Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54569bb4d3a615ec06c7f386202cf3c9d30570b940238c6dd64c192c95c84b4f
+oid sha256:d30c4a142008d1667738f04274603af896c576b8d94962f3509b91db33b6dee6
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e892e29aca24e07786db886c797e19d28a046c6f32dbf524fa06c605ab8031
+oid sha256:74eba59faffd18054385adeac319f0c57a79e79f6037276aeb46e3e5a153dcae
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c972560184ed3c2f23dac5dce36d314f6d11a20e2d058da06a5bbdd4f904b2b
+oid sha256:2b1cfff1f8bcf6ed37b27b73a75e4bacc6bd5f25aace99c77698a0e827c23340
 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": 1.184130072593689,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005930670462295762,
+  "best_metric": 0.4184398353099823,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0011861340924591525,
   "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": 6.673,
       "eval_steps_per_second": 3.336,
       "step": 10
+    },
+    {
+      "epoch": 0.0006523737508525338,
+      "grad_norm": 4.106665134429932,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.7186,
+      "step": 11
+    },
+    {
+      "epoch": 0.0007116804554754915,
+      "grad_norm": 2.682950973510742,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.6629,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007709871600984491,
+      "grad_norm": 2.9775516986846924,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.4503,
+      "step": 13
+    },
+    {
+      "epoch": 0.0008302938647214067,
+      "grad_norm": 3.0503790378570557,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.446,
+      "step": 14
+    },
+    {
+      "epoch": 0.0008896005693443643,
+      "grad_norm": 1.703140377998352,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.323,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008896005693443643,
+      "eval_loss": 0.33504584431648254,
+      "eval_runtime": 1072.4211,
+      "eval_samples_per_second": 6.621,
+      "eval_steps_per_second": 3.31,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009489072739673221,
+      "grad_norm": 3.130513906478882,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.3606,
+      "step": 16
+    },
+    {
+      "epoch": 0.0010082139785902795,
+      "grad_norm": 1.3841800689697266,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.3898,
+      "step": 17
+    },
+    {
+      "epoch": 0.0010675206832132373,
+      "grad_norm": 1.2063566446304321,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.3137,
+      "step": 18
+    },
+    {
+      "epoch": 0.001126827387836195,
+      "grad_norm": 2.978433609008789,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.2997,
+      "step": 19
+    },
+    {
+      "epoch": 0.0011861340924591525,
+      "grad_norm": 1.0437448024749756,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.3152,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011861340924591525,
+      "eval_loss": 0.4184398353099823,
+      "eval_runtime": 1085.3899,
+      "eval_samples_per_second": 6.541,
+      "eval_steps_per_second": 3.271,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1895803354349568.0,
+  "total_flos": 3930324027310080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null