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:ca17d9fecc408f0d35e417f66929c8b9fa7f153c8cf499ca247598a88011e46a
+oid sha256:8c61caf51db4aff0abb808e749af8ea87ee73b3c32b8ff20dd29dbaba11dfe6a
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145f70f53894f64402c6dba6ebd4ab7ba12809667d8fcc353895527c99d825c8
+oid sha256:e5c15cdd77fc7b4715f4d994facc38118d7168cdd80b1eeb6591854bcb078bfc
 size 102864868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:995e50b4ee2fbf19669e7dc094838704b938f2d6f250049b09fbbd77a9c9c9c9
+oid sha256:feb50f0ffa24c4c0124c4275aa89acc1038fe1a8a5ba7cba25b0854ab8d8ad8e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1123dd497c9b8910fe9a2e80a4ab323c0694a06c711a817decbfc0ad393e20a4
+oid sha256:913ab8b0d366eeaae4f2a144c807ce2c591297e394af2372dd426dd4c3850119
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.057299852371216,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.024707917122586565,
+  "best_metric": 2.037623643875122,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.028237619568670363,
   "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": 54.484,
       "eval_steps_per_second": 13.628,
       "step": 350
+    },
+    {
+      "epoch": 0.025413857611803325,
+      "grad_norm": 0.9228034615516663,
+      "learning_rate": 4.5623534490777714e-05,
+      "loss": 2.1183,
+      "step": 360
+    },
+    {
+      "epoch": 0.026119798101020084,
+      "grad_norm": 0.9374071955680847,
+      "learning_rate": 3.9779037303794365e-05,
+      "loss": 2.0988,
+      "step": 370
+    },
+    {
+      "epoch": 0.026825738590236844,
+      "grad_norm": 1.051098108291626,
+      "learning_rate": 3.42449822418582e-05,
+      "loss": 1.9813,
+      "step": 380
+    },
+    {
+      "epoch": 0.027531679079453603,
+      "grad_norm": 1.083287000656128,
+      "learning_rate": 2.9048330664949622e-05,
+      "loss": 2.1039,
+      "step": 390
+    },
+    {
+      "epoch": 0.028237619568670363,
+      "grad_norm": 1.2849839925765991,
+      "learning_rate": 2.4214400137185785e-05,
+      "loss": 1.9843,
+      "step": 400
+    },
+    {
+      "epoch": 0.028237619568670363,
+      "eval_loss": 2.037623643875122,
+      "eval_runtime": 107.9784,
+      "eval_samples_per_second": 55.243,
+      "eval_steps_per_second": 13.818,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9719154902827008.0,
+  "total_flos": 1.1105701006934016e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null