Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cad10b92bff94191d65d9963421f13037fbdcf8cc901a320cdca10760f89fbd
+oid sha256:9ae1df6bfc14931b81d95afab24ef7deff4cc0603110fd52691b876634aff55f
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15dc414cd70a7ddede42fd5059056276b98faf382da29b3a9cd6a5324ca533bb
+oid sha256:9842354ad999616c4a695315f2fb4d4fd783004f60c69ec8350f2ad83d9d55d2
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f398d6d5e0292aaa60975bde0021b09e40fb2f522e3913641ce55f7b2e96b22
+oid sha256:ff9e8b8959b07c3fcc4f9a3ecd8d26c9bc6096133f8fd0f9a8688bac5888efda
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df5e5050a0ff52cea44571b5037b2909f550f4879890bcf49e688c2671f68f9
+oid sha256:fe87338e4ba1efd5d615d5d9baf393a9bb34e6e665458d2ef6480a0343b58576
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1abb0ed6b0c795813dab66118b7479b2f2e1b632b1902fa102c055457e0c6d81
+oid sha256:f9feb013a9ce7056e3488998d9a831e050654b4244b85f51fbe285a5fe5a87e6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0113767a544a32bb207ff2dd5c575a16fbf9912cbc10a44094bfa00ffb1875f
+oid sha256:ad6363d5dd06bb5249784913af943f8827dec701824daf31079ab08d251023f4
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3052322566509247,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.1554605518849592,
+  "best_metric": 0.29731500148773193,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3109211037699184,
   "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": 75.543,
       "eval_steps_per_second": 19.641,
       "step": 25
+    },
+    {
+      "epoch": 0.16167897396035755,
+      "grad_norm": 0.05467255786061287,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3056,
+      "step": 26
+    },
+    {
+      "epoch": 0.16789739603575593,
+      "grad_norm": 0.07083805650472641,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.2749,
+      "step": 27
+    },
+    {
+      "epoch": 0.17411581811115429,
+      "grad_norm": 0.07528531551361084,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.2818,
+      "step": 28
+    },
+    {
+      "epoch": 0.18033424018655267,
+      "grad_norm": 0.09004832059144974,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.2856,
+      "step": 29
+    },
+    {
+      "epoch": 0.18655266226195102,
+      "grad_norm": 0.10006168484687805,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.2992,
+      "step": 30
+    },
+    {
+      "epoch": 0.1927710843373494,
+      "grad_norm": 0.10617878288030624,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.2736,
+      "step": 31
+    },
+    {
+      "epoch": 0.19898950641274776,
+      "grad_norm": 0.10531214624643326,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.251,
+      "step": 32
+    },
+    {
+      "epoch": 0.20520792848814615,
+      "grad_norm": 0.12280702590942383,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2671,
+      "step": 33
+    },
+    {
+      "epoch": 0.2114263505635445,
+      "grad_norm": 0.13969354331493378,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2841,
+      "step": 34
+    },
+    {
+      "epoch": 0.21764477263894286,
+      "grad_norm": 0.1534193456172943,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3061,
+      "step": 35
+    },
+    {
+      "epoch": 0.22386319471434124,
+      "grad_norm": 0.17459821701049805,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3199,
+      "step": 36
+    },
+    {
+      "epoch": 0.2300816167897396,
+      "grad_norm": 0.20583975315093994,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3434,
+      "step": 37
+    },
+    {
+      "epoch": 0.23630003886513798,
+      "grad_norm": 0.06656050682067871,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3414,
+      "step": 38
+    },
+    {
+      "epoch": 0.24251846094053633,
+      "grad_norm": 0.06291203200817108,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.2861,
+      "step": 39
+    },
+    {
+      "epoch": 0.24873688301593472,
+      "grad_norm": 0.07160060852766037,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.275,
+      "step": 40
+    },
+    {
+      "epoch": 0.2549553050913331,
+      "grad_norm": 0.08236276358366013,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3031,
+      "step": 41
+    },
+    {
+      "epoch": 0.26117372716673143,
+      "grad_norm": 0.16188380122184753,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.2749,
+      "step": 42
+    },
+    {
+      "epoch": 0.2673921492421298,
+      "grad_norm": 0.0924171581864357,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2471,
+      "step": 43
+    },
+    {
+      "epoch": 0.2736105713175282,
+      "grad_norm": 0.11398671567440033,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2917,
+      "step": 44
+    },
+    {
+      "epoch": 0.27982899339292655,
+      "grad_norm": 0.11780249327421188,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.273,
+      "step": 45
+    },
+    {
+      "epoch": 0.2860474154683249,
+      "grad_norm": 0.13337303698062897,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.2713,
+      "step": 46
+    },
+    {
+      "epoch": 0.29226583754372326,
+      "grad_norm": 0.12880964577198029,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3067,
+      "step": 47
+    },
+    {
+      "epoch": 0.2984842596191217,
+      "grad_norm": 0.14828264713287354,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3396,
+      "step": 48
+    },
+    {
+      "epoch": 0.30470268169452003,
+      "grad_norm": 0.15794625878334045,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3561,
+      "step": 49
+    },
+    {
+      "epoch": 0.3109211037699184,
+      "grad_norm": 0.23790889978408813,
+      "learning_rate": 1e-05,
+      "loss": 0.3821,
+      "step": 50
+    },
+    {
+      "epoch": 0.3109211037699184,
+      "eval_loss": 0.29731500148773193,
+      "eval_runtime": 0.6608,
+      "eval_samples_per_second": 75.67,
+      "eval_steps_per_second": 19.674,
+      "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": 5.310925972176896e+16,
+  "total_flos": 1.0618540886956442e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null