Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df8ee5083919cfb0f248f93911511b6ba371d77be54235c91d8fb343d109906
+oid sha256:8cc7f5790b0fa9183b6486230120f460d96f2bca188d19757eb0309fc8581890
 size 209760536

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2052e39991a3a421b452d1ce344e1c15b052cfe72295d85786f9d9dd135720f6
+oid sha256:3d9d874bf75b0fbe25d863262a3f19d44ebd67435bb4dba45d3467360724b7aa
 size 419700154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7cd68ab6874817b2f942b648b5fe377777bbd2943f16069450a746d45f3977d
+oid sha256:e9e11466f82218754490b95bb449a80bce8218c54ffd359611bec3539d895142
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3997441530227661,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0936768149882904,
+  "best_metric": 1.214084267616272,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.1873536299765808,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 2.828,
       "eval_steps_per_second": 1.445,
       "step": 10
+    },
+    {
+      "epoch": 0.11241217798594848,
+      "grad_norm": 2.0864598751068115,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 5.2922,
+      "step": 12
+    },
+    {
+      "epoch": 0.1405152224824356,
+      "grad_norm": 2.491011619567871,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.0416,
+      "step": 15
+    },
+    {
+      "epoch": 0.1405152224824356,
+      "eval_loss": 1.2667834758758545,
+      "eval_runtime": 15.8816,
+      "eval_samples_per_second": 2.833,
+      "eval_steps_per_second": 1.448,
+      "step": 15
+    },
+    {
+      "epoch": 0.1686182669789227,
+      "grad_norm": 2.8564693927764893,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 4.7651,
+      "step": 18
+    },
+    {
+      "epoch": 0.1873536299765808,
+      "eval_loss": 1.214084267616272,
+      "eval_runtime": 15.8452,
+      "eval_samples_per_second": 2.84,
+      "eval_steps_per_second": 1.452,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.25750703292416e+16,
+  "total_flos": 2.51501406584832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null