Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:433505514de7161c3989cf50c4728dfd4df7d71b5e3e06f544f63d2182fddf38
+oid sha256:37dbab2e8759ea6a0c82928c4d70103c8260aec0d081c2d7d5c76fb94701c24c
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1363f0c7d269eeac60ca270cee259d1042a33a6c7f6f609fae004006f45c283
+oid sha256:de8d6699f9700c7f47caf14924ebfb3debd01f89b149b458f0b7d433a8d3ce05
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f7d23fcbd9ec61efd175c137436a90b0329947bf2915c551cf24fcf20b8891
+oid sha256:50a602e7cd827ff4fcd8e6f6caeb6592b9deeacaaac03dcbbe1c95eecb89912e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13363b09ad980385f6677034e1af85fe34f5185febd2e296b362529a1238782a
+oid sha256:87e96e5b8e9719329082a9ce8377ba7d026548793818af9e7f6e76046a2b5b14
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1500756e888c0e0d63172fedd92f3216b6237f46a7a25ae51a6345e74663c50e
+oid sha256:cb5255779ee5048c42aa788e1c85c4fd90dca03b96a146b6ac735a1312f21941
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e931f27b730b828872ceefb0679ecf9ae748162cd357604d47df188b4e80ff7a
+oid sha256:a9ea90d34442a809eb1893806da61a67daa0fc0ebe7a5a5e1fd89d1ee5e60434
 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": 0.4141184985637665,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.021777596297808628,
+  "best_metric": 0.3801743686199188,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.032666394446712946,
   "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": 203.605,
       "eval_steps_per_second": 52.937,
       "step": 50
+    },
+    {
+      "epoch": 0.0222131482237648,
+      "grad_norm": 0.24732612073421478,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 0.2459,
+      "step": 51
+    },
+    {
+      "epoch": 0.022648700149720976,
+      "grad_norm": 0.20642635226249695,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 0.2487,
+      "step": 52
+    },
+    {
+      "epoch": 0.023084252075677148,
+      "grad_norm": 0.22898025810718536,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 0.2472,
+      "step": 53
+    },
+    {
+      "epoch": 0.02351980400163332,
+      "grad_norm": 0.22252477705478668,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 0.2727,
+      "step": 54
+    },
+    {
+      "epoch": 0.023955355927589492,
+      "grad_norm": 0.19623643159866333,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 0.2588,
+      "step": 55
+    },
+    {
+      "epoch": 0.024390907853545665,
+      "grad_norm": 0.20294366776943207,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 0.2963,
+      "step": 56
+    },
+    {
+      "epoch": 0.024826459779501837,
+      "grad_norm": 0.20770514011383057,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 0.3126,
+      "step": 57
+    },
+    {
+      "epoch": 0.02526201170545801,
+      "grad_norm": 0.19810672104358673,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 0.3228,
+      "step": 58
+    },
+    {
+      "epoch": 0.02569756363141418,
+      "grad_norm": 0.1933719962835312,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 0.3274,
+      "step": 59
+    },
+    {
+      "epoch": 0.026133115557370357,
+      "grad_norm": 0.2459198236465454,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 0.3681,
+      "step": 60
+    },
+    {
+      "epoch": 0.02656866748332653,
+      "grad_norm": 0.3370075821876526,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 0.5462,
+      "step": 61
+    },
+    {
+      "epoch": 0.0270042194092827,
+      "grad_norm": 0.5243966579437256,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.7319,
+      "step": 62
+    },
+    {
+      "epoch": 0.027439771335238873,
+      "grad_norm": 0.5417724251747131,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 0.3378,
+      "step": 63
+    },
+    {
+      "epoch": 0.027875323261195045,
+      "grad_norm": 0.4117334485054016,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 0.221,
+      "step": 64
+    },
+    {
+      "epoch": 0.028310875187151217,
+      "grad_norm": 0.20625002682209015,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 0.2245,
+      "step": 65
+    },
+    {
+      "epoch": 0.02874642711310739,
+      "grad_norm": 0.16709944605827332,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 0.2614,
+      "step": 66
+    },
+    {
+      "epoch": 0.02918197903906356,
+      "grad_norm": 0.1745489239692688,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 0.2537,
+      "step": 67
+    },
+    {
+      "epoch": 0.029617530965019737,
+      "grad_norm": 0.20561543107032776,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 0.2623,
+      "step": 68
+    },
+    {
+      "epoch": 0.03005308289097591,
+      "grad_norm": 0.1879180371761322,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 0.2818,
+      "step": 69
+    },
+    {
+      "epoch": 0.03048863481693208,
+      "grad_norm": 0.2245042622089386,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 0.3014,
+      "step": 70
+    },
+    {
+      "epoch": 0.030924186742888254,
+      "grad_norm": 0.23973950743675232,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 0.3235,
+      "step": 71
+    },
+    {
+      "epoch": 0.03135973866884443,
+      "grad_norm": 0.23406189680099487,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 0.3335,
+      "step": 72
+    },
+    {
+      "epoch": 0.0317952905948006,
+      "grad_norm": 0.2864845097064972,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 0.4684,
+      "step": 73
+    },
+    {
+      "epoch": 0.032230842520756774,
+      "grad_norm": 0.3619403541088104,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 0.6046,
+      "step": 74
+    },
+    {
+      "epoch": 0.032666394446712946,
+      "grad_norm": 0.6084543466567993,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 0.8631,
+      "step": 75
+    },
+    {
+      "epoch": 0.032666394446712946,
+      "eval_loss": 0.3801743686199188,
+      "eval_runtime": 0.2473,
+      "eval_samples_per_second": 202.169,
+      "eval_steps_per_second": 52.564,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.13737243557888e+16,
+  "total_flos": 1.70605865336832e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null