Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a8252b6960a835b6a73cca5f1e39b38ef8f436a13f62024c2cc80012ef90c9
+oid sha256:883d2964689f634137daea8f481fe34b529c5a6b9752f6007384a8afbe7e738a
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6254400d599c12bff3f348d16da26b40308b53841a18c1a49381d61b41dbc0ea
+oid sha256:5b59782933813562e5679509e7fc03aded69f113ca747533011bbe6803250ffa
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6c8371fd74ad53bb467626b98e2cabda2a3aa6bfab0f88556b909596483d7b
+oid sha256:261f70f85f425bbd284f7f85527904e8cd240becbede007e863cd93833b34e73
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77863bf89357c0e938e109fc1fcac56c283db59225ab9d09a84b8cd0e7fb0913
+oid sha256:7062af04d374b0ef0b393dc0b45bd7ef83a826f57e121f27c8c8146c8cccb268
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd4439c54f436da9ae0918c219d1e42c48a0f4efdbe255fd75f66b97c33cb79
+oid sha256:1eadf4e06493c281b99965e1f7cfbf9033cb22583292ae0e283ff08e032ca4a6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14f5c3a1957ff373d173bceb44d8d6ae1300c629f1ae489c3114af852a1b9eca
+oid sha256:fae39f098ef950d3e2e74eefd6dad76699c7875cf181f7d581abd415abe95878
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2849206924438477,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.035031637948021804,
+  "best_metric": 1.26985502243042,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.05254745692203271,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 100.532,
       "eval_steps_per_second": 26.138,
       "step": 50
+    },
+    {
+      "epoch": 0.03573227070698224,
+      "grad_norm": 0.6857272386550903,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.3856,
+      "step": 51
+    },
+    {
+      "epoch": 0.03643290346594268,
+      "grad_norm": 0.8008691072463989,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 1.3073,
+      "step": 52
+    },
+    {
+      "epoch": 0.03713353622490312,
+      "grad_norm": 0.8453397750854492,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 1.2912,
+      "step": 53
+    },
+    {
+      "epoch": 0.037834168983863554,
+      "grad_norm": 0.8887794017791748,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2623,
+      "step": 54
+    },
+    {
+      "epoch": 0.03853480174282399,
+      "grad_norm": 0.9477584362030029,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 1.3305,
+      "step": 55
+    },
+    {
+      "epoch": 0.039235434501784426,
+      "grad_norm": 1.0366019010543823,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 1.2388,
+      "step": 56
+    },
+    {
+      "epoch": 0.03993606726074486,
+      "grad_norm": 1.0282713174819946,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.2277,
+      "step": 57
+    },
+    {
+      "epoch": 0.0406367000197053,
+      "grad_norm": 1.2580724954605103,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 1.3221,
+      "step": 58
+    },
+    {
+      "epoch": 0.041337332778665734,
+      "grad_norm": 1.2110230922698975,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 1.3361,
+      "step": 59
+    },
+    {
+      "epoch": 0.04203796553762617,
+      "grad_norm": 1.372668743133545,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.2663,
+      "step": 60
+    },
+    {
+      "epoch": 0.042738598296586605,
+      "grad_norm": 1.3554086685180664,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 1.196,
+      "step": 61
+    },
+    {
+      "epoch": 0.04343923105554704,
+      "grad_norm": 1.7051923274993896,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 1.0735,
+      "step": 62
+    },
+    {
+      "epoch": 0.04413986381450748,
+      "grad_norm": 0.7950019240379333,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2806,
+      "step": 63
+    },
+    {
+      "epoch": 0.04484049657346791,
+      "grad_norm": 0.7287315726280212,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 1.3186,
+      "step": 64
+    },
+    {
+      "epoch": 0.04554112933242835,
+      "grad_norm": 0.7858335375785828,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 1.285,
+      "step": 65
+    },
+    {
+      "epoch": 0.046241762091388784,
+      "grad_norm": 0.8817285299301147,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2665,
+      "step": 66
+    },
+    {
+      "epoch": 0.04694239485034922,
+      "grad_norm": 0.8588771224021912,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 1.2035,
+      "step": 67
+    },
+    {
+      "epoch": 0.047643027609309656,
+      "grad_norm": 0.9993865489959717,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 1.2994,
+      "step": 68
+    },
+    {
+      "epoch": 0.04834366036827009,
+      "grad_norm": 1.0302021503448486,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2741,
+      "step": 69
+    },
+    {
+      "epoch": 0.04904429312723053,
+      "grad_norm": 1.016481876373291,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 1.1815,
+      "step": 70
+    },
+    {
+      "epoch": 0.04974492588619096,
+      "grad_norm": 1.1564722061157227,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 1.1741,
+      "step": 71
+    },
+    {
+      "epoch": 0.0504455586451514,
+      "grad_norm": 1.3200898170471191,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.2825,
+      "step": 72
+    },
+    {
+      "epoch": 0.05114619140411184,
+      "grad_norm": 1.399703860282898,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 1.2678,
+      "step": 73
+    },
+    {
+      "epoch": 0.05184682416307228,
+      "grad_norm": 1.51980459690094,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 1.2508,
+      "step": 74
+    },
+    {
+      "epoch": 0.05254745692203271,
+      "grad_norm": 2.086326837539673,
+      "learning_rate": 1e-05,
+      "loss": 0.9637,
+      "step": 75
+    },
+    {
+      "epoch": 0.05254745692203271,
+      "eval_loss": 1.26985502243042,
+      "eval_runtime": 0.5009,
+      "eval_samples_per_second": 99.826,
+      "eval_steps_per_second": 25.955,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.95300912644096e+16,
+  "total_flos": 4.42951368966144e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null