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:d2c498440e14d45573ae2b673745821291c38a0a7ca59fc7b3d1d01db4bb19f5
+oid sha256:7024ed870c72782997e257b3f7f210d326d274bab0f307a7cb323e3fd6664856
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c48fef6b2cd079ce05a0537ed3e4dc03ad5028f16fe5de151263c032fb8e2bf
+oid sha256:fad0307a24d0bc83a21a4b04d2edb8ddc18505c1478c779f719666a36f3c3095
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64c4d1e15739dd367dbfb77061f43866888ac8bc17a377a2cc3befad540fd566
+oid sha256:ccc3d373c540b6fb95e7f3c349a05075736af07874b83aa12e4a1fd4d3eb1781
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:588c1172ca2fcfc35c23a3418461f64923ca5e04d70694e286c7a7299cbf29ed
+oid sha256:87c0d8c5f4ed2d09a76407466f42c42e45f0d42176af133cde53faf29c89abee
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f020a2172ac0d2ebaea4214dab167b3f58461af7deab49eb8c9e87bf4ab13235
+oid sha256:412e34e4515af77849d5a77023e4b6f2cb115f03df1a39589c472752ed9f9ad6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb6982649eba1a563297a707313739b9db5acd91fe6c6046c0531cd0a76aa77
+oid sha256:bd7627b058432db7598c9609b104437e07edea25edae7d0b7c593ced01f41739
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.252530038356781,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12940795858945325,
+  "best_metric": 0.2419588714838028,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2588159171789065,
   "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": 34.761,
       "eval_steps_per_second": 9.038,
       "step": 25
+    },
+    {
+      "epoch": 0.13458427693303138,
+      "grad_norm": 0.06610764563083649,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.2569,
+      "step": 26
+    },
+    {
+      "epoch": 0.1397605952766095,
+      "grad_norm": 0.0721898227930069,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.2493,
+      "step": 27
+    },
+    {
+      "epoch": 0.14493691362018765,
+      "grad_norm": 0.07561353594064713,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.2764,
+      "step": 28
+    },
+    {
+      "epoch": 0.15011323196376578,
+      "grad_norm": 0.06619886308908463,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.2175,
+      "step": 29
+    },
+    {
+      "epoch": 0.1552895503073439,
+      "grad_norm": 0.07458724081516266,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.2708,
+      "step": 30
+    },
+    {
+      "epoch": 0.16046586865092202,
+      "grad_norm": 0.0770750567317009,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.2586,
+      "step": 31
+    },
+    {
+      "epoch": 0.16564218699450017,
+      "grad_norm": 0.07303706556558609,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.2312,
+      "step": 32
+    },
+    {
+      "epoch": 0.1708185053380783,
+      "grad_norm": 0.07124622166156769,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2386,
+      "step": 33
+    },
+    {
+      "epoch": 0.17599482368165642,
+      "grad_norm": 0.07879437506198883,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2524,
+      "step": 34
+    },
+    {
+      "epoch": 0.18117114202523454,
+      "grad_norm": 0.08590403199195862,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2526,
+      "step": 35
+    },
+    {
+      "epoch": 0.1863474603688127,
+      "grad_norm": 0.08869822323322296,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2401,
+      "step": 36
+    },
+    {
+      "epoch": 0.19152377871239082,
+      "grad_norm": 0.09655508399009705,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.2486,
+      "step": 37
+    },
+    {
+      "epoch": 0.19670009705596894,
+      "grad_norm": 0.042593903839588165,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.2101,
+      "step": 38
+    },
+    {
+      "epoch": 0.20187641539954707,
+      "grad_norm": 0.05090802162885666,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.262,
+      "step": 39
+    },
+    {
+      "epoch": 0.2070527337431252,
+      "grad_norm": 0.05375056713819504,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.2499,
+      "step": 40
+    },
+    {
+      "epoch": 0.21222905208670334,
+      "grad_norm": 0.05331680178642273,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.223,
+      "step": 41
+    },
+    {
+      "epoch": 0.21740537043028146,
+      "grad_norm": 0.061501894146203995,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.2438,
+      "step": 42
+    },
+    {
+      "epoch": 0.2225816887738596,
+      "grad_norm": 0.0702476054430008,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.247,
+      "step": 43
+    },
+    {
+      "epoch": 0.2277580071174377,
+      "grad_norm": 0.06131530553102493,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2211,
+      "step": 44
+    },
+    {
+      "epoch": 0.23293432546101586,
+      "grad_norm": 0.066093310713768,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.2444,
+      "step": 45
+    },
+    {
+      "epoch": 0.23811064380459399,
+      "grad_norm": 0.06885978579521179,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.2602,
+      "step": 46
+    },
+    {
+      "epoch": 0.2432869621481721,
+      "grad_norm": 0.07169124484062195,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2462,
+      "step": 47
+    },
+    {
+      "epoch": 0.24846328049175023,
+      "grad_norm": 0.08826154470443726,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.2691,
+      "step": 48
+    },
+    {
+      "epoch": 0.2536395988353284,
+      "grad_norm": 0.08812335878610611,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.2274,
+      "step": 49
+    },
+    {
+      "epoch": 0.2588159171789065,
+      "grad_norm": 0.11969379335641861,
+      "learning_rate": 1e-05,
+      "loss": 0.2547,
+      "step": 50
+    },
+    {
+      "epoch": 0.2588159171789065,
+      "eval_loss": 0.2419588714838028,
+      "eval_runtime": 1.4385,
+      "eval_samples_per_second": 34.758,
+      "eval_steps_per_second": 9.037,
+      "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": 2.8137864274169037e+17,
+  "total_flos": 5.6275728548338074e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null