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:ff078530ab150c40b61897c54f17db650404243aab9890a5e190d19a1f289110
+oid sha256:1631ec2a135b47e5ba605c376c59bad2167458fac75bc1131581b86299b5991b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab64cffb0b6ad24da69f45dc185b59e1a1ede4c3fc8e6e40b0753cbe26d355c
+oid sha256:d8ca3bacca827f5092d589c3fc2f77a0f84a606cee6d3727ee737d3445bcce78
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565c117b0554bcadbb2962d5778f478da838b047d26cc08e6b3663c916f71fed
+oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.227739691734314,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.006278449223041909,
+  "best_metric": 0.40428486466407776,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.012556898446083818,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 5.256,
       "eval_steps_per_second": 2.632,
       "step": 10
+    },
+    {
+      "epoch": 0.006906294145346099,
+      "grad_norm": 4.8174285888671875,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.5564,
+      "step": 11
+    },
+    {
+      "epoch": 0.00753413906765029,
+      "grad_norm": 6.006891250610352,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.5441,
+      "step": 12
+    },
+    {
+      "epoch": 0.00816198398995448,
+      "grad_norm": 5.428179740905762,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 3.6617,
+      "step": 13
+    },
+    {
+      "epoch": 0.008789828912258673,
+      "grad_norm": 7.354944229125977,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.2464,
+      "step": 14
+    },
+    {
+      "epoch": 0.009417673834562863,
+      "grad_norm": 4.133303642272949,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.8796,
+      "step": 15
+    },
+    {
+      "epoch": 0.009417673834562863,
+      "eval_loss": 0.51548171043396,
+      "eval_runtime": 127.4469,
+      "eval_samples_per_second": 5.265,
+      "eval_steps_per_second": 2.636,
+      "step": 15
+    },
+    {
+      "epoch": 0.010045518756867053,
+      "grad_norm": 5.053266525268555,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.2643,
+      "step": 16
+    },
+    {
+      "epoch": 0.010673363679171245,
+      "grad_norm": 6.078112602233887,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.8569,
+      "step": 17
+    },
+    {
+      "epoch": 0.011301208601475436,
+      "grad_norm": 3.603733539581299,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.3892,
+      "step": 18
+    },
+    {
+      "epoch": 0.011929053523779626,
+      "grad_norm": 5.492099761962891,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.8328,
+      "step": 19
+    },
+    {
+      "epoch": 0.012556898446083818,
+      "grad_norm": 4.075289249420166,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.5149,
+      "step": 20
+    },
+    {
+      "epoch": 0.012556898446083818,
+      "eval_loss": 0.40428486466407776,
+      "eval_runtime": 128.1933,
+      "eval_samples_per_second": 5.234,
+      "eval_steps_per_second": 2.621,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3166224305356800.0,
+  "total_flos": 6332448610713600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null