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:ebbe41e39f49c46555fc32241a2d314e754715ca4574742d83a7f0e5491a84a4
+oid sha256:719f29ee76f559420eb591897ff5f9c634ce02ae11ea78bda0e8155ffb885da2
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c871f9a0585029209edb598fe450bd193f26baa26ab6d1b5652b77c8a17388e4
+oid sha256:80b6a2ca44f804b8750b117ed7a187c1e09a380c456522ba74f2613fda283722
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b18c08412ac1046c7267e2574028c1e7058f6c7d1c15c73c1cf167d5b788ca9c
+oid sha256:a79d8bb6261ae6f0d6a70b8f218e7f74fad160365eb5f04ccbb70e24782bc98c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4724a4322486cf07c6f137f6430836b1a2cb9ae0cd696f1604a47814630e3ba
+oid sha256:6a53e373878af8696de39d4b7adb8634138f0e346e89bffc05bcb76c7b6de169
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9416553974151611,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.02281393605579637,
+  "best_metric": 0.8955165147781372,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.026073069778052994,
   "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": 14.375,
       "eval_steps_per_second": 3.594,
       "step": 350
+    },
+    {
+      "epoch": 0.023465762800247696,
+      "grad_norm": 1.5010788440704346,
+      "learning_rate": 4.5843938039042344e-05,
+      "loss": 0.829,
+      "step": 360
+    },
+    {
+      "epoch": 0.02411758954469902,
+      "grad_norm": 3.3226091861724854,
+      "learning_rate": 3.997120656613154e-05,
+      "loss": 0.9773,
+      "step": 370
+    },
+    {
+      "epoch": 0.024769416289150345,
+      "grad_norm": 1.6384238004684448,
+      "learning_rate": 3.441041693867878e-05,
+      "loss": 0.8725,
+      "step": 380
+    },
+    {
+      "epoch": 0.02542124303360167,
+      "grad_norm": 2.352992534637451,
+      "learning_rate": 2.9188660764780296e-05,
+      "loss": 0.9907,
+      "step": 390
+    },
+    {
+      "epoch": 0.026073069778052994,
+      "grad_norm": 3.1694495677948,
+      "learning_rate": 2.4331377915626298e-05,
+      "loss": 1.2449,
+      "step": 400
+    },
+    {
+      "epoch": 0.026073069778052994,
+      "eval_loss": 0.8955165147781372,
+      "eval_runtime": 446.7108,
+      "eval_samples_per_second": 14.461,
+      "eval_steps_per_second": 3.615,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.28057050646446e+16,
+  "total_flos": 8.303876499308544e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null