Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:545bd46ce6ae0252cac56e413922b70150c1e037ca499a2a25b574a4e36c64e0
+oid sha256:d7f6b35a15bbc586d486edb3e9dbccaf970941ed7cb752aad9925c9529f2c6d8
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6e185a7c6de810efda09c831684a466f8ae3f07f6f9f3c8d880eba921fcce2
+oid sha256:dadc8b499392fc88cc7987b2d57354e8053bcc9c4c5790c958325acf153a8265
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c470e229d232210edbc871f3fa0f9e6e064cb8869be419bd4e9dd985a271955d
+oid sha256:b024ad065d96944204d5b2a3ffba39d2b87a1e829f5b00d95dab5a621815a684
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.7246010303497314,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005164622336991607,
+  "best_metric": 1.5286188125610352,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.010329244673983214,
   "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": 13.942,
       "eval_steps_per_second": 6.971,
       "step": 10
+    },
+    {
+      "epoch": 0.006197546804389929,
+      "grad_norm": 2.797802448272705,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.6598,
+      "step": 12
+    },
+    {
+      "epoch": 0.007746933505487412,
+      "grad_norm": 4.242660999298096,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.3718,
+      "step": 15
+    },
+    {
+      "epoch": 0.007746933505487412,
+      "eval_loss": 1.5960263013839722,
+      "eval_runtime": 58.594,
+      "eval_samples_per_second": 13.926,
+      "eval_steps_per_second": 6.963,
+      "step": 15
+    },
+    {
+      "epoch": 0.009296320206584894,
+      "grad_norm": 5.3486151695251465,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.5097,
+      "step": 18
+    },
+    {
+      "epoch": 0.010329244673983214,
+      "eval_loss": 1.5286188125610352,
+      "eval_runtime": 58.629,
+      "eval_samples_per_second": 13.918,
+      "eval_steps_per_second": 6.959,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 705278609719296.0,
+  "total_flos": 1350533507973120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null