Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38649563c311852d5cd9ca5b56d84b84ce243ec72f3a8ddad2405094c17b5b52
+oid sha256:f67120401588fe1ceea73be1fae6b43c99c1fba465ed210554919b98f947e953
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e20c655af3439125ffdfcf924c0e6a3bde373dfd60a7ddf1dde92b399b4c9525
+oid sha256:bde6200fdfc8e3f56b8f4936b753c6810636c2bd42940a7ff8cb6a59bbc543e2
 size 100824826

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3b4b51333ad0eca420eb23a39071d07dc0c4e94778b5d5462e00f1ce3f0b7c
+oid sha256:c148ca972f2aaf7a34547844672cf27a17c69763eb813e497a939cdd68bdd555
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:830c8a7b1c632a75a92d015b81635cf1d210e8b64c7217421b7792c741cd1c9b
+oid sha256:7b1ca61c5a56bdf1168afa1c604ac5dddd78278ae5e898470a9b64fce0e27685
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5510b21bcf747fe3ef0f9a9c367f9ff50881f94b79b0bb9b5ff8f6a3891f25
+oid sha256:de0316b52649de3e038979772b4ffa1bc5bc8ff8b1c5cf8011e3e4f03076ce7e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ffa4f8d2a2e70dcc2cd824bb908e851252f28a0ebd6b79d34717348830303bc
+oid sha256:a331c2e1a31ffe0b180ad9b40136020e550b7ec3f42ba7d543db0d85a8302875
 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": 1.4233994483947754,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22271714922049,
+  "best_metric": 1.3863598108291626,
+  "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": 38.639,
       "eval_steps_per_second": 10.046,
       "step": 25
+    },
+    {
+      "epoch": 0.23162583518930957,
+      "grad_norm": 33.941383361816406,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 52.7992,
+      "step": 26
+    },
+    {
+      "epoch": 0.24053452115812918,
+      "grad_norm": 40.879173278808594,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 49.1806,
+      "step": 27
+    },
+    {
+      "epoch": 0.24944320712694878,
+      "grad_norm": 32.683921813964844,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 52.5922,
+      "step": 28
+    },
+    {
+      "epoch": 0.2583518930957684,
+      "grad_norm": 21.145339965820312,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 51.5849,
+      "step": 29
+    },
+    {
+      "epoch": 0.267260579064588,
+      "grad_norm": 15.121529579162598,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 59.9594,
+      "step": 30
+    },
+    {
+      "epoch": 0.27616926503340755,
+      "grad_norm": 19.04533576965332,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 62.9299,
+      "step": 31
+    },
+    {
+      "epoch": 0.28507795100222716,
+      "grad_norm": 24.32951545715332,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 59.8828,
+      "step": 32
+    },
+    {
+      "epoch": 0.29398663697104677,
+      "grad_norm": 25.904399871826172,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 58.6128,
+      "step": 33
+    },
+    {
+      "epoch": 0.3028953229398664,
+      "grad_norm": 22.204713821411133,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 57.3137,
+      "step": 34
+    },
+    {
+      "epoch": 0.311804008908686,
+      "grad_norm": 18.657562255859375,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 51.4032,
+      "step": 35
+    },
+    {
+      "epoch": 0.3207126948775056,
+      "grad_norm": 22.999425888061523,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 37.3169,
+      "step": 36
+    },
+    {
+      "epoch": 0.32962138084632514,
+      "grad_norm": 20.26948356628418,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 26.2206,
+      "step": 37
+    },
+    {
+      "epoch": 0.33853006681514475,
+      "grad_norm": 28.839693069458008,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 36.0885,
+      "step": 38
+    },
+    {
+      "epoch": 0.34743875278396436,
+      "grad_norm": 13.177519798278809,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 48.8262,
+      "step": 39
+    },
+    {
+      "epoch": 0.35634743875278396,
+      "grad_norm": 11.345005989074707,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 44.1522,
+      "step": 40
+    },
+    {
+      "epoch": 0.36525612472160357,
+      "grad_norm": 11.286595344543457,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 50.7088,
+      "step": 41
+    },
+    {
+      "epoch": 0.3741648106904232,
+      "grad_norm": 11.777042388916016,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 58.1622,
+      "step": 42
+    },
+    {
+      "epoch": 0.3830734966592428,
+      "grad_norm": 12.77750301361084,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 57.6741,
+      "step": 43
+    },
+    {
+      "epoch": 0.39198218262806234,
+      "grad_norm": 11.639248847961426,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 61.6269,
+      "step": 44
+    },
+    {
+      "epoch": 0.40089086859688194,
+      "grad_norm": 11.823376655578613,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 59.2622,
+      "step": 45
+    },
+    {
+      "epoch": 0.40979955456570155,
+      "grad_norm": 12.545153617858887,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 55.0974,
+      "step": 46
+    },
+    {
+      "epoch": 0.41870824053452116,
+      "grad_norm": 14.012038230895996,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 54.5045,
+      "step": 47
+    },
+    {
+      "epoch": 0.42761692650334077,
+      "grad_norm": 16.74378204345703,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 49.9349,
+      "step": 48
+    },
+    {
+      "epoch": 0.4365256124721604,
+      "grad_norm": 19.43877410888672,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 33.3399,
+      "step": 49
+    },
+    {
+      "epoch": 0.44543429844098,
+      "grad_norm": 41.29233932495117,
+      "learning_rate": 1e-05,
+      "loss": 26.2172,
+      "step": 50
+    },
+    {
+      "epoch": 0.44543429844098,
+      "eval_loss": 1.3863598108291626,
+      "eval_runtime": 1.287,
+      "eval_samples_per_second": 38.851,
+      "eval_steps_per_second": 10.101,
+      "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": 1.2413185227227136e+16,
+  "total_flos": 2.4818631527366656e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null