Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8811606896aa094d25de2a20a022375bfbb8afab61c12de530811250cfb417a2
+oid sha256:452b918fd58af590dfecb8a6ef8ae1893936c4047ca760a9d4bf58513fb697f3
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7a391bd085ed1737078abe0d508aa842b8fdbbb6eb153e9e4c6ffc3f510a68
+oid sha256:176f9d20e6c1f120e6ac8440d3126dcaf0f3d11e0d39248481bcfc3e8e97a513
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae4af2ffba970414e4d4b70633318f9d7d5737e98b96ad920ed71aecdaa875d
+oid sha256:32319360bea69a353b8dbd7cd43c82fa8e161e8d12be7d1c2fde2aec99a9b0d7
 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": 0.16593347489833832,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.3806416530723219,
+  "best_metric": 0.1496591418981552,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.43501903208265363,
   "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": 17.026,
       "eval_steps_per_second": 4.257,
       "step": 350
+    },
+    {
+      "epoch": 0.3915171288743883,
+      "grad_norm": 0.5802284479141235,
+      "learning_rate": 4.62847451355716e-05,
+      "loss": 0.1449,
+      "step": 360
+    },
+    {
+      "epoch": 0.4023926046764546,
+      "grad_norm": 2.2887635231018066,
+      "learning_rate": 4.035554509080588e-05,
+      "loss": 0.1412,
+      "step": 370
+    },
+    {
+      "epoch": 0.4132680804785209,
+      "grad_norm": 1.0761778354644775,
+      "learning_rate": 3.474128633231992e-05,
+      "loss": 0.1024,
+      "step": 380
+    },
+    {
+      "epoch": 0.42414355628058725,
+      "grad_norm": 1.304354190826416,
+      "learning_rate": 2.946932096444165e-05,
+      "loss": 0.1266,
+      "step": 390
+    },
+    {
+      "epoch": 0.43501903208265363,
+      "grad_norm": 2.448615789413452,
+      "learning_rate": 2.456533347250732e-05,
+      "loss": 0.1724,
+      "step": 400
+    },
+    {
+      "epoch": 0.43501903208265363,
+      "eval_loss": 0.1496591418981552,
+      "eval_runtime": 22.6015,
+      "eval_samples_per_second": 17.167,
+      "eval_steps_per_second": 4.292,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.30963104120832e+16,
+  "total_flos": 7.207198273830912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null