Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e47bb561a5feb7bcf864c61e2c66c357882bbe63ac7161d08cf966801d2139b
+oid sha256:b04965e8750ec878d8a86cf7bd9fbc8839190418e3291eb47ce727d371fc48ff
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5ec0fdbb629efacaf51b19eba3e8b6fa5fcc9c77d6c9ac859163dbef4b8cfee
+oid sha256:f9f5894e17e57d55f1fe4f9bb840675e788a469aff620a42bdd69239cce321fb
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3a794838ad98cb24e90db23231e689208506f9fde5fabc681bc616ecb6cb47
+oid sha256:817e28a7323eeff0931278655530d1bb814a42987c579e90a94eb3bf234b89ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3407292f65425c0593f095883f5f3c050baccb28fc15b3c1ad88090d6c23ef
+oid sha256:9aefa5c0989fb1076f44dee5ec81119730caab480902e567590e4c3defecd81d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9112545847892761,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.028333962976955042,
+  "best_metric": 0.8866726160049438,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.03305629013978088,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 17.362,
       "eval_steps_per_second": 4.343,
       "step": 300
+    },
+    {
+      "epoch": 0.02927842840952021,
+      "grad_norm": 0.5989169478416443,
+      "learning_rate": 8.263051337963623e-05,
+      "loss": 1.007,
+      "step": 310
+    },
+    {
+      "epoch": 0.03022289384208538,
+      "grad_norm": 0.7678573131561279,
+      "learning_rate": 7.531714761313074e-05,
+      "loss": 0.9324,
+      "step": 320
+    },
+    {
+      "epoch": 0.031167359274650547,
+      "grad_norm": 0.8592800498008728,
+      "learning_rate": 6.816788131766559e-05,
+      "loss": 0.8615,
+      "step": 330
+    },
+    {
+      "epoch": 0.032111824707215714,
+      "grad_norm": 1.0715807676315308,
+      "learning_rate": 6.121754499999055e-05,
+      "loss": 0.8406,
+      "step": 340
+    },
+    {
+      "epoch": 0.03305629013978088,
+      "grad_norm": 2.368269205093384,
+      "learning_rate": 5.450000000000003e-05,
+      "loss": 0.6401,
+      "step": 350
+    },
+    {
+      "epoch": 0.03305629013978088,
+      "eval_loss": 0.8866726160049438,
+      "eval_runtime": 257.0405,
+      "eval_samples_per_second": 17.344,
+      "eval_steps_per_second": 4.338,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.0550395633664e+16,
+  "total_flos": 5.8961443160064e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null