Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54eaeccfa42366eec3053481adc58c9abe7844142d46ee69ee534db192a6b2d2
+oid sha256:9485abd4a845b953b760780b52bf566eba363cae67aaeb4a1caed36245804b8b
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fde7d245b1af815cdb37087ffa3096c9d00ecee212968f741f25b9891cc6f064
+oid sha256:2e9e95d2545ef83ccc81b272bae7faed2f10eeb24dab86cf75499e1920af3d83
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96bcc9f2208627343efb282c69f858dfa3339a1ca3e40f4ad215b8dc03deb055
+oid sha256:17b6ab54758d6c72638402e84fae2aad65a221b35640878ae19e43b4230eac2d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3febf3425d01f9a8670f76097b63bdde8ab2c4b9db69f7e047b33a3ea4a950e
+oid sha256:af8c70a94900d9b287ae32cb4f95d47fb8ad712363557219eb89e270f8b96010
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0988595485687256,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.24441340782122906,
+  "best_metric": 1.0803192853927612,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.27932960893854747,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 11.356,
       "eval_steps_per_second": 2.844,
       "step": 350
+    },
+    {
+      "epoch": 0.25139664804469275,
+      "grad_norm": 0.40342968702316284,
+      "learning_rate": 4.62847451355716e-05,
+      "loss": 0.846,
+      "step": 360
+    },
+    {
+      "epoch": 0.25837988826815644,
+      "grad_norm": 0.3979036509990692,
+      "learning_rate": 4.035554509080588e-05,
+      "loss": 0.8506,
+      "step": 370
+    },
+    {
+      "epoch": 0.26536312849162014,
+      "grad_norm": 0.46212857961654663,
+      "learning_rate": 3.474128633231992e-05,
+      "loss": 0.769,
+      "step": 380
+    },
+    {
+      "epoch": 0.2723463687150838,
+      "grad_norm": 0.49502870440483093,
+      "learning_rate": 2.946932096444165e-05,
+      "loss": 0.9183,
+      "step": 390
+    },
+    {
+      "epoch": 0.27932960893854747,
+      "grad_norm": 1.1559889316558838,
+      "learning_rate": 2.456533347250732e-05,
+      "loss": 2.3416,
+      "step": 400
+    },
+    {
+      "epoch": 0.27932960893854747,
+      "eval_loss": 1.0803192853927612,
+      "eval_runtime": 51.8492,
+      "eval_samples_per_second": 11.63,
+      "eval_steps_per_second": 2.912,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.882126363131904e+16,
+  "total_flos": 1.1268467831341056e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null