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:fdd308c177c7e1b34647a824c371d87db5cb625d5b1f67c7af230f85e2794464
+oid sha256:6d4ed7cc5befbe5542f4b0d160ce8f1babada7425cec7c9a6fb42c5d4a4e902e
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ccec6201ca75eed9c8fa7204e92683881443754e312c90653c1d615d332781b
+oid sha256:a603c11ace18511cb84d5ca6e4b0fd881542b5f1aa95c650ee7b325df67734fd
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca7951baaa2c6cf4f6c90bee00b1e551cdb09d39e7c82313a0976e12094433a
+oid sha256:c0af4b7557845ab179aa5b1a933ab24d7c9dc4c07fb792299422186a11274f63
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c50f4180bfdd0f1fe79b893b92ba018bdf47e8874f9b969d765634068fe31b
+oid sha256:3d06f558f71558f948e454a7e5c9472755db03d1e0a078ea2ecb2f78f4649e69
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c963d068834a096167a8afde3ae9f6c3ceb8126d2d8f18c1d297f3aca37cdd51
+oid sha256:41469298a95ad8befd1dd6cc3536d34b10cd7e4dff8699cb95656ea668f3716c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80708ebc34cd3be021af1eb3ecd21790c8ad80fca7f426741e040b462ac52cb1
+oid sha256:f4806948d3e2e59a0817022e04ee049d80529ef7abee3c31d8015f589357b158
 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": 1.4878519773483276,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22271714922049,
+  "best_metric": 1.4320266246795654,
+  "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": 11.19,
       "eval_steps_per_second": 2.909,
       "step": 25
+    },
+    {
+      "epoch": 0.23162583518930957,
+      "grad_norm": 0.106295645236969,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.4001,
+      "step": 26
+    },
+    {
+      "epoch": 0.24053452115812918,
+      "grad_norm": 0.1709941029548645,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.4012,
+      "step": 27
+    },
+    {
+      "epoch": 0.24944320712694878,
+      "grad_norm": 0.16162072122097015,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.7046,
+      "step": 28
+    },
+    {
+      "epoch": 0.2583518930957684,
+      "grad_norm": 0.19702105224132538,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.5872,
+      "step": 29
+    },
+    {
+      "epoch": 0.267260579064588,
+      "grad_norm": 0.16122843325138092,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.7371,
+      "step": 30
+    },
+    {
+      "epoch": 0.27616926503340755,
+      "grad_norm": 0.16591770946979523,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.7689,
+      "step": 31
+    },
+    {
+      "epoch": 0.28507795100222716,
+      "grad_norm": 0.18897826969623566,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.7202,
+      "step": 32
+    },
+    {
+      "epoch": 0.29398663697104677,
+      "grad_norm": 0.19742853939533234,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.5054,
+      "step": 33
+    },
+    {
+      "epoch": 0.3028953229398664,
+      "grad_norm": 0.23214320838451385,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.5492,
+      "step": 34
+    },
+    {
+      "epoch": 0.311804008908686,
+      "grad_norm": 0.3052574396133423,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.4624,
+      "step": 35
+    },
+    {
+      "epoch": 0.3207126948775056,
+      "grad_norm": 0.4707745909690857,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.3587,
+      "step": 36
+    },
+    {
+      "epoch": 0.32962138084632514,
+      "grad_norm": 0.7316482663154602,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.1474,
+      "step": 37
+    },
+    {
+      "epoch": 0.33853006681514475,
+      "grad_norm": 0.15378858149051666,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.3779,
+      "step": 38
+    },
+    {
+      "epoch": 0.34743875278396436,
+      "grad_norm": 0.11696304380893707,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.3097,
+      "step": 39
+    },
+    {
+      "epoch": 0.35634743875278396,
+      "grad_norm": 0.1411445140838623,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.4874,
+      "step": 40
+    },
+    {
+      "epoch": 0.36525612472160357,
+      "grad_norm": 0.16639839112758636,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.5469,
+      "step": 41
+    },
+    {
+      "epoch": 0.3741648106904232,
+      "grad_norm": 0.1573583036661148,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.7053,
+      "step": 42
+    },
+    {
+      "epoch": 0.3830734966592428,
+      "grad_norm": 0.16417503356933594,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.6204,
+      "step": 43
+    },
+    {
+      "epoch": 0.39198218262806234,
+      "grad_norm": 0.18815577030181885,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.7019,
+      "step": 44
+    },
+    {
+      "epoch": 0.40089086859688194,
+      "grad_norm": 0.19217829406261444,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.6421,
+      "step": 45
+    },
+    {
+      "epoch": 0.40979955456570155,
+      "grad_norm": 0.20727165043354034,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.5612,
+      "step": 46
+    },
+    {
+      "epoch": 0.41870824053452116,
+      "grad_norm": 0.25485751032829285,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4737,
+      "step": 47
+    },
+    {
+      "epoch": 0.42761692650334077,
+      "grad_norm": 0.33714011311531067,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.5148,
+      "step": 48
+    },
+    {
+      "epoch": 0.4365256124721604,
+      "grad_norm": 0.4841104745864868,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.2554,
+      "step": 49
+    },
+    {
+      "epoch": 0.44543429844098,
+      "grad_norm": 1.1299854516983032,
+      "learning_rate": 1e-05,
+      "loss": 1.4161,
+      "step": 50
+    },
+    {
+      "epoch": 0.44543429844098,
+      "eval_loss": 1.4320266246795654,
+      "eval_runtime": 4.4777,
+      "eval_samples_per_second": 11.166,
+      "eval_steps_per_second": 2.903,
+      "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": 2.8199377547401626e+17,
+  "total_flos": 5.6372392263417856e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null