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:b79e7de1549878ea5ec1f7315303ce2126e11ad39e51a9d2efb38827e16f1151
+oid sha256:05c3c048052b26505bcbe14caa7a7564e2616aca80017766f6d9dcb5c72b0b93
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f3fa3fe740d4a07e1a31230289b4338ece0e86316aa87bfea0367325b2697e3
+oid sha256:ed1ae9987d13850c59b919b9c6ce075f51d97eef2e00178c06cabeed9535bdeb
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
+oid sha256:1e97bf1fc0df7b7494795657cf00ff10f81fe5ecaafce75d405590f0e5957162
 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": 0.45037999749183655,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008355964069354502,
+  "best_metric": 0.2781434953212738,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.016711928138709004,
   "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": 11.867,
       "eval_steps_per_second": 5.934,
       "step": 10
+    },
+    {
+      "epoch": 0.009191560476289952,
+      "grad_norm": 15.18215274810791,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.2433,
+      "step": 11
+    },
+    {
+      "epoch": 0.010027156883225401,
+      "grad_norm": 8.072440147399902,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.786,
+      "step": 12
+    },
+    {
+      "epoch": 0.010862753290160853,
+      "grad_norm": 16.285877227783203,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.4247,
+      "step": 13
+    },
+    {
+      "epoch": 0.011698349697096303,
+      "grad_norm": 12.89522647857666,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.2496,
+      "step": 14
+    },
+    {
+      "epoch": 0.012533946104031753,
+      "grad_norm": 8.819092750549316,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.1286,
+      "step": 15
+    },
+    {
+      "epoch": 0.012533946104031753,
+      "eval_loss": 0.2794611155986786,
+      "eval_runtime": 42.4792,
+      "eval_samples_per_second": 11.865,
+      "eval_steps_per_second": 5.932,
+      "step": 15
+    },
+    {
+      "epoch": 0.013369542510967202,
+      "grad_norm": 15.040021896362305,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0071,
+      "step": 16
+    },
+    {
+      "epoch": 0.014205138917902652,
+      "grad_norm": 12.307514190673828,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.9801,
+      "step": 17
+    },
+    {
+      "epoch": 0.015040735324838104,
+      "grad_norm": 5.802730083465576,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.8074,
+      "step": 18
+    },
+    {
+      "epoch": 0.015876331731773552,
+      "grad_norm": 2.801945924758911,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5972,
+      "step": 19
+    },
+    {
+      "epoch": 0.016711928138709004,
+      "grad_norm": 29.06494903564453,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.0841,
+      "step": 20
+    },
+    {
+      "epoch": 0.016711928138709004,
+      "eval_loss": 0.2781434953212738,
+      "eval_runtime": 43.062,
+      "eval_samples_per_second": 11.704,
+      "eval_steps_per_second": 5.852,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 652949323776000.0,
+  "total_flos": 1322222380646400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null