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:e6f4dac56dbaef3c69c747a9438157654696107247801930ca65d7ab1e010d83
+oid sha256:f14b98721fd78d56d91768fa4bbbd66f4cc7fe6b48f2adf6af4db86fc8f7462f
 size 556856304

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a0ae8b7bbedd5dc85bdded7856ffde5bab078ec86434f7b24379445c2e49fd
+oid sha256:416d45d931ecb3d674f2892b483c5831f63400a080814346cb7baf8e8d1536ff
 size 21599060

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ca2f09f9de957054550f9a625d706d2e44e39a8a311ac8107aa98178e5c87a
+oid sha256:3b1857c66e6e8d6e11a0747eed5b4017955023dcf6f7964ebdc3cb5802d5c9a1
 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": 1.2067017555236816,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00021695974311966416,
+  "best_metric": 0.9340419769287109,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0004339194862393283,
   "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": 11.381,
       "eval_steps_per_second": 5.691,
       "step": 10
+    },
+    {
+      "epoch": 0.00023865571743163057,
+      "grad_norm": 5.8415374755859375,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.639,
+      "step": 11
+    },
+    {
+      "epoch": 0.000260351691743597,
+      "grad_norm": 4.822943210601807,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.8134,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002820476660555634,
+      "grad_norm": 4.433187484741211,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.3497,
+      "step": 13
+    },
+    {
+      "epoch": 0.0003037436403675298,
+      "grad_norm": 5.982097148895264,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 5.1374,
+      "step": 14
+    },
+    {
+      "epoch": 0.0003254396146794962,
+      "grad_norm": 5.101588249206543,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.4414,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003254396146794962,
+      "eval_loss": 1.0443052053451538,
+      "eval_runtime": 1757.1215,
+      "eval_samples_per_second": 11.045,
+      "eval_steps_per_second": 5.523,
+      "step": 15
+    },
+    {
+      "epoch": 0.00034713558899146263,
+      "grad_norm": 4.684109210968018,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.1763,
+      "step": 16
+    },
+    {
+      "epoch": 0.00036883156330342904,
+      "grad_norm": 4.625067710876465,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.4839,
+      "step": 17
+    },
+    {
+      "epoch": 0.00039052753761539545,
+      "grad_norm": 5.083712577819824,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.2659,
+      "step": 18
+    },
+    {
+      "epoch": 0.00041222351192736186,
+      "grad_norm": 3.9180216789245605,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.9517,
+      "step": 19
+    },
+    {
+      "epoch": 0.0004339194862393283,
+      "grad_norm": 3.9014394283294678,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.7442,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004339194862393283,
+      "eval_loss": 0.9340419769287109,
+      "eval_runtime": 1708.7785,
+      "eval_samples_per_second": 11.357,
+      "eval_steps_per_second": 5.679,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 652949323776000.0,
+  "total_flos": 1305898647552000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null