Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41bd78f15fc76044e95ffbbb382cdf0923b9eeeb5fbbfa4b4c2b2fb94d9432e4
+oid sha256:e37405de8391ef7687baf9d7901cb51843117399ea1d9d259aa61ebf90223d51
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494505ece73f7744f083bdf21ac62d9245e95f6b8cb66b0ef1b48df4731e5997
+oid sha256:e2c086033575fb443c2ffedcfbc78e34ddd715147bd8980645463444933d4f32
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96bf91d104877e5fc94a4a35757e3a5a493eba768ea28e07e8d2173129bd99f
+oid sha256:dc3e6b3c3225c0d18610ff0681c760c9a53bdc6330a7fa4105d2b548f0d683b5
 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": 1.6017259359359741,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.024524831391784182,
+  "best_metric": 1.330055594444275,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.049049662783568364,
   "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": 2.982,
       "eval_steps_per_second": 1.491,
       "step": 10
+    },
+    {
+      "epoch": 0.0269773145309626,
+      "grad_norm": 1.1864739656448364,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.6257,
+      "step": 11
+    },
+    {
+      "epoch": 0.029429797670141016,
+      "grad_norm": 1.2734822034835815,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.3936,
+      "step": 12
+    },
+    {
+      "epoch": 0.03188228080931944,
+      "grad_norm": 1.3825111389160156,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.5453,
+      "step": 13
+    },
+    {
+      "epoch": 0.034334763948497854,
+      "grad_norm": 1.420120358467102,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.3915,
+      "step": 14
+    },
+    {
+      "epoch": 0.03678724708767627,
+      "grad_norm": 1.3357456922531128,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.3022,
+      "step": 15
+    },
+    {
+      "epoch": 0.03678724708767627,
+      "eval_loss": 1.3924585580825806,
+      "eval_runtime": 54.1859,
+      "eval_samples_per_second": 3.174,
+      "eval_steps_per_second": 1.587,
+      "step": 15
+    },
+    {
+      "epoch": 0.03923973022685469,
+      "grad_norm": 1.8347684144973755,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.4377,
+      "step": 16
+    },
+    {
+      "epoch": 0.041692213366033105,
+      "grad_norm": 1.6689603328704834,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.3391,
+      "step": 17
+    },
+    {
+      "epoch": 0.04414469650521153,
+      "grad_norm": 1.8359532356262207,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.4132,
+      "step": 18
+    },
+    {
+      "epoch": 0.04659717964438995,
+      "grad_norm": 1.6253583431243896,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.0545,
+      "step": 19
+    },
+    {
+      "epoch": 0.049049662783568364,
+      "grad_norm": 1.4194138050079346,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.098,
+      "step": 20
+    },
+    {
+      "epoch": 0.049049662783568364,
+      "eval_loss": 1.330055594444275,
+      "eval_runtime": 55.0506,
+      "eval_samples_per_second": 3.124,
+      "eval_steps_per_second": 1.562,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3135311286632448.0,
+  "total_flos": 6352059230060544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null