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:b04965e8750ec878d8a86cf7bd9fbc8839190418e3291eb47ce727d371fc48ff
+oid sha256:86842072a86c1fbfe24bb2e711e1666d8d3323731b0a6b71e64e1b2cbbaf52ed
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9f5894e17e57d55f1fe4f9bb840675e788a469aff620a42bdd69239cce321fb
+oid sha256:532da984f6568a047876364cd8a190012d03c61d1b67c32346b02636eb944b11
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:817e28a7323eeff0931278655530d1bb814a42987c579e90a94eb3bf234b89ec
+oid sha256:8b47a025ca265ce7c3bef466cc3aa9a5f0953f8b9621fcbdbd0af52bd3a48206
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aefa5c0989fb1076f44dee5ec81119730caab480902e567590e4c3defecd81d
+oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8866726160049438,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.03305629013978088,
+  "best_metric": 0.8729479908943176,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.037778617302606725,
   "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": 17.344,
       "eval_steps_per_second": 4.338,
       "step": 350
+    },
+    {
+      "epoch": 0.03400075557234605,
+      "grad_norm": 0.9228352308273315,
+      "learning_rate": 4.804797352168861e-05,
+      "loss": 0.9052,
+      "step": 360
+    },
+    {
+      "epoch": 0.03494522100491122,
+      "grad_norm": 0.7789422273635864,
+      "learning_rate": 4.189289918950325e-05,
+      "loss": 0.9935,
+      "step": 370
+    },
+    {
+      "epoch": 0.035889686437476385,
+      "grad_norm": 1.0351366996765137,
+      "learning_rate": 3.606476390688449e-05,
+      "loss": 0.9121,
+      "step": 380
+    },
+    {
+      "epoch": 0.036834151870041555,
+      "grad_norm": 0.9583853483200073,
+      "learning_rate": 3.0591961763087043e-05,
+      "loss": 0.8531,
+      "step": 390
+    },
+    {
+      "epoch": 0.037778617302606725,
+      "grad_norm": 1.4442740678787231,
+      "learning_rate": 2.550115570003141e-05,
+      "loss": 0.7264,
+      "step": 400
+    },
+    {
+      "epoch": 0.037778617302606725,
+      "eval_loss": 0.8729479908943176,
+      "eval_runtime": 256.8229,
+      "eval_samples_per_second": 17.358,
+      "eval_steps_per_second": 4.342,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.8961443160064e+16,
+  "total_flos": 6.7372490686464e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null