Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bd147aa3357cfdca7be21ac9bd8165eeb041fd900b8cc345628332e43ac3ba
+oid sha256:ce11877e4e553b7dc4a5a65cdabc39ec8d921d058f2c9d82614d79393797ab0e
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09c03e9f5c31d4f677db605ce4f243c2bf8322a7087754417194530294737759
+oid sha256:7688bd49ceef3c0f870a5ae30078b923ab31b7827a8c4524911c4cd30208fa02
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c615fdcb1af9159396500207ffb4a5b04371e0d2685ad2d53e199b3a2fd0bef6
+oid sha256:23a6eee3875a9902a549f4bad55856201b51958acc44fbbb2102e758981da379
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efceaa5c248a4d80b63fee15b42b7a10a2394777ecd3ca622c0d4a7cf33eef18
+oid sha256:c9270801a091d1fd46d6e273e2ff0ed3fb1f5321828110607b5eb48295bb7f4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.9600940942764282,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.15037593984962405,
+  "epoch": 0.3007518796992481,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 16.369,
       "eval_steps_per_second": 4.092,
       "step": 50
+    },
+    {
+      "epoch": 0.18045112781954886,
+      "grad_norm": 4.931917667388916,
+      "learning_rate": 0.00021732906980769228,
+      "loss": 1.7875,
+      "step": 60
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 5.513779640197754,
+      "learning_rate": 0.00021532453881467652,
+      "loss": 1.415,
+      "step": 70
+    },
+    {
+      "epoch": 0.24060150375939848,
+      "grad_norm": 8.94431209564209,
+      "learning_rate": 0.0002120110840918633,
+      "loss": 1.4613,
+      "step": 80
+    },
+    {
+      "epoch": 0.2706766917293233,
+      "grad_norm": 7.7282328605651855,
+      "learning_rate": 0.00020742949640648896,
+      "loss": 1.6876,
+      "step": 90
+    },
+    {
+      "epoch": 0.3007518796992481,
+      "grad_norm": 9.372624397277832,
+      "learning_rate": 0.00020163617806143107,
+      "loss": 1.7947,
+      "step": 100
+    },
+    {
+      "epoch": 0.3007518796992481,
+      "eval_loss": 2.0332393646240234,
+      "eval_runtime": 8.5853,
+      "eval_samples_per_second": 16.307,
+      "eval_steps_per_second": 4.077,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9428209867161600.0,
+  "total_flos": 1.88564197343232e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null