Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9eb4dca174a98560b04c92824e14c3085d0b08cf2e490ea5fae3547f54ae00
+oid sha256:c8d09a40f0f079a10711ac5e5e6c30748d0c429c6f65d05f6eb880bee88f8e27
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c77551bc9e1d0525c97e4102f2f92266a3cfb9acbafddc9d5d45e330675f09c4
+oid sha256:45274b8fcd1e550eac9e157eea3669ba3e5c929b78e9900b5faf017713e78b7a
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8157b51842d6bc4f029ef64b31a7a7a9436acfdd804e4b831794f68643c4d742
+oid sha256:662b3af3afccb427bbaba8887715540fcc035c071a766681b89fd98d5564317d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac9562147e29fc5ccb755493a2e76c81ac8d400bc2d4769fa66947bc74bc652
+oid sha256:9c49f00976105a96c5c227af8f48c57ac723055549cd3d3736d98eea5b4897ba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967c052fdb274f96bfd1edc249fa586018e536d154ada9a041589fc9ecaf6b41
+oid sha256:854e2f104af2cd3fa0c2a3def4e117851e44cceb92866c22c5329853917d0b34
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:299f9facfadba837783fba324cb95e9c33f911369a002c5aea6ec1066633de13
+oid sha256:aa6f40e196c0a4cfc1da1b5367d1fe68039af7328de1829ef9a58cac1a784b5d
 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": 0.9514667391777039,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22271714922049,
+  "best_metric": 0.9468846917152405,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.44543429844098,
   "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": 26.411,
       "eval_steps_per_second": 6.867,
       "step": 25
+    },
+    {
+      "epoch": 0.23162583518930957,
+      "grad_norm": 0.14698415994644165,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5137,
+      "step": 26
+    },
+    {
+      "epoch": 0.24053452115812918,
+      "grad_norm": 0.17574959993362427,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.4575,
+      "step": 27
+    },
+    {
+      "epoch": 0.24944320712694878,
+      "grad_norm": 0.20597203075885773,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5864,
+      "step": 28
+    },
+    {
+      "epoch": 0.2583518930957684,
+      "grad_norm": 0.23045676946640015,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.5454,
+      "step": 29
+    },
+    {
+      "epoch": 0.267260579064588,
+      "grad_norm": 0.24907086789608002,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.6148,
+      "step": 30
+    },
+    {
+      "epoch": 0.27616926503340755,
+      "grad_norm": 0.2596317231655121,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.5663,
+      "step": 31
+    },
+    {
+      "epoch": 0.28507795100222716,
+      "grad_norm": 0.3124055862426758,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.5177,
+      "step": 32
+    },
+    {
+      "epoch": 0.29398663697104677,
+      "grad_norm": 0.2827463448047638,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3123,
+      "step": 33
+    },
+    {
+      "epoch": 0.3028953229398664,
+      "grad_norm": 0.27426767349243164,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2493,
+      "step": 34
+    },
+    {
+      "epoch": 0.311804008908686,
+      "grad_norm": 0.2786475419998169,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.0859,
+      "step": 35
+    },
+    {
+      "epoch": 0.3207126948775056,
+      "grad_norm": 0.3908156156539917,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8041,
+      "step": 36
+    },
+    {
+      "epoch": 0.32962138084632514,
+      "grad_norm": 0.3256056606769562,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.5106,
+      "step": 37
+    },
+    {
+      "epoch": 0.33853006681514475,
+      "grad_norm": 0.17346952855587006,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.4636,
+      "step": 38
+    },
+    {
+      "epoch": 0.34743875278396436,
+      "grad_norm": 0.15939083695411682,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.4421,
+      "step": 39
+    },
+    {
+      "epoch": 0.35634743875278396,
+      "grad_norm": 0.17302539944648743,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.4762,
+      "step": 40
+    },
+    {
+      "epoch": 0.36525612472160357,
+      "grad_norm": 0.180658221244812,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.4226,
+      "step": 41
+    },
+    {
+      "epoch": 0.3741648106904232,
+      "grad_norm": 0.1790269911289215,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.6501,
+      "step": 42
+    },
+    {
+      "epoch": 0.3830734966592428,
+      "grad_norm": 0.18365341424942017,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.4913,
+      "step": 43
+    },
+    {
+      "epoch": 0.39198218262806234,
+      "grad_norm": 0.1884250044822693,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.5275,
+      "step": 44
+    },
+    {
+      "epoch": 0.40089086859688194,
+      "grad_norm": 0.19831326603889465,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.4273,
+      "step": 45
+    },
+    {
+      "epoch": 0.40979955456570155,
+      "grad_norm": 0.2138986438512802,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.3098,
+      "step": 46
+    },
+    {
+      "epoch": 0.41870824053452116,
+      "grad_norm": 0.25467658042907715,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.1632,
+      "step": 47
+    },
+    {
+      "epoch": 0.42761692650334077,
+      "grad_norm": 0.32772597670555115,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.0352,
+      "step": 48
+    },
+    {
+      "epoch": 0.4365256124721604,
+      "grad_norm": 0.4011337459087372,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.6836,
+      "step": 49
+    },
+    {
+      "epoch": 0.44543429844098,
+      "grad_norm": 0.6807431578636169,
+      "learning_rate": 1e-05,
+      "loss": 0.5322,
+      "step": 50
+    },
+    {
+      "epoch": 0.44543429844098,
+      "eval_loss": 0.9468846917152405,
+      "eval_runtime": 1.8575,
+      "eval_samples_per_second": 26.918,
+      "eval_steps_per_second": 6.999,
+      "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": 5.312581507586458e+16,
+  "total_flos": 1.0625163001751142e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null