Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d76030b99a05293e55be8eb7786dbb3742e555fb762aec123af68caf6f94d4b
+oid sha256:e0d683097420445ae2da7ae9bd76187929932263fba955aafc473f15f6763f34
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e326fa0de9155a70dcfd4d3e546ceca7f6cc0ca90819141d04737e6e0e57b95
+oid sha256:a1db7773a45f6e1fd92a6632c0312bbec8bb7abc442c18fbf412d506775af22b
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8194e1b8c74d7216b4daf200bbfe7e0ecb859e151ee00b0f9ea8e824e6edee25
+oid sha256:1bd0f89b229cfeaa8b1bf1cf4a142955879943acc15ca9084fb458bceded42a4
 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": 4.565164089202881,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004642525533890436,
+  "best_metric": 3.892979621887207,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.009285051067780872,
   "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": 10.672,
       "eval_steps_per_second": 5.342,
       "step": 10
+    },
+    {
+      "epoch": 0.00510677808727948,
+      "grad_norm": 18.395423889160156,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 19.0316,
+      "step": 11
+    },
+    {
+      "epoch": 0.005571030640668524,
+      "grad_norm": 20.571325302124023,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 16.4249,
+      "step": 12
+    },
+    {
+      "epoch": 0.0060352831940575676,
+      "grad_norm": 26.195552825927734,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 17.4389,
+      "step": 13
+    },
+    {
+      "epoch": 0.0064995357474466105,
+      "grad_norm": 30.251649856567383,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 17.2635,
+      "step": 14
+    },
+    {
+      "epoch": 0.006963788300835654,
+      "grad_norm": 35.24900436401367,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 18.2635,
+      "step": 15
+    },
+    {
+      "epoch": 0.006963788300835654,
+      "eval_loss": 4.202820777893066,
+      "eval_runtime": 84.7163,
+      "eval_samples_per_second": 10.706,
+      "eval_steps_per_second": 5.359,
+      "step": 15
+    },
+    {
+      "epoch": 0.007428040854224698,
+      "grad_norm": 32.32241439819336,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 19.6751,
+      "step": 16
+    },
+    {
+      "epoch": 0.007892293407613741,
+      "grad_norm": 30.068628311157227,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 16.9337,
+      "step": 17
+    },
+    {
+      "epoch": 0.008356545961002786,
+      "grad_norm": 25.404611587524414,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 16.751,
+      "step": 18
+    },
+    {
+      "epoch": 0.008820798514391829,
+      "grad_norm": 22.091705322265625,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 15.4559,
+      "step": 19
+    },
+    {
+      "epoch": 0.009285051067780872,
+      "grad_norm": 24.179677963256836,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 16.1199,
+      "step": 20
+    },
+    {
+      "epoch": 0.009285051067780872,
+      "eval_loss": 3.892979621887207,
+      "eval_runtime": 84.3821,
+      "eval_samples_per_second": 10.749,
+      "eval_steps_per_second": 5.38,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1632478030725120.0,
+  "total_flos": 3264956061450240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null