Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62f42244a5722e29274adf26c05a5525c9afc4cc1703df9ed9f76b3ef12a774e
+oid sha256:b10bce8d5d84c15eeb4042f0e320c0e40cdac42ee29f6c89daec1552952952c1
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d4f9c02e02907e08fde41357e2788a58e02122f0b79fcdd6a323bcc74fa2a9
+oid sha256:46d9e6f29c5ec2f1e19ec5efb0c143adbf413efbf5f25931ddcade2ac0ec3122
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:769da8e4447524e633f93f76d341b4b2705f1e367dd0ff1c880819b427f7763b
+oid sha256:976ddfffcf431fe77a5c77c02d74fdf8f4ca62876a3e0635e750427d9f20e837
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ff3cc9727c45552d411cba0b4218ebf96078dc6833fe6461dcb4ba430f6e35
+oid sha256:18e9a2929e7509be2773c3d7e3c49f919baf16ad5df6e84bc7952aac5fc28ba3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8211a6d46987dcdcea9cbc40781d7ad98b5d78fb69a051111a7cd25b8e63e61
+oid sha256:6e8482dd36ec8c8b78fb7750e4f23974c53dc998f90c0eb08104ac6ee1fe490b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8841b37fd368c23ff5de0dbd1532c16c2578aa549b516714e143b21ae186071
+oid sha256:5c18cf85942adf6b7485fb843a325bf4a041ad6a87954417334bc075bce864a9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5586592178770949,
+  "epoch": 1.1201117318435754,
   "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": 58.089,
       "eval_steps_per_second": 7.309,
       "step": 25
+    },
+    {
+      "epoch": 0.5810055865921788,
+      "grad_norm": 0.5823168754577637,
+      "learning_rate": 5e-05,
+      "loss": 2.2451,
+      "step": 26
+    },
+    {
+      "epoch": 0.6033519553072626,
+      "grad_norm": 0.6771988272666931,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.2603,
+      "step": 27
+    },
+    {
+      "epoch": 0.6256983240223464,
+      "grad_norm": 0.83906090259552,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.0626,
+      "step": 28
+    },
+    {
+      "epoch": 0.6480446927374302,
+      "grad_norm": 0.6448845267295837,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.3127,
+      "step": 29
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "grad_norm": 0.6946954727172852,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.2754,
+      "step": 30
+    },
+    {
+      "epoch": 0.6927374301675978,
+      "grad_norm": 0.6927757859230042,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.4821,
+      "step": 31
+    },
+    {
+      "epoch": 0.7150837988826816,
+      "grad_norm": 0.7330152988433838,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.4882,
+      "step": 32
+    },
+    {
+      "epoch": 0.7374301675977654,
+      "grad_norm": 1.3319170475006104,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.582,
+      "step": 33
+    },
+    {
+      "epoch": 0.7597765363128491,
+      "grad_norm": 0.6171111464500427,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.2166,
+      "step": 34
+    },
+    {
+      "epoch": 0.7821229050279329,
+      "grad_norm": 0.6328678727149963,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.1576,
+      "step": 35
+    },
+    {
+      "epoch": 0.8044692737430168,
+      "grad_norm": 0.60038161277771,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.1738,
+      "step": 36
+    },
+    {
+      "epoch": 0.8268156424581006,
+      "grad_norm": 0.5997684597969055,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.0954,
+      "step": 37
+    },
+    {
+      "epoch": 0.8491620111731844,
+      "grad_norm": 0.7614952921867371,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2288,
+      "step": 38
+    },
+    {
+      "epoch": 0.8715083798882681,
+      "grad_norm": 0.7809704542160034,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.079,
+      "step": 39
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 0.6555606722831726,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.3115,
+      "step": 40
+    },
+    {
+      "epoch": 0.9162011173184358,
+      "grad_norm": 0.6785370111465454,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.3111,
+      "step": 41
+    },
+    {
+      "epoch": 0.9385474860335196,
+      "grad_norm": 0.6954032778739929,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.4374,
+      "step": 42
+    },
+    {
+      "epoch": 0.9608938547486033,
+      "grad_norm": 0.7169734835624695,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.3836,
+      "step": 43
+    },
+    {
+      "epoch": 0.9832402234636871,
+      "grad_norm": 1.2481937408447266,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.4977,
+      "step": 44
+    },
+    {
+      "epoch": 1.0083798882681565,
+      "grad_norm": 0.7138010859489441,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.1846,
+      "step": 45
+    },
+    {
+      "epoch": 1.0307262569832403,
+      "grad_norm": 0.5319519639015198,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.0249,
+      "step": 46
+    },
+    {
+      "epoch": 1.053072625698324,
+      "grad_norm": 0.6440411806106567,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.1081,
+      "step": 47
+    },
+    {
+      "epoch": 1.0754189944134078,
+      "grad_norm": 0.6161705851554871,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.2051,
+      "step": 48
+    },
+    {
+      "epoch": 1.0977653631284916,
+      "grad_norm": 0.5636197924613953,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.0141,
+      "step": 49
+    },
+    {
+      "epoch": 1.1201117318435754,
+      "grad_norm": 0.7595768570899963,
+      "learning_rate": 0.0,
+      "loss": 2.1503,
+      "step": 50
+    },
+    {
+      "epoch": 1.1201117318435754,
+      "eval_loss": NaN,
+      "eval_runtime": 5.1987,
+      "eval_samples_per_second": 58.092,
+      "eval_steps_per_second": 7.31,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null