a1e228cb448a7d14
+oid sha256:906ab5c72a66a822dc060527e20fb9aaad3e1fe2fced82eaf47616ffdbfc22a5
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba9f4419379ad0d79a1c88af97b2efc7faa22c31bf9496537670b4def43be49
+oid sha256:14c36267f93ac4e07961fe2c6acd1df381e7947abd9b25e71eef62925949563e
 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": 1.307538628578186,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.12424289485945023,
+  "best_metric": 1.3009710311889648,
+  "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": 42.037,
       "eval_steps_per_second": 10.93,
       "step": 50
+    },
+    {
+      "epoch": 0.12672775275663922,
+      "grad_norm": 0.1314828097820282,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 1.0635,
+      "step": 51
+    },
+    {
+      "epoch": 0.12921261065382825,
+      "grad_norm": 0.14226771891117096,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 1.135,
+      "step": 52
+    },
+    {
+      "epoch": 0.13169746855101724,
+      "grad_norm": 0.16140902042388916,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 1.0796,
+      "step": 53
+    },
+    {
+      "epoch": 0.13418232644820624,
+      "grad_norm": 0.1799178272485733,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 1.1422,
+      "step": 54
+    },
+    {
+      "epoch": 0.13666718434539524,
+      "grad_norm": 0.2081109583377838,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 1.2189,
+      "step": 55
+    },
+    {
+      "epoch": 0.13915204224258426,
+      "grad_norm": 0.25022587180137634,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 1.2379,
+      "step": 56
+    },
+    {
+      "epoch": 0.14163690013977326,
+      "grad_norm": 0.28561145067214966,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 1.2227,
+      "step": 57
+    },
+    {
+      "epoch": 0.14412175803696226,
+      "grad_norm": 0.39062267541885376,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 1.4685,
+      "step": 58
+    },
+    {
+      "epoch": 0.14660661593415125,
+      "grad_norm": 0.44714751839637756,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 1.391,
+      "step": 59
+    },
+    {
+      "epoch": 0.14909147383134028,
+      "grad_norm": 0.5737501382827759,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 1.4773,
+      "step": 60
+    },
+    {
+      "epoch": 0.15157633172852927,
+      "grad_norm": 0.6805304884910583,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 1.5433,
+      "step": 61
+    },
+    {
+      "epoch": 0.15406118962571827,
+      "grad_norm": 0.9832828044891357,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 1.7847,
+      "step": 62
+    },
+    {
+      "epoch": 0.1565460475229073,
+      "grad_norm": 0.14597496390342712,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 1.0738,
+      "step": 63
+    },
+    {
+      "epoch": 0.1590309054200963,
+      "grad_norm": 0.12474174797534943,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 1.0669,
+      "step": 64
+    },
+    {
+      "epoch": 0.1615157633172853,
+      "grad_norm": 0.13938696682453156,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 1.0996,
+      "step": 65
+    },
+    {
+      "epoch": 0.16400062121447428,
+      "grad_norm": 0.14947223663330078,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 1.1537,
+      "step": 66
+    },
+    {
+      "epoch": 0.1664854791116633,
+      "grad_norm": 0.15758228302001953,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 1.1751,
+      "step": 67
+    },
+    {
+      "epoch": 0.1689703370088523,
+      "grad_norm": 0.1946917325258255,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 1.2175,
+      "step": 68
+    },
+    {
+      "epoch": 0.1714551949060413,
+      "grad_norm": 0.22615738213062286,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 1.2667,
+      "step": 69
+    },
+    {
+      "epoch": 0.17394005280323033,
+      "grad_norm": 0.2879005968570709,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 1.3261,
+      "step": 70
+    },
+    {
+      "epoch": 0.17642491070041932,
+      "grad_norm": 0.385571151971817,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 1.3998,
+      "step": 71
+    },
+    {
+      "epoch": 0.17890976859760832,
+      "grad_norm": 0.4972687363624573,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 1.4713,
+      "step": 72
+    },
+    {
+      "epoch": 0.18139462649479732,
+      "grad_norm": 0.6449961066246033,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 1.5434,
+      "step": 73
+    },
+    {
+      "epoch": 0.18387948439198634,
+      "grad_norm": 0.8163850903511047,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 1.5494,
+      "step": 74
+    },
+    {
+      "epoch": 0.18636434228917534,
+      "grad_norm": 1.7719392776489258,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 2.154,
+      "step": 75
+    },
+    {
+      "epoch": 0.18636434228917534,
+      "eval_loss": 1.3009710311889648,
+      "eval_runtime": 1.193,
+      "eval_samples_per_second": 41.91,
+      "eval_steps_per_second": 10.897,
+      "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