Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5913556d423b9b4bddbae635045e1577865cfe90ae4bd4383775c30fed1de431
+oid sha256:374f7d3f96c037724c7c5329e4eab3a809b4fdbbb9095b031b1a7c497a5e92f9
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61943b5c8fa512a3e998c0c3a654991deeffaa8cee87eade4d977dbd93885536
+oid sha256:9497d4d04ddb7e9089cba9b807d767b815dd343704a171700e5ad9f79830ed9a
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bc572fa878f5e53027d72133d5a005349c43eaf762cabf369a01657ae2f2caf
+oid sha256:36f9d4df5fa80b8af0ae9e036c834f318a3d9c628c3b781762ee3d1f9db0527c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152cf5e1f9adf3dc2c608dbb3e394e09940ab42688cdb5a07d89f1cccb7f89a5
+oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6046526432037354,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0429553264604811,
+  "best_metric": 1.560912847518921,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.0859106529209622,
   "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": 12.572,
       "eval_steps_per_second": 3.156,
       "step": 50
+    },
+    {
+      "epoch": 0.05154639175257732,
+      "grad_norm": 0.4915436804294586,
+      "learning_rate": 6.992307692307692e-06,
+      "loss": 1.5171,
+      "step": 60
+    },
+    {
+      "epoch": 0.06013745704467354,
+      "grad_norm": 0.4138346016407013,
+      "learning_rate": 6.215384615384615e-06,
+      "loss": 1.5871,
+      "step": 70
+    },
+    {
+      "epoch": 0.06872852233676977,
+      "grad_norm": 0.5473077297210693,
+      "learning_rate": 5.438461538461538e-06,
+      "loss": 1.557,
+      "step": 80
+    },
+    {
+      "epoch": 0.07731958762886598,
+      "grad_norm": 0.7715198397636414,
+      "learning_rate": 4.661538461538462e-06,
+      "loss": 1.5657,
+      "step": 90
+    },
+    {
+      "epoch": 0.0859106529209622,
+      "grad_norm": 1.106988787651062,
+      "learning_rate": 3.884615384615385e-06,
+      "loss": 1.6544,
+      "step": 100
+    },
+    {
+      "epoch": 0.0859106529209622,
+      "eval_loss": 1.560912847518921,
+      "eval_runtime": 38.5363,
+      "eval_samples_per_second": 12.715,
+      "eval_steps_per_second": 3.192,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.52331425792e+16,
+  "total_flos": 4.9793401356288e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null