Training in progress, step 43, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:082354cf7b77354d1d6e5589631097bde4739e55f073aa94a1e51b5274982cbb
+oid sha256:53bd8c8fade11fc56f34d5339aa8f1be48f79647bac70f5f7e34f883f68ec4fe
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8460cf88fbb16903fe660ac0647d0ceaee3a2b24ee5bdc120b421cac066515
+oid sha256:cc7ebf280a204c672f79134f07d895828a519ac7f15f3da3423991817f62c56b
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92dd984373340a83b6635650b1d6d2134397bd39f683514afcb6b3b73706a09e
+oid sha256:bcff83727b6b623bf51e52c0614085c94e82ef8fed0b36ad05063d0dcd917a30
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0cfad423318cd794f93b9568f8f426e15cd0d879d8e07775c13405cf02f8f7a
+oid sha256:d4be715c64555aafbe9b0606977d1c7ff5bbcbd835648b41d6bc9b7e98899862
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bebb0d2c8120b1fa7cb74dfdc180dd65d203c6951cb9f6e5d1fd5aa7d20914e7
+oid sha256:1838ebb50c0de5b2e009a4d7607b195a41c6302f637c5d48f70e69ad53bdcb33
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ceca311914967ea008d145501d04ee43941fdb13dbb534e8fd993e0e7d3e81
+oid sha256:ed73194d87cb572d77f8c6849feed306097b7e95819c1471668d47853cd18865
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
+oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.7126981019973755,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7532751091703056,
+  "epoch": 3.024017467248908,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,132 @@
       "eval_samples_per_second": 10.329,
       "eval_steps_per_second": 2.686,
       "step": 25
+    },
+    {
+      "epoch": 1.8231441048034935,
+      "grad_norm": 1.3660728931427002,
+      "learning_rate": 4.307583240115024e-05,
+      "loss": 1.7941,
+      "step": 26
+    },
+    {
+      "epoch": 1.8930131004366813,
+      "grad_norm": 1.4073928594589233,
+      "learning_rate": 3.9789240471617385e-05,
+      "loss": 1.6295,
+      "step": 27
+    },
+    {
+      "epoch": 1.962882096069869,
+      "grad_norm": 2.1648712158203125,
+      "learning_rate": 3.659191132728971e-05,
+      "loss": 1.7869,
+      "step": 28
+    },
+    {
+      "epoch": 2.039301310043668,
+      "grad_norm": 2.377962112426758,
+      "learning_rate": 3.350260816694816e-05,
+      "loss": 2.797,
+      "step": 29
+    },
+    {
+      "epoch": 2.109170305676856,
+      "grad_norm": 1.0877033472061157,
+      "learning_rate": 3.0539460249945056e-05,
+      "loss": 1.3597,
+      "step": 30
+    },
+    {
+      "epoch": 2.1790393013100435,
+      "grad_norm": 1.52259361743927,
+      "learning_rate": 2.7719856506501306e-05,
+      "loss": 1.4955,
+      "step": 31
+    },
+    {
+      "epoch": 2.2489082969432315,
+      "grad_norm": 0.9151427745819092,
+      "learning_rate": 2.5060343492549566e-05,
+      "loss": 0.9611,
+      "step": 32
+    },
+    {
+      "epoch": 2.3187772925764194,
+      "grad_norm": 1.2203819751739502,
+      "learning_rate": 2.257652828796459e-05,
+      "loss": 1.9958,
+      "step": 33
+    },
+    {
+      "epoch": 2.388646288209607,
+      "grad_norm": 1.1448140144348145,
+      "learning_rate": 2.0282986908012567e-05,
+      "loss": 1.3613,
+      "step": 34
+    },
+    {
+      "epoch": 2.458515283842795,
+      "grad_norm": 1.8198349475860596,
+      "learning_rate": 1.819317876549771e-05,
+      "loss": 1.5567,
+      "step": 35
+    },
+    {
+      "epoch": 2.5283842794759828,
+      "grad_norm": 1.442224144935608,
+      "learning_rate": 1.631936768557596e-05,
+      "loss": 1.4807,
+      "step": 36
+    },
+    {
+      "epoch": 2.5982532751091703,
+      "grad_norm": 0.909432053565979,
+      "learning_rate": 1.4672549936752506e-05,
+      "loss": 1.3377,
+      "step": 37
+    },
+    {
+      "epoch": 2.668122270742358,
+      "grad_norm": 1.3751412630081177,
+      "learning_rate": 1.3262389700405744e-05,
+      "loss": 1.3987,
+      "step": 38
+    },
+    {
+      "epoch": 2.7379912663755457,
+      "grad_norm": 0.9823693633079529,
+      "learning_rate": 1.2097162357528127e-05,
+      "loss": 0.8902,
+      "step": 39
+    },
+    {
+      "epoch": 2.8078602620087336,
+      "grad_norm": 1.2921277284622192,
+      "learning_rate": 1.1183705925499948e-05,
+      "loss": 1.981,
+      "step": 40
+    },
+    {
+      "epoch": 2.8777292576419216,
+      "grad_norm": 1.107571005821228,
+      "learning_rate": 1.0527380929884324e-05,
+      "loss": 1.401,
+      "step": 41
+    },
+    {
+      "epoch": 2.947598253275109,
+      "grad_norm": 1.6754684448242188,
+      "learning_rate": 1.013203894673168e-05,
+      "loss": 1.4869,
+      "step": 42
+    },
+    {
+      "epoch": 3.024017467248908,
+      "grad_norm": 2.1372737884521484,
+      "learning_rate": 1e-05,
+      "loss": 2.5759,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -221,12 +347,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.087239672233984e+17,
+  "total_flos": 5.3100522362424525e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null