Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:044be5fc4cc7d5c08dc34ddc983238c8f268095224658a99936538a9a67b7cad
+oid sha256:edff49dae6fbfa82e108524fa407bac79dc7b721abbde7c7f8e4246bbc249a12
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f161569c7ab29de49e024d2213f34084fdb688fcfa45e3871cd909c2e49ef6a
+oid sha256:141cfd9c23e36c135b178778613bbd56f8575db0f0bd2a8b0bdfb47fbe4767ad
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2f5d65f5a32bb682977b6c4356ff5f02e27d845cc88a7d963cead714c58030
+oid sha256:d90ed794fabc145ca1fe8d93ef3741dc08d83f7fb23996bdeea133ed87a57417
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebdc45a6580077d2c89265d57abc1b5a637ba473c927a51147dee937d671b89a
+oid sha256:8570e83633a9df9421a0333daa234e96e537a0f52a70020ed41595461becd121
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e87e6a5d625154cd254ca533b7a8249a10808810d83dd3f5c34a312f607e39
+oid sha256:04e04b3314f503f634e8ecd58745c1befb6b99a8f21dbad479453dbc2501be71
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4803df0f8a5cfee87c8217a5f576fcf1a427eee30d91263895b11e7718fdf0c1
+oid sha256:f303b2338d5a332fc37fec2f7c677603717c8dcc2c2cf84557e0e0fdbd96e674
 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": 0.424012690782547,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.15311004784688995,
+  "best_metric": 0.3190205991268158,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.3062200956937799,
   "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": 24.316,
       "eval_steps_per_second": 6.322,
       "step": 25
+    },
+    {
+      "epoch": 0.15923444976076556,
+      "grad_norm": 0.3771899342536926,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.2051,
+      "step": 26
+    },
+    {
+      "epoch": 0.16535885167464115,
+      "grad_norm": 0.3396134376525879,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.1877,
+      "step": 27
+    },
+    {
+      "epoch": 0.17148325358851674,
+      "grad_norm": 0.28315144777297974,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.1407,
+      "step": 28
+    },
+    {
+      "epoch": 0.17760765550239235,
+      "grad_norm": 0.5146012306213379,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1578,
+      "step": 29
+    },
+    {
+      "epoch": 0.18373205741626794,
+      "grad_norm": 0.9754877090454102,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5997,
+      "step": 30
+    },
+    {
+      "epoch": 0.18985645933014353,
+      "grad_norm": 2.0145418643951416,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.7871,
+      "step": 31
+    },
+    {
+      "epoch": 0.19598086124401914,
+      "grad_norm": 3.73909854888916,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8302,
+      "step": 32
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 1.4725128412246704,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.7317,
+      "step": 33
+    },
+    {
+      "epoch": 0.20822966507177035,
+      "grad_norm": 2.3814151287078857,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.802,
+      "step": 34
+    },
+    {
+      "epoch": 0.21435406698564594,
+      "grad_norm": 1.2523080110549927,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.6503,
+      "step": 35
+    },
+    {
+      "epoch": 0.22047846889952152,
+      "grad_norm": 1.2774503231048584,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.5147,
+      "step": 36
+    },
+    {
+      "epoch": 0.22660287081339714,
+      "grad_norm": 0.9718907475471497,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4658,
+      "step": 37
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 0.34255456924438477,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.2052,
+      "step": 38
+    },
+    {
+      "epoch": 0.23885167464114831,
+      "grad_norm": 0.3709205090999603,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1799,
+      "step": 39
+    },
+    {
+      "epoch": 0.24497607655502393,
+      "grad_norm": 0.3074520528316498,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.1566,
+      "step": 40
+    },
+    {
+      "epoch": 0.25110047846889955,
+      "grad_norm": 0.6865524649620056,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1098,
+      "step": 41
+    },
+    {
+      "epoch": 0.25722488038277513,
+      "grad_norm": 0.7394497394561768,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.2496,
+      "step": 42
+    },
+    {
+      "epoch": 0.2633492822966507,
+      "grad_norm": 1.2238065004348755,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.544,
+      "step": 43
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 1.4266135692596436,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.5695,
+      "step": 44
+    },
+    {
+      "epoch": 0.2755980861244019,
+      "grad_norm": 1.3586610555648804,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6553,
+      "step": 45
+    },
+    {
+      "epoch": 0.2817224880382775,
+      "grad_norm": 1.0930596590042114,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.5945,
+      "step": 46
+    },
+    {
+      "epoch": 0.28784688995215313,
+      "grad_norm": 1.1304785013198853,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.5402,
+      "step": 47
+    },
+    {
+      "epoch": 0.2939712918660287,
+      "grad_norm": 0.9247140288352966,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.514,
+      "step": 48
+    },
+    {
+      "epoch": 0.3000956937799043,
+      "grad_norm": 0.7985676527023315,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.359,
+      "step": 49
+    },
+    {
+      "epoch": 0.3062200956937799,
+      "grad_norm": 1.2171745300292969,
+      "learning_rate": 1e-05,
+      "loss": 0.3971,
+      "step": 50
+    },
+    {
+      "epoch": 0.3062200956937799,
+      "eval_loss": 0.3190205991268158,
+      "eval_runtime": 2.0665,
+      "eval_samples_per_second": 24.196,
+      "eval_steps_per_second": 6.291,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null