Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7c2e20a926129d29a08acb7bc3ad7473fcdef597915c6d28d89bedc694a6ec
+oid sha256:8811606896aa094d25de2a20a022375bfbb8afab61c12de530811250cfb417a2
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f993ff850d525263c9ec68a03eb27bf7ab20b42446876d807fbb312674ae280b
+oid sha256:8e7a391bd085ed1737078abe0d508aa842b8fdbbb6eb153e9e4c6ffc3f510a68
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:256f6f2952f913c7f60ec5567b86f4d6fc189f83109a141672b19e11afb733ca
+oid sha256:9ae4af2ffba970414e4d4b70633318f9d7d5737e98b96ad920ed71aecdaa875d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09bf653dc25e0c029a8db4ba507ae3589e41445bb2b0fcc38f99c09150129f49
+oid sha256:b3febf3425d01f9a8670f76097b63bdde8ab2c4b9db69f7e047b33a3ea4a950e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.22318749129772186,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.3262642740619902,
+  "best_metric": 0.16593347489833832,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.3806416530723219,
   "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": 16.995,
       "eval_steps_per_second": 4.249,
       "step": 300
+    },
+    {
+      "epoch": 0.33713974986405654,
+      "grad_norm": 0.3159692585468292,
+      "learning_rate": 7.95982009620349e-05,
+      "loss": 0.1784,
+      "step": 310
+    },
+    {
+      "epoch": 0.3480152256661229,
+      "grad_norm": 0.8129618763923645,
+      "learning_rate": 7.255321559063053e-05,
+      "loss": 0.1069,
+      "step": 320
+    },
+    {
+      "epoch": 0.35889070146818924,
+      "grad_norm": 1.2382850646972656,
+      "learning_rate": 6.566630769132923e-05,
+      "loss": 0.13,
+      "step": 330
+    },
+    {
+      "epoch": 0.36976617727025557,
+      "grad_norm": 2.3374767303466797,
+      "learning_rate": 5.897102958714686e-05,
+      "loss": 0.2035,
+      "step": 340
+    },
+    {
+      "epoch": 0.3806416530723219,
+      "grad_norm": 2.183784008026123,
+      "learning_rate": 5.250000000000002e-05,
+      "loss": 0.2272,
+      "step": 350
+    },
+    {
+      "epoch": 0.3806416530723219,
+      "eval_loss": 0.16593347489833832,
+      "eval_runtime": 22.788,
+      "eval_samples_per_second": 17.026,
+      "eval_steps_per_second": 4.257,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.412063808585728e+16,
+  "total_flos": 6.30963104120832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null