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:ab2bd5b83e4fdcb5dd7a7e6d125cc7fdb75ed8c9b26fe2a4fe872551654010a3
+oid sha256:6875314447b697f74cd89652a3c74f819b4b58f87c716a50ab9ef0990661a1cb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de7574e3363b3be041f84a1cef480df9aa945e30b7ddb37b5cd89b16f3b0944
+oid sha256:1748fc6f85a9e8ffcbc21232dd22bb53ec8747df4eb0781d8e595d5e05fc20fc
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b28d21d1a02d6dfd2de0961be4ce10cb29fd8c8b050878f9cc227b3a93b6c4e
+oid sha256:13bbf54e33ef3ed7828dcad285c092227bba16ae439a02256202a0818006526d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c91453c7a87e9b7adeecff888eb81b989c98e75395880ecbb8433defb419c72a
+oid sha256:0532ef09948c6fb5143af00955f5ac204e1e8dfa915ef8bcdf4a95d032cc87e9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6906ef9a655abb8b6bdfbc51032a996aeabacc2b5df84c695b72eb928f75605
+oid sha256:b1d6af24a755f13bdb1191c44ff5d9e2a3d418db12b062b97f47b9604d8c87f2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0cf09897ede6be7a14b2b19a6bfa75f8bf54f3abdb1ac34f3e5ee23b1bfc252
+oid sha256:4b4eb08991c7ddd9802b7ca1c2ec415c02c2686023aaa9803684e25d1b6ffe91
 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": 3.0354466438293457,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9685230024213075,
+  "best_metric": 3.0068626403808594,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9564164648910412,
   "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": 14.605,
       "eval_steps_per_second": 1.847,
       "step": 25
+    },
+    {
+      "epoch": 1.026634382566586,
+      "grad_norm": 2.9393057823181152,
+      "learning_rate": 5e-05,
+      "loss": 5.7408,
+      "step": 26
+    },
+    {
+      "epoch": 1.0653753026634383,
+      "grad_norm": 1.3096283674240112,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.135,
+      "step": 27
+    },
+    {
+      "epoch": 1.1041162227602905,
+      "grad_norm": 1.031684398651123,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.8978,
+      "step": 28
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.2637622356414795,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.9017,
+      "step": 29
+    },
+    {
+      "epoch": 1.181598062953995,
+      "grad_norm": 0.9409626722335815,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.8737,
+      "step": 30
+    },
+    {
+      "epoch": 1.2203389830508475,
+      "grad_norm": 0.982624888420105,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.819,
+      "step": 31
+    },
+    {
+      "epoch": 1.2590799031476998,
+      "grad_norm": 1.4315216541290283,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.1233,
+      "step": 32
+    },
+    {
+      "epoch": 1.297820823244552,
+      "grad_norm": 1.4830853939056396,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.335,
+      "step": 33
+    },
+    {
+      "epoch": 1.3365617433414043,
+      "grad_norm": 1.272890567779541,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.9649,
+      "step": 34
+    },
+    {
+      "epoch": 1.3753026634382566,
+      "grad_norm": 1.2674185037612915,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.9028,
+      "step": 35
+    },
+    {
+      "epoch": 1.414043583535109,
+      "grad_norm": 1.2481498718261719,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.941,
+      "step": 36
+    },
+    {
+      "epoch": 1.4527845036319613,
+      "grad_norm": 0.9147533774375916,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.7872,
+      "step": 37
+    },
+    {
+      "epoch": 1.4915254237288136,
+      "grad_norm": 1.4051660299301147,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.952,
+      "step": 38
+    },
+    {
+      "epoch": 1.5302663438256658,
+      "grad_norm": 2.065242052078247,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.4175,
+      "step": 39
+    },
+    {
+      "epoch": 1.569007263922518,
+      "grad_norm": 1.2460421323776245,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.9729,
+      "step": 40
+    },
+    {
+      "epoch": 1.6077481840193704,
+      "grad_norm": 0.9894155263900757,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.8412,
+      "step": 41
+    },
+    {
+      "epoch": 1.6464891041162226,
+      "grad_norm": 2.462437629699707,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.8047,
+      "step": 42
+    },
+    {
+      "epoch": 1.685230024213075,
+      "grad_norm": 0.9419494867324829,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.8367,
+      "step": 43
+    },
+    {
+      "epoch": 1.7239709443099274,
+      "grad_norm": 1.5156563520431519,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.7518,
+      "step": 44
+    },
+    {
+      "epoch": 1.7627118644067796,
+      "grad_norm": 1.8598206043243408,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.3659,
+      "step": 45
+    },
+    {
+      "epoch": 1.801452784503632,
+      "grad_norm": 1.3871934413909912,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.95,
+      "step": 46
+    },
+    {
+      "epoch": 1.8401937046004844,
+      "grad_norm": 1.2430062294006348,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.8985,
+      "step": 47
+    },
+    {
+      "epoch": 1.8789346246973366,
+      "grad_norm": 1.2211697101593018,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.8497,
+      "step": 48
+    },
+    {
+      "epoch": 1.917675544794189,
+      "grad_norm": 1.6619465351104736,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.8456,
+      "step": 49
+    },
+    {
+      "epoch": 1.9564164648910412,
+      "grad_norm": 0.6423755288124084,
+      "learning_rate": 0.0,
+      "loss": 2.7164,
+      "step": 50
+    },
+    {
+      "epoch": 1.9564164648910412,
+      "eval_loss": 3.0068626403808594,
+      "eval_runtime": 11.9198,
+      "eval_samples_per_second": 14.598,
+      "eval_steps_per_second": 1.846,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null