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:c994ed763ffdf01a4ace29018f755540d0176eb8ed228a7cac3e6bac0439a59b
+oid sha256:4a337e774f238d7b3ec7ac5e7b4d8c17a438573785824c6c4f93fa939dbb42ac
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03ca68ebd84761490f58e0f451dc0d547e94878bd68d5cd963bd4dc96f8ed280
+oid sha256:76e6ea45a60028da44f5b5f956012ec79978563b710a89964d3165a82ae053c6
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25d7a045d89bd8ceaab7d1045abc7faefdff2f720a23807664708ea64c4a5995
+oid sha256:df1918c7f88de125ce5246fd3922030589a12d0dd55aa33f9cff99ad5f2953d5
 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": 1.1927704811096191,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.17050298380221654,
+  "best_metric": 1.1823617219924927,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.19892014776925263,
   "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": 35.408,
       "eval_steps_per_second": 8.888,
       "step": 300
+    },
+    {
+      "epoch": 0.17618641659562376,
+      "grad_norm": 0.20985211431980133,
+      "learning_rate": 7.95982009620349e-05,
+      "loss": 1.1342,
+      "step": 310
+    },
+    {
+      "epoch": 0.18186984938903097,
+      "grad_norm": 0.2655479609966278,
+      "learning_rate": 7.255321559063053e-05,
+      "loss": 1.1409,
+      "step": 320
+    },
+    {
+      "epoch": 0.1875532821824382,
+      "grad_norm": 0.41280436515808105,
+      "learning_rate": 6.566630769132923e-05,
+      "loss": 1.1169,
+      "step": 330
+    },
+    {
+      "epoch": 0.1932367149758454,
+      "grad_norm": 0.5316308736801147,
+      "learning_rate": 5.897102958714686e-05,
+      "loss": 1.2024,
+      "step": 340
+    },
+    {
+      "epoch": 0.19892014776925263,
+      "grad_norm": 1.7537466287612915,
+      "learning_rate": 5.250000000000002e-05,
+      "loss": 1.2405,
+      "step": 350
+    },
+    {
+      "epoch": 0.19892014776925263,
+      "eval_loss": 1.1823617219924927,
+      "eval_runtime": 20.6991,
+      "eval_samples_per_second": 35.799,
+      "eval_steps_per_second": 8.986,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4539094960898048e+16,
+  "total_flos": 1.6876104534982656e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null