Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a6850777541de14cc9bd2b4def13dabe4483a70fd4415e199d4e0faafe9b28
+oid sha256:339c1190f432c23d6c1daf8f6677fadcb579fad0f870eb787a951b9c14e19662
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221966b65f6fec6d63d1aea1e470a1013c1f43f93b15fbe26bdb80c2771593dc
+oid sha256:6b3a455ca5d5edd307fad8171fde0e04728e9c4ef9b8b0d4022306f40abeaa05
 size 83282170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:310bb6727fee8c47ab830d63c0d0fb961145c0365ca0793daf588b90a402b171
+oid sha256:de5a71f85b9114cd14ba8af960a46ef128aa17617f8a68ea324dbe570a75123f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8938112258911133,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00211999152003392,
+  "best_metric": 1.739220380783081,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00423998304006784,
   "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": 7.14,
       "eval_steps_per_second": 3.572,
       "step": 10
+    },
+    {
+      "epoch": 0.002331990672037312,
+      "grad_norm": 0.7144079208374023,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 1.7174,
+      "step": 11
+    },
+    {
+      "epoch": 0.0025439898240407037,
+      "grad_norm": 0.8546844720840454,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 1.903,
+      "step": 12
+    },
+    {
+      "epoch": 0.002755988976044096,
+      "grad_norm": 0.8503435254096985,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.1831,
+      "step": 13
+    },
+    {
+      "epoch": 0.002967988128047488,
+      "grad_norm": 1.2312841415405273,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 1.8006,
+      "step": 14
+    },
+    {
+      "epoch": 0.0031799872800508796,
+      "grad_norm": 0.9335196018218994,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.74,
+      "step": 15
+    },
+    {
+      "epoch": 0.0031799872800508796,
+      "eval_loss": 1.8009980916976929,
+      "eval_runtime": 279.0929,
+      "eval_samples_per_second": 7.119,
+      "eval_steps_per_second": 3.562,
+      "step": 15
+    },
+    {
+      "epoch": 0.0033919864320542717,
+      "grad_norm": 1.0158390998840332,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1792,
+      "step": 16
+    },
+    {
+      "epoch": 0.003603985584057664,
+      "grad_norm": 0.8165982365608215,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.6872,
+      "step": 17
+    },
+    {
+      "epoch": 0.0038159847360610556,
+      "grad_norm": 0.8424365520477295,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.8862,
+      "step": 18
+    },
+    {
+      "epoch": 0.004027983888064448,
+      "grad_norm": 0.8149735331535339,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.6499,
+      "step": 19
+    },
+    {
+      "epoch": 0.00423998304006784,
+      "grad_norm": 0.8468019962310791,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.816,
+      "step": 20
+    },
+    {
+      "epoch": 0.00423998304006784,
+      "eval_loss": 1.739220380783081,
+      "eval_runtime": 281.1808,
+      "eval_samples_per_second": 7.067,
+      "eval_steps_per_second": 3.535,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1000194661416960.0,
+  "total_flos": 2000389322833920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null