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:ae5e02aa38a8cce980fcde1a1e0cd8f1dedbf1a9074e3f776584271f5b75c475
+oid sha256:7a441d19aa280352bb764683a1fb2d387278721a4f34e9313a77cd28ed8627b8
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244613ef9af9f46a25b382c87657e4ba253e54e244ec47fa84884d9835072867
+oid sha256:4c4df38dac65f1bb66cc8b7b93cadef77281c83a32d7caef9891da1e81eac96c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af4cbe6dd62788676ba2597afaddb6a97ff06bf7b18f8e3a0ce4190a674ccd8
+oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
 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": 2.5102765560150146,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.007979253939756632,
+  "best_metric": 1.7614365816116333,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.015958507879513265,
   "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": 4.695,
       "eval_steps_per_second": 2.348,
       "step": 10
+    },
+    {
+      "epoch": 0.008777179333732297,
+      "grad_norm": 3.2941677570343018,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.6612,
+      "step": 11
+    },
+    {
+      "epoch": 0.009575104727707959,
+      "grad_norm": 3.6355504989624023,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.4075,
+      "step": 12
+    },
+    {
+      "epoch": 0.010373030121683623,
+      "grad_norm": 3.447693109512329,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.7719,
+      "step": 13
+    },
+    {
+      "epoch": 0.011170955515659286,
+      "grad_norm": 4.26869010925293,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.0118,
+      "step": 14
+    },
+    {
+      "epoch": 0.011968880909634948,
+      "grad_norm": 4.2341389656066895,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9992,
+      "step": 15
+    },
+    {
+      "epoch": 0.011968880909634948,
+      "eval_loss": 1.9001727104187012,
+      "eval_runtime": 111.7285,
+      "eval_samples_per_second": 4.726,
+      "eval_steps_per_second": 2.363,
+      "step": 15
+    },
+    {
+      "epoch": 0.012766806303610613,
+      "grad_norm": 3.968799352645874,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.0193,
+      "step": 16
+    },
+    {
+      "epoch": 0.013564731697586275,
+      "grad_norm": 4.071308612823486,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.7212,
+      "step": 17
+    },
+    {
+      "epoch": 0.01436265709156194,
+      "grad_norm": 2.9081594944000244,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.5923,
+      "step": 18
+    },
+    {
+      "epoch": 0.015160582485537602,
+      "grad_norm": 2.9626481533050537,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.7981,
+      "step": 19
+    },
+    {
+      "epoch": 0.015958507879513265,
+      "grad_norm": 3.4484167098999023,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.4806,
+      "step": 20
+    },
+    {
+      "epoch": 0.015958507879513265,
+      "eval_loss": 1.7614365816116333,
+      "eval_runtime": 114.7069,
+      "eval_samples_per_second": 4.603,
+      "eval_steps_per_second": 2.302,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null