Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dc8423aca2b8cddaaa1aae863af7804ca5c57fe85e13b54f441e067de9185b9
+oid sha256:c49eca6f0e15050bbf85e7bdcee025bf385fa39adb9ceb30813cd32b23a5cdad
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9502500dbbf39a0028965773d1af2c703c55f20c30ef6b136e3615912b97791
+oid sha256:10b39ecfdf33409025f4b60db0fba2c848eb0dd2f9ac9c92ec7946ef2eef2394
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea30508b2168921b3e75386a046978772f5cbc66bbd566c5d99dd61ea40c26f1
+oid sha256:a2f51136095b7fc6d10a6bb7fc123482a16d9870f2a5453d8d83fc637dd1ee7e
 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": 1.9385418891906738,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004253056884635832,
+  "best_metric": 1.938501000404358,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.008506113769271665,
   "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": 10.853,
       "eval_steps_per_second": 5.427,
       "step": 10
+    },
+    {
+      "epoch": 0.004678362573099415,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.1107,
+      "step": 11
+    },
+    {
+      "epoch": 0.005103668261562998,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.9652,
+      "step": 12
+    },
+    {
+      "epoch": 0.005528973950026581,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.8957,
+      "step": 13
+    },
+    {
+      "epoch": 0.005954279638490165,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.0176,
+      "step": 14
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.5971,
+      "step": 15
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "eval_loss": 1.9382401704788208,
+      "eval_runtime": 94.2275,
+      "eval_samples_per_second": 10.506,
+      "eval_steps_per_second": 5.253,
+      "step": 15
+    },
+    {
+      "epoch": 0.006804891015417331,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.3362,
+      "step": 16
+    },
+    {
+      "epoch": 0.007230196703880914,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.8985,
+      "step": 17
+    },
+    {
+      "epoch": 0.007655502392344498,
+      "grad_norm": Infinity,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.3079,
+      "step": 18
+    },
+    {
+      "epoch": 0.00808080808080808,
+      "grad_norm": Infinity,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.1374,
+      "step": 19
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "grad_norm": Infinity,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.7818,
+      "step": 20
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "eval_loss": 1.938501000404358,
+      "eval_runtime": 96.2698,
+      "eval_samples_per_second": 10.284,
+      "eval_steps_per_second": 5.142,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 511583956500480.0,
+  "total_flos": 1003983514632192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null