Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2de40690cf65edd413b5bcd47460a978cb416abffc3ffaeb5069c81f18f5fa
+oid sha256:74fb4e2e79b702d18ecb0e3054321969c42e7ac05c86d1da5c3c99b7dedd72e7
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c552068265d6055ce86f5a48964dfe867d5220018c21da3c25bbac18ea53ee2b
+oid sha256:8d9259ee1eb332efcb740768297dfad88170ed976ed41351684e1172f45fee50
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d532d1753fde9d2c1cf00c0b37994359d3f5a91e73654280084ad095c7968c59
+oid sha256:86b7c41bffe49f31b8c2127a738b5a2e1ce2673c7fc76505c48f33a9224a1a4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67bdc1680e75e7cf9661cc84482edc217f841c56aca5f9a3979c1c72a436f392
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6363804340362549,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.001298830619498911,
+  "best_metric": 1.62236487865448,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.0017317741593318816,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 4.94,
       "eval_steps_per_second": 2.47,
       "step": 75
+    },
+    {
+      "epoch": 0.00131614836109223,
+      "grad_norm": 2.4752883911132812,
+      "learning_rate": 2.9876321572751144e-05,
+      "loss": 2.0203,
+      "step": 76
+    },
+    {
+      "epoch": 0.0013334661026855488,
+      "grad_norm": 2.1483538150787354,
+      "learning_rate": 2.7557479520891104e-05,
+      "loss": 1.5806,
+      "step": 77
+    },
+    {
+      "epoch": 0.0013507838442788677,
+      "grad_norm": 1.9293116331100464,
+      "learning_rate": 2.5317852301584643e-05,
+      "loss": 2.0804,
+      "step": 78
+    },
+    {
+      "epoch": 0.0013681015858721863,
+      "grad_norm": 1.519399881362915,
+      "learning_rate": 2.315988891431412e-05,
+      "loss": 1.4393,
+      "step": 79
+    },
+    {
+      "epoch": 0.0013854193274655052,
+      "grad_norm": 1.9969561100006104,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 1.5912,
+      "step": 80
+    },
+    {
+      "epoch": 0.001402737069058824,
+      "grad_norm": 1.9334006309509277,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.5095,
+      "step": 81
+    },
+    {
+      "epoch": 0.0014200548106521429,
+      "grad_norm": 1.8917192220687866,
+      "learning_rate": 1.7199116885197995e-05,
+      "loss": 1.8712,
+      "step": 82
+    },
+    {
+      "epoch": 0.0014373725522454617,
+      "grad_norm": 1.6807430982589722,
+      "learning_rate": 1.5390474757906446e-05,
+      "loss": 1.6938,
+      "step": 83
+    },
+    {
+      "epoch": 0.0014546902938387806,
+      "grad_norm": 1.641627550125122,
+      "learning_rate": 1.3674351904242611e-05,
+      "loss": 1.5532,
+      "step": 84
+    },
+    {
+      "epoch": 0.0014720080354320992,
+      "grad_norm": 2.6051013469696045,
+      "learning_rate": 1.2052624879351104e-05,
+      "loss": 1.8125,
+      "step": 85
+    },
+    {
+      "epoch": 0.001489325777025418,
+      "grad_norm": 1.6829463243484497,
+      "learning_rate": 1.0527067017923654e-05,
+      "loss": 1.5045,
+      "step": 86
+    },
+    {
+      "epoch": 0.001506643518618737,
+      "grad_norm": 1.6704628467559814,
+      "learning_rate": 9.09934649508375e-06,
+      "loss": 1.5594,
+      "step": 87
+    },
+    {
+      "epoch": 0.0015239612602120558,
+      "grad_norm": 2.3541147708892822,
+      "learning_rate": 7.771024502261526e-06,
+      "loss": 2.2284,
+      "step": 88
+    },
+    {
+      "epoch": 0.0015412790018053746,
+      "grad_norm": 2.744718074798584,
+      "learning_rate": 6.543553540053926e-06,
+      "loss": 1.2474,
+      "step": 89
+    },
+    {
+      "epoch": 0.0015585967433986933,
+      "grad_norm": 2.3282785415649414,
+      "learning_rate": 5.418275829936537e-06,
+      "loss": 1.9081,
+      "step": 90
+    },
+    {
+      "epoch": 0.0015759144849920121,
+      "grad_norm": 1.7221317291259766,
+      "learning_rate": 4.3964218465642355e-06,
+      "loss": 1.5467,
+      "step": 91
+    },
+    {
+      "epoch": 0.001593232226585331,
+      "grad_norm": 2.2455320358276367,
+      "learning_rate": 3.4791089722651436e-06,
+      "loss": 1.8693,
+      "step": 92
+    },
+    {
+      "epoch": 0.0016105499681786498,
+      "grad_norm": 1.896304726600647,
+      "learning_rate": 2.667340275199426e-06,
+      "loss": 1.3848,
+      "step": 93
+    },
+    {
+      "epoch": 0.0016278677097719687,
+      "grad_norm": 2.8605098724365234,
+      "learning_rate": 1.9620034125190644e-06,
+      "loss": 1.6698,
+      "step": 94
+    },
+    {
+      "epoch": 0.0016451854513652876,
+      "grad_norm": 1.6910480260849,
+      "learning_rate": 1.3638696597277679e-06,
+      "loss": 1.4249,
+      "step": 95
+    },
+    {
+      "epoch": 0.0016625031929586062,
+      "grad_norm": 3.1670644283294678,
+      "learning_rate": 8.735930673024806e-07,
+      "loss": 1.7864,
+      "step": 96
+    },
+    {
+      "epoch": 0.001679820934551925,
+      "grad_norm": 2.209742784500122,
+      "learning_rate": 4.917097454988584e-07,
+      "loss": 1.7708,
+      "step": 97
+    },
+    {
+      "epoch": 0.001697138676145244,
+      "grad_norm": 2.015029191970825,
+      "learning_rate": 2.1863727812254653e-07,
+      "loss": 1.471,
+      "step": 98
+    },
+    {
+      "epoch": 0.0017144564177385628,
+      "grad_norm": 2.405651569366455,
+      "learning_rate": 5.467426590739511e-08,
+      "loss": 1.6094,
+      "step": 99
+    },
+    {
+      "epoch": 0.0017317741593318816,
+      "grad_norm": 4.6894025802612305,
+      "learning_rate": 0.0,
+      "loss": 2.0444,
+      "step": 100
+    },
+    {
+      "epoch": 0.0017317741593318816,
+      "eval_loss": 1.62236487865448,
+      "eval_runtime": 4922.5195,
+      "eval_samples_per_second": 4.939,
+      "eval_steps_per_second": 2.47,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.13570923757568e+16,
+  "total_flos": 5.51427898343424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null