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:b29a4ae849e2a861f244425f7da29da37bb6ee3939dc516f27ea2fc21620b0a6
+oid sha256:ad7c8da8f869e90bb6529bf734b6265d18e2532c4520ce34a20e94c828ace670
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5dc8c2ecb9060e1f77d30276491d798a46fe12596cd6c1d588449dee39ef9d7
+oid sha256:0f744d33f60c81fcec6846e333b71636ca5a1246ae19f920fc5d5493ebf229da
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35dcf07fe09b44ecdeb939341e4c74d2062874130d18a98dd15ef7552d0e61e4
+oid sha256:c34eaffeb97d16d7d5fc3f58d34117373e21f932c97684c4f93e8476b32271d1
 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": 0.11864767968654633,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.19042437431991294,
+  "best_metric": 0.1065056249499321,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.2176278563656148,
   "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": 5.927,
       "eval_steps_per_second": 1.486,
       "step": 350
+    },
+    {
+      "epoch": 0.19586507072905332,
+      "grad_norm": 0.27000942826271057,
+      "learning_rate": 4.62847451355716e-05,
+      "loss": 0.1948,
+      "step": 360
+    },
+    {
+      "epoch": 0.20130576713819368,
+      "grad_norm": 0.3730561435222626,
+      "learning_rate": 4.035554509080588e-05,
+      "loss": 0.1986,
+      "step": 370
+    },
+    {
+      "epoch": 0.20674646354733406,
+      "grad_norm": 0.4994836151599884,
+      "learning_rate": 3.474128633231992e-05,
+      "loss": 0.2262,
+      "step": 380
+    },
+    {
+      "epoch": 0.21218715995647444,
+      "grad_norm": 0.7578539848327637,
+      "learning_rate": 2.946932096444165e-05,
+      "loss": 0.3025,
+      "step": 390
+    },
+    {
+      "epoch": 0.2176278563656148,
+      "grad_norm": 1.3834261894226074,
+      "learning_rate": 2.456533347250732e-05,
+      "loss": 0.5652,
+      "step": 400
+    },
+    {
+      "epoch": 0.2176278563656148,
+      "eval_loss": 0.1065056249499321,
+      "eval_runtime": 65.2426,
+      "eval_samples_per_second": 5.932,
+      "eval_steps_per_second": 1.487,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.426722828058624e+16,
+  "total_flos": 1.0473242014777344e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null