Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296d00ccd9fa2379e606fbcf47ea671c9e254e894cb91f620883e46fadfc2308
+oid sha256:8c8f50fe2b965692fba8740a59d3a2eddd958e7a3d88ea53809b797387d80737
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02172c4c304859925ea28e00c06a0258921089ea6d053d68aaed42d52abf6315
+oid sha256:9b0fc074cab8930b3f92a6ca2e41c4d035e22d1ca202f609559f7db9fd016b2a
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa2fb06a85811b339dd731794396486199bd99dc3c57345fa4dec2b0c46f1a40
+oid sha256:d8f67d3ffa63a9325a4e54e3858fd9c5305f595b9016fa36f8838ba1575de998
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
+oid sha256:c41568ec8d15c28a2145796b65c5977bed142a18699c02f8db4b41d7a5440c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.04743492603302,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.014166981488477521,
+  "best_metric": 1.0043987035751343,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.018889308651303362,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 17.386,
       "eval_steps_per_second": 4.349,
       "step": 150
+    },
+    {
+      "epoch": 0.01511144692104269,
+      "grad_norm": 0.7381725907325745,
+      "learning_rate": 0.00018740803823691298,
+      "loss": 1.0541,
+      "step": 160
+    },
+    {
+      "epoch": 0.016055912353607857,
+      "grad_norm": 0.8298458456993103,
+      "learning_rate": 0.00018193523609311556,
+      "loss": 0.9556,
+      "step": 170
+    },
+    {
+      "epoch": 0.017000377786173027,
+      "grad_norm": 1.0353724956512451,
+      "learning_rate": 0.00017610710081049675,
+      "loss": 0.877,
+      "step": 180
+    },
+    {
+      "epoch": 0.017944843218738193,
+      "grad_norm": 1.3693569898605347,
+      "learning_rate": 0.00016995202647831142,
+      "loss": 0.9031,
+      "step": 190
+    },
+    {
+      "epoch": 0.018889308651303362,
+      "grad_norm": 1.9539626836776733,
+      "learning_rate": 0.00016350000000000002,
+      "loss": 0.878,
+      "step": 200
+    },
+    {
+      "epoch": 0.018889308651303362,
+      "eval_loss": 1.0043987035751343,
+      "eval_runtime": 256.9248,
+      "eval_samples_per_second": 17.351,
+      "eval_steps_per_second": 4.34,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5317253054464e+16,
+  "total_flos": 3.3728300580864e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null