Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8fbe89c89fe8b76fbbc2b92b5e8e3c202960066263105478e3dd057db9425c
+oid sha256:e112f6280ea87968966c4e6ed169cca225df194f22dbcd5fee4738e30364ae28
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0cab110c6c1ce6ff7d90d0f7275f14888461c6858620a5581215075a35b10a5
+oid sha256:cfe23a7ce69d9f0aa99222fae7b7d261c3e586f5c2ce985f1e5e0874093809dd
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7b954aa125cb706989c93eb8b8a07d1f671c59f16b1a580fbfb54e4277378b1
+oid sha256:f730d25ca7055812680848b28a7f272d6c688ebe371af523184e3e32b4a5c53b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e5fa9b5dd6a1e93b49fb54b88fcd17f280fec5b8ecd677a0fd769432d6af9a
+oid sha256:e184f69d00141178850739df7430ff513af0727be2f561e148f54a68dd89a4d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ebe216a68903ec3b1ec0fd787b455a9025050298e1faacd6a6dfd0e3c4c3cd3
+oid sha256:afbf69036d9a73903827785037cdde400907c7e61c3874bffeddbb41adcc82b1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:489c6810aa00bdabb22946e4ee8163eee88c18ee07387d934dbaae647cbc97c4
+oid sha256:6e878db44b907ff1c4121e7918493401b760e4740646221db7d716b8d9cf7f22
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.218059539794922,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4351687388987566,
+  "best_metric": 4.043777942657471,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.8703374777975132,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 76.553,
       "eval_steps_per_second": 19.904,
       "step": 25
+    },
+    {
+      "epoch": 1.492007104795737,
+      "grad_norm": 0.6616500020027161,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.0374,
+      "step": 26
+    },
+    {
+      "epoch": 1.5488454706927177,
+      "grad_norm": 0.9311549067497253,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.6396,
+      "step": 27
+    },
+    {
+      "epoch": 1.605683836589698,
+      "grad_norm": 0.7478369474411011,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.8456,
+      "step": 28
+    },
+    {
+      "epoch": 1.6625222024866786,
+      "grad_norm": 0.6867173910140991,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.1692,
+      "step": 29
+    },
+    {
+      "epoch": 1.7193605683836588,
+      "grad_norm": 0.5758339166641235,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.2151,
+      "step": 30
+    },
+    {
+      "epoch": 1.7761989342806395,
+      "grad_norm": 1.5432807207107544,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 5.6372,
+      "step": 31
+    },
+    {
+      "epoch": 1.83303730017762,
+      "grad_norm": 0.5938176512718201,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.8315,
+      "step": 32
+    },
+    {
+      "epoch": 1.8898756660746003,
+      "grad_norm": 0.652653157711029,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.0855,
+      "step": 33
+    },
+    {
+      "epoch": 1.9467140319715808,
+      "grad_norm": 1.2059962749481201,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.448,
+      "step": 34
+    },
+    {
+      "epoch": 2.0177619893428065,
+      "grad_norm": 0.9915326833724976,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.6656,
+      "step": 35
+    },
+    {
+      "epoch": 2.0746003552397867,
+      "grad_norm": 0.5259771943092346,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.3707,
+      "step": 36
+    },
+    {
+      "epoch": 2.1314387211367674,
+      "grad_norm": 0.7280540466308594,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.8562,
+      "step": 37
+    },
+    {
+      "epoch": 2.1882770870337476,
+      "grad_norm": 0.7593219876289368,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.1603,
+      "step": 38
+    },
+    {
+      "epoch": 2.2451154529307282,
+      "grad_norm": 0.7831996083259583,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.4129,
+      "step": 39
+    },
+    {
+      "epoch": 2.301953818827709,
+      "grad_norm": 0.9821178317070007,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.3152,
+      "step": 40
+    },
+    {
+      "epoch": 2.358792184724689,
+      "grad_norm": 0.5698879957199097,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.8146,
+      "step": 41
+    },
+    {
+      "epoch": 2.4156305506216698,
+      "grad_norm": 0.6594037413597107,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.0656,
+      "step": 42
+    },
+    {
+      "epoch": 2.47246891651865,
+      "grad_norm": 0.6938492059707642,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.8914,
+      "step": 43
+    },
+    {
+      "epoch": 2.5293072824156306,
+      "grad_norm": 1.052404761314392,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.7826,
+      "step": 44
+    },
+    {
+      "epoch": 2.586145648312611,
+      "grad_norm": 0.5612595677375793,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.7658,
+      "step": 45
+    },
+    {
+      "epoch": 2.6429840142095915,
+      "grad_norm": 0.7995758056640625,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.0587,
+      "step": 46
+    },
+    {
+      "epoch": 2.699822380106572,
+      "grad_norm": 0.6661505699157715,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.0607,
+      "step": 47
+    },
+    {
+      "epoch": 2.7566607460035524,
+      "grad_norm": 0.7999106645584106,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.5456,
+      "step": 48
+    },
+    {
+      "epoch": 2.8134991119005326,
+      "grad_norm": 0.5701779127120972,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.6241,
+      "step": 49
+    },
+    {
+      "epoch": 2.8703374777975132,
+      "grad_norm": 0.5628406405448914,
+      "learning_rate": 1e-05,
+      "loss": 3.9367,
+      "step": 50
+    },
+    {
+      "epoch": 2.8703374777975132,
+      "eval_loss": 4.043777942657471,
+      "eval_runtime": 0.661,
+      "eval_samples_per_second": 75.642,
+      "eval_steps_per_second": 19.667,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5686862177894400.0,
+  "total_flos": 1.13737243557888e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null