Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020b57a6810aa9ef9503fb1fb906173bfac12542a6d1ee85a1917b4ba7bf1dc4
+oid sha256:19abd315ba6325d3c69b88a3523bb893fbeae7c9f11cf8e8a532a7568424f786
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daae98f08aabfbf39c38c8c1e10788eebe632f6cddcc53af1f68fa343a7e4e94
+oid sha256:18677bb0c402f4eda66d46ad6d9c4a85fa0a1b070c5b88fc2fa36935f4de1987
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11871e7c5b50a0f38caedab28b7a1fb5fc525ab1b378b4cbbb14489bbe44d75c
+oid sha256:905784641e6ebfaee544262c51ccc7825688f2bd1c5d6d6a9e62061183b37db7
 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": 1.2037712335586548,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0017139429257005741,
+  "best_metric": 1.1016162633895874,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0034278858514011482,
   "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": 5.637,
       "eval_steps_per_second": 2.819,
       "step": 10
+    },
+    {
+      "epoch": 0.0018853372182706316,
+      "grad_norm": 1.1513092517852783,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.9643,
+      "step": 11
+    },
+    {
+      "epoch": 0.002056731510840689,
+      "grad_norm": 1.0634475946426392,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.6718,
+      "step": 12
+    },
+    {
+      "epoch": 0.0022281258034107464,
+      "grad_norm": 1.3111153841018677,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.5046,
+      "step": 13
+    },
+    {
+      "epoch": 0.0023995200959808036,
+      "grad_norm": 0.991614043712616,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.0563,
+      "step": 14
+    },
+    {
+      "epoch": 0.0025709143885508613,
+      "grad_norm": 1.1510419845581055,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.2992,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025709143885508613,
+      "eval_loss": 1.1422899961471558,
+      "eval_runtime": 436.8758,
+      "eval_samples_per_second": 5.624,
+      "eval_steps_per_second": 2.813,
+      "step": 15
+    },
+    {
+      "epoch": 0.0027423086811209185,
+      "grad_norm": 1.321584701538086,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.4959,
+      "step": 16
+    },
+    {
+      "epoch": 0.002913702973690976,
+      "grad_norm": 1.3295321464538574,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.4349,
+      "step": 17
+    },
+    {
+      "epoch": 0.0030850972662610334,
+      "grad_norm": 1.6836707592010498,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.4752,
+      "step": 18
+    },
+    {
+      "epoch": 0.003256491558831091,
+      "grad_norm": 1.7872774600982666,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 4.4012,
+      "step": 19
+    },
+    {
+      "epoch": 0.0034278858514011482,
+      "grad_norm": 1.1536753177642822,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 4.1452,
+      "step": 20
+    },
+    {
+      "epoch": 0.0034278858514011482,
+      "eval_loss": 1.1016162633895874,
+      "eval_runtime": 433.766,
+      "eval_samples_per_second": 5.664,
+      "eval_steps_per_second": 2.833,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4246709207040000.0,
+  "total_flos": 8238615861657600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null