Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb6be533d55fe58bfb1f6d64518142fb95d0fc7cac74d8077d4a8fa50c66713
+oid sha256:2ed47462082a9c9d564f1245e88381edd4919d1c6d927c0a9baa65067dc20478
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6507ed83ef87d8987ad42416375656be880ce7988be655a14da29b22647bf548
+oid sha256:8dce2a7c169df44a13155ff92b8c8df0dda9517731e76a254bee2e59ac6ae653
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14a64bfd9176d14f55dcad0bac9819c374a7752a2140799833008b9c3afa7a34
+oid sha256:c9e51a2209d1739c364384d0bc4e94871f9dbec8f5f6e8abed3de2c7bf755ea5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1425969cd8e5d9456eff9b286f7f5cbcd4119e2e34178d957af8f58c73bf1eea
+oid sha256:70f9eefb79e5a651e4979588997923d1fc997984394f03e9fb61aca38c6bee05
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.008491799235343933,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.020226537216828478,
+  "best_metric": 0.005722765810787678,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.040453074433656956,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 18.025,
       "eval_steps_per_second": 4.523,
       "step": 50
+    },
+    {
+      "epoch": 0.024271844660194174,
+      "grad_norm": 0.9959584474563599,
+      "learning_rate": 7.855555555555556e-06,
+      "loss": 0.0005,
+      "step": 60
+    },
+    {
+      "epoch": 0.02831715210355987,
+      "grad_norm": 0.14248639345169067,
+      "learning_rate": 7.294444444444444e-06,
+      "loss": 0.0035,
+      "step": 70
+    },
+    {
+      "epoch": 0.032362459546925564,
+      "grad_norm": 0.0067140571773052216,
+      "learning_rate": 6.733333333333333e-06,
+      "loss": 0.001,
+      "step": 80
+    },
+    {
+      "epoch": 0.03640776699029126,
+      "grad_norm": 0.009364698082208633,
+      "learning_rate": 6.172222222222223e-06,
+      "loss": 0.0003,
+      "step": 90
+    },
+    {
+      "epoch": 0.040453074433656956,
+      "grad_norm": 0.013642555102705956,
+      "learning_rate": 5.611111111111111e-06,
+      "loss": 0.0023,
+      "step": 100
+    },
+    {
+      "epoch": 0.040453074433656956,
+      "eval_loss": 0.005722765810787678,
+      "eval_runtime": 43.3568,
+      "eval_samples_per_second": 18.013,
+      "eval_steps_per_second": 4.521,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4425161096757248e+16,
+  "total_flos": 2.856747589749965e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null