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:a3d62fa6c5136ae1c29a0713332f9f9c789a5b96409f2b52d1db60f435b8daff
+oid sha256:3a7ba2eebe874f091291dffecfe55b7332dae4d8d63e11c416e308af73d1f2d1
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f2ff58af0ede4fb10f12c3243f8eb61ef72368c430b677b891d7c29bbf54040
+oid sha256:12a0f339da764fb5739ae255569973720c18b05bfa7b9a2ff78256f8bb3d5bbc
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e5378b06691929bd5fb86de3501deae06db1a07c13d1ad6f3e2785ddbeec2d3
+oid sha256:994034717e12e40cf8684521a3d2529d09c2397c5a8d5800aa2a30d80556de58
 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": 3.275075674057007,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.027932960893854747,
+  "best_metric": 3.155805826187134,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.055865921787709494,
   "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": 31.448,
       "eval_steps_per_second": 15.828,
       "step": 10
+    },
+    {
+      "epoch": 0.030726256983240222,
+      "grad_norm": 2734.73876953125,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 13.0272,
+      "step": 11
+    },
+    {
+      "epoch": 0.0335195530726257,
+      "grad_norm": 1246.3319091796875,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 14.1851,
+      "step": 12
+    },
+    {
+      "epoch": 0.036312849162011177,
+      "grad_norm": 959.4293212890625,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 12.7241,
+      "step": 13
+    },
+    {
+      "epoch": 0.03910614525139665,
+      "grad_norm": 1641.6357421875,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 13.6186,
+      "step": 14
+    },
+    {
+      "epoch": 0.04189944134078212,
+      "grad_norm": 1507.56640625,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 11.9316,
+      "step": 15
+    },
+    {
+      "epoch": 0.04189944134078212,
+      "eval_loss": 3.233804702758789,
+      "eval_runtime": 4.8696,
+      "eval_samples_per_second": 31.009,
+      "eval_steps_per_second": 15.607,
+      "step": 15
+    },
+    {
+      "epoch": 0.0446927374301676,
+      "grad_norm": 2713.677001953125,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 13.57,
+      "step": 16
+    },
+    {
+      "epoch": 0.04748603351955307,
+      "grad_norm": 1984.106689453125,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 11.9724,
+      "step": 17
+    },
+    {
+      "epoch": 0.05027932960893855,
+      "grad_norm": 851.5194702148438,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 12.0016,
+      "step": 18
+    },
+    {
+      "epoch": 0.05307262569832402,
+      "grad_norm": 986.9415893554688,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 12.7948,
+      "step": 19
+    },
+    {
+      "epoch": 0.055865921787709494,
+      "grad_norm": 939.6593017578125,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 13.3214,
+      "step": 20
+    },
+    {
+      "epoch": 0.055865921787709494,
+      "eval_loss": 3.155805826187134,
+      "eval_runtime": 5.0184,
+      "eval_samples_per_second": 30.089,
+      "eval_steps_per_second": 15.144,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 30687834931200.0,
+  "total_flos": 61375669862400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null