Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ae8cc4ed1760aaf52137cc29af689a1f0ffafd8127fa130683fc5771beea835
+oid sha256:07d4669abcafa1e4ffd4094fd4dead1c5f5b255ef58535f18838a912a8520a35
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b848c54164deb9117227cf9e6d0c3d5617c1b37b98d7912afa0083fabd9fa35
+oid sha256:5c7cbee7f44d5ac14bf7714106f89fce09244334f6ea9f68f24fcb21e4ef3d7c
 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": 2.518630266189575,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.007979253939756632,
+  "best_metric": 1.7598896026611328,
+  "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": 6.734,
       "eval_steps_per_second": 3.367,
       "step": 10
+    },
+    {
+      "epoch": 0.008777179333732297,
+      "grad_norm": 3.283538818359375,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.6401,
+      "step": 11
+    },
+    {
+      "epoch": 0.009575104727707959,
+      "grad_norm": 3.5200719833374023,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.4038,
+      "step": 12
+    },
+    {
+      "epoch": 0.010373030121683623,
+      "grad_norm": 3.327225685119629,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.8051,
+      "step": 13
+    },
+    {
+      "epoch": 0.011170955515659286,
+      "grad_norm": 3.6973745822906494,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.0058,
+      "step": 14
+    },
+    {
+      "epoch": 0.011968880909634948,
+      "grad_norm": 4.162341594696045,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9943,
+      "step": 15
+    },
+    {
+      "epoch": 0.011968880909634948,
+      "eval_loss": 1.8908601999282837,
+      "eval_runtime": 77.3751,
+      "eval_samples_per_second": 6.824,
+      "eval_steps_per_second": 3.412,
+      "step": 15
+    },
+    {
+      "epoch": 0.012766806303610613,
+      "grad_norm": 3.85834002494812,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.0078,
+      "step": 16
+    },
+    {
+      "epoch": 0.013564731697586275,
+      "grad_norm": 3.9787638187408447,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.7308,
+      "step": 17
+    },
+    {
+      "epoch": 0.01436265709156194,
+      "grad_norm": 2.864772081375122,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.5955,
+      "step": 18
+    },
+    {
+      "epoch": 0.015160582485537602,
+      "grad_norm": 2.9417033195495605,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.7731,
+      "step": 19
+    },
+    {
+      "epoch": 0.015958507879513265,
+      "grad_norm": 3.152362585067749,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.4819,
+      "step": 20
+    },
+    {
+      "epoch": 0.015958507879513265,
+      "eval_loss": 1.7598896026611328,
+      "eval_runtime": 77.2455,
+      "eval_samples_per_second": 6.835,
+      "eval_steps_per_second": 3.418,
+      "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