Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f73a1e23a417367c5a9668264f1eb9f0ae978643897a10430d165db48639a26f
+oid sha256:c18b924e9f94faa2194c7dd165d815f5bad3562d15d7d8755923a4efc4d3c166
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd8261692559781739203e2597ba1dd46a9fa144476d53d3f25d02117ea6f9d
+oid sha256:a961572d93f460389a432fa1bc4312972bbda4259583020c0e5dc03bc63f0af8
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f680f1df5166c32096111cd9904604cb506551c7aa7236fc44053f1327df18
+oid sha256:f93a1d0de4f7c19691454ad529d0353516a3e1eb23d9afad1c3d52995855276f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55d3e7c1ed0c97284af244303bca6a5d088d8cb3b01d30724439d8b3ccafefb8
+oid sha256:bcb75c6922499baeeed67a00e449f5c50cc9e2e1d8c3c20af2cdb8e08ee582bb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1b0f4f26c760c2d49353619e173b0a05b570d23be5bc83f03b5b6f0e3ceb5b2
+oid sha256:8e6d2520db646d11fc16ab1481a74170d3f4375da45df57d7d1ae1e4f9c79f3b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ef00efea6ec0eb927725c06f8b8e9493d8000e50113a39e9fe9bb49143fde6
+oid sha256:bf6e900df2749ef46238c8122fd74ed7b619f9726a98de0c4df1a9719ca0f99f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370cee31176b8bff781da8f054b9870dc93c63a8623674218a84718aa7abd3af
+oid sha256:051dee7dfbeecb34b46e8409ffafec324501f465585234624669bc8c9e863ae4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0358448028564453,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.035737685389242956,
+  "best_metric": 2.0155577659606934,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.047650247185657274,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 24.129,
       "eval_steps_per_second": 6.273,
       "step": 75
+    },
+    {
+      "epoch": 0.03621418786109953,
+      "grad_norm": 1.061888575553894,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.0602,
+      "step": 76
+    },
+    {
+      "epoch": 0.036690690332956105,
+      "grad_norm": 1.073085904121399,
+      "learning_rate": 2.215611672859741e-05,
+      "loss": 2.1428,
+      "step": 77
+    },
+    {
+      "epoch": 0.037167192804812677,
+      "grad_norm": 1.0822275876998901,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.1602,
+      "step": 78
+    },
+    {
+      "epoch": 0.03764369527666925,
+      "grad_norm": 1.0458821058273315,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 2.055,
+      "step": 79
+    },
+    {
+      "epoch": 0.03812019774852582,
+      "grad_norm": 1.0914690494537354,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.0903,
+      "step": 80
+    },
+    {
+      "epoch": 0.03859670022038239,
+      "grad_norm": 1.0751844644546509,
+      "learning_rate": 1.842189919337732e-05,
+      "loss": 2.0763,
+      "step": 81
+    },
+    {
+      "epoch": 0.03907320269223897,
+      "grad_norm": 1.065314531326294,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.0768,
+      "step": 82
+    },
+    {
+      "epoch": 0.03954970516409554,
+      "grad_norm": 0.9963571429252625,
+      "learning_rate": 1.6785901831303956e-05,
+      "loss": 2.1178,
+      "step": 83
+    },
+    {
+      "epoch": 0.04002620763595211,
+      "grad_norm": 1.0645560026168823,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.0319,
+      "step": 84
+    },
+    {
+      "epoch": 0.04050271010780868,
+      "grad_norm": 1.1069632768630981,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 2.1816,
+      "step": 85
+    },
+    {
+      "epoch": 0.040979212579665254,
+      "grad_norm": 1.0914970636367798,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.0122,
+      "step": 86
+    },
+    {
+      "epoch": 0.04145571505152183,
+      "grad_norm": 1.220619797706604,
+      "learning_rate": 1.4011127878547087e-05,
+      "loss": 2.26,
+      "step": 87
+    },
+    {
+      "epoch": 0.041932217523378404,
+      "grad_norm": 1.2335286140441895,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.2017,
+      "step": 88
+    },
+    {
+      "epoch": 0.042408719995234975,
+      "grad_norm": 1.0788054466247559,
+      "learning_rate": 1.2884233295920353e-05,
+      "loss": 2.1318,
+      "step": 89
+    },
+    {
+      "epoch": 0.04288522246709155,
+      "grad_norm": 1.0492669343948364,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.0355,
+      "step": 90
+    },
+    {
+      "epoch": 0.04336172493894812,
+      "grad_norm": 1.109262466430664,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 2.0891,
+      "step": 91
+    },
+    {
+      "epoch": 0.043838227410804696,
+      "grad_norm": 1.066548228263855,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.9607,
+      "step": 92
+    },
+    {
+      "epoch": 0.04431472988266127,
+      "grad_norm": 1.1744662523269653,
+      "learning_rate": 1.1175535932519987e-05,
+      "loss": 2.1241,
+      "step": 93
+    },
+    {
+      "epoch": 0.04479123235451784,
+      "grad_norm": 1.099749207496643,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.1312,
+      "step": 94
+    },
+    {
+      "epoch": 0.04526773482637441,
+      "grad_norm": 1.049397349357605,
+      "learning_rate": 1.0601050056180447e-05,
+      "loss": 2.0349,
+      "step": 95
+    },
+    {
+      "epoch": 0.04574423729823098,
+      "grad_norm": 1.1223000288009644,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.1497,
+      "step": 96
+    },
+    {
+      "epoch": 0.04622073977008756,
+      "grad_norm": 1.1168677806854248,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 2.0932,
+      "step": 97
+    },
+    {
+      "epoch": 0.04669724224194413,
+      "grad_norm": 1.1823430061340332,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.1753,
+      "step": 98
+    },
+    {
+      "epoch": 0.0471737447138007,
+      "grad_norm": 1.2020727396011353,
+      "learning_rate": 1.0024093563563546e-05,
+      "loss": 2.1313,
+      "step": 99
+    },
+    {
+      "epoch": 0.047650247185657274,
+      "grad_norm": 1.3995245695114136,
+      "learning_rate": 1e-05,
+      "loss": 2.3944,
+      "step": 100
+    },
+    {
+      "epoch": 0.047650247185657274,
+      "eval_loss": 2.0155577659606934,
+      "eval_runtime": 2.0739,
+      "eval_samples_per_second": 24.109,
+      "eval_steps_per_second": 6.268,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.43721341763584e+17,
+  "total_flos": 3.24961789018112e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null