Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125a9720ad98f2f998a62906ffd8957d7a56a86fdfc7bbcd2995014433777bd3
+oid sha256:f5deb0af7c2975acff860fab574406b29d034773139a9c522f4d108f9dfb3867
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5080a1f46fdf7cbc1f3d2650761401fe01df09e9b0adc02fffa64996a87e0e7
+oid sha256:8e5b22d36596a7bd2f0cefb735c4e80953b0ade5e54ac4063f6a4a13d137a1e5
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a850cc6eda316843b981d8bd2fc891e4769877ed1461a31c08af31fbf0c075d3
+oid sha256:e31e0fdb3869a241061ca27b64da9fbd0a58f71586f852b6544558cc627e89db
 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": 1.5192136764526367,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.005689900426742532,
+  "best_metric": 1.4222428798675537,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.011379800853485065,
   "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": 2.559,
       "eval_steps_per_second": 1.28,
       "step": 10
+    },
+    {
+      "epoch": 0.006258890469416785,
+      "grad_norm": 1.0535948276519775,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.5521,
+      "step": 11
+    },
+    {
+      "epoch": 0.0068278805120910386,
+      "grad_norm": 0.8515264987945557,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.6025,
+      "step": 12
+    },
+    {
+      "epoch": 0.007396870554765292,
+      "grad_norm": 0.9776663184165955,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.5925,
+      "step": 13
+    },
+    {
+      "epoch": 0.007965860597439544,
+      "grad_norm": 0.8630133867263794,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.4374,
+      "step": 14
+    },
+    {
+      "epoch": 0.008534850640113799,
+      "grad_norm": 0.7540029287338257,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.476,
+      "step": 15
+    },
+    {
+      "epoch": 0.008534850640113799,
+      "eval_loss": 1.4430253505706787,
+      "eval_runtime": 290.3197,
+      "eval_samples_per_second": 2.549,
+      "eval_steps_per_second": 1.274,
+      "step": 15
+    },
+    {
+      "epoch": 0.009103840682788052,
+      "grad_norm": 0.7366471290588379,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3592,
+      "step": 16
+    },
+    {
+      "epoch": 0.009672830725462305,
+      "grad_norm": 0.7789183259010315,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.4968,
+      "step": 17
+    },
+    {
+      "epoch": 0.010241820768136558,
+      "grad_norm": 0.7127480506896973,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.3537,
+      "step": 18
+    },
+    {
+      "epoch": 0.010810810810810811,
+      "grad_norm": 0.7237548828125,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.41,
+      "step": 19
+    },
+    {
+      "epoch": 0.011379800853485065,
+      "grad_norm": 0.840724527835846,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.5217,
+      "step": 20
+    },
+    {
+      "epoch": 0.011379800853485065,
+      "eval_loss": 1.4222428798675537,
+      "eval_runtime": 298.5166,
+      "eval_samples_per_second": 2.479,
+      "eval_steps_per_second": 1.239,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3822182832537600.0,
+  "total_flos": 7644365665075200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null