Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85d3174a04571c7f2186222486d972c2516092500f373b7b10a305fc8f22b152
+oid sha256:0251d7cd096edfae39026cac7cfdad2b0827a127e53284c813eeb30f74095237
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24528615853c4e517fa9d0824ee6d7e5d92c9753e1f6f5abfb74d2c9d4b249e7
+oid sha256:47d2b1e19662489de2f08a8770810f604e8cfa132fdcc999f70c6b3fbc57abbb
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e27d2fdb17a5dd88adab61a1b3f4228092d7b2c636b8553f37dc9cece8444a9
+oid sha256:88bf23645dfac1688a9ad0207a3d71e99b6dd7981f13e9ca9fedb0fcd332da97
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:038704a59189d5aaf48dabbbaa65fc09777e0a5606f4c0d940f1ec3ade7746f9
+oid sha256:0c813ff53f3312b89acb50706c87a501faedd23a7992bf9a62a3f1a06768dcc3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:147a6d2e52905d3ea3cb886964177dcc1fd867019590c7ea2b0acedc4fc5c58b
+oid sha256:5bbe38e49c1f66cd2f7ca145c73481e15873d8906a369a1299856a29078e78b8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b638beaf4cda6a6ae056c790d6062ebab45cfd3c2d1267ae58c7fa7034184504
+oid sha256:0e5368a1ee3bec2d5f4b60b8bf4ac2989a2049570f1489612df021c39df7debd
 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": 2.1521599292755127,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.020300446609825416,
+  "best_metric": 2.078681707382202,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04060089321965083,
   "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": 14.371,
       "eval_steps_per_second": 3.736,
       "step": 25
+    },
+    {
+      "epoch": 0.021112464474218433,
+      "grad_norm": 0.6315709948539734,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.457,
+      "step": 26
+    },
+    {
+      "epoch": 0.02192448233861145,
+      "grad_norm": 0.5546303987503052,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.2939,
+      "step": 27
+    },
+    {
+      "epoch": 0.022736500203004467,
+      "grad_norm": 0.5207832455635071,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.1513,
+      "step": 28
+    },
+    {
+      "epoch": 0.023548518067397484,
+      "grad_norm": 0.511827290058136,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.0922,
+      "step": 29
+    },
+    {
+      "epoch": 0.024360535931790498,
+      "grad_norm": 0.47535425424575806,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.0867,
+      "step": 30
+    },
+    {
+      "epoch": 0.025172553796183515,
+      "grad_norm": 0.5138943791389465,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.1385,
+      "step": 31
+    },
+    {
+      "epoch": 0.025984571660576532,
+      "grad_norm": 0.568745493888855,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.1733,
+      "step": 32
+    },
+    {
+      "epoch": 0.02679658952496955,
+      "grad_norm": 0.6428608894348145,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.1206,
+      "step": 33
+    },
+    {
+      "epoch": 0.027608607389362567,
+      "grad_norm": 0.6441438794136047,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.1233,
+      "step": 34
+    },
+    {
+      "epoch": 0.028420625253755584,
+      "grad_norm": 0.6346638202667236,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.1293,
+      "step": 35
+    },
+    {
+      "epoch": 0.029232643118148598,
+      "grad_norm": 0.6601185202598572,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.0685,
+      "step": 36
+    },
+    {
+      "epoch": 0.030044660982541615,
+      "grad_norm": 0.7575770020484924,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.1927,
+      "step": 37
+    },
+    {
+      "epoch": 0.030856678846934632,
+      "grad_norm": 0.4314456284046173,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.394,
+      "step": 38
+    },
+    {
+      "epoch": 0.031668696711327646,
+      "grad_norm": 0.4646899104118347,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.3228,
+      "step": 39
+    },
+    {
+      "epoch": 0.032480714575720666,
+      "grad_norm": 0.5209022760391235,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.2017,
+      "step": 40
+    },
+    {
+      "epoch": 0.03329273244011368,
+      "grad_norm": 0.5574424266815186,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.0931,
+      "step": 41
+    },
+    {
+      "epoch": 0.0341047503045067,
+      "grad_norm": 0.5595993995666504,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.0513,
+      "step": 42
+    },
+    {
+      "epoch": 0.034916768168899714,
+      "grad_norm": 0.5162716507911682,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.067,
+      "step": 43
+    },
+    {
+      "epoch": 0.035728786033292735,
+      "grad_norm": 0.5021359324455261,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.0076,
+      "step": 44
+    },
+    {
+      "epoch": 0.03654080389768575,
+      "grad_norm": 0.4660208821296692,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.0467,
+      "step": 45
+    },
+    {
+      "epoch": 0.03735282176207876,
+      "grad_norm": 0.4938836395740509,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.008,
+      "step": 46
+    },
+    {
+      "epoch": 0.03816483962647178,
+      "grad_norm": 0.49616798758506775,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.1064,
+      "step": 47
+    },
+    {
+      "epoch": 0.0389768574908648,
+      "grad_norm": 0.585048496723175,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.0985,
+      "step": 48
+    },
+    {
+      "epoch": 0.03978887535525782,
+      "grad_norm": 0.6445486545562744,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.075,
+      "step": 49
+    },
+    {
+      "epoch": 0.04060089321965083,
+      "grad_norm": 0.948281466960907,
+      "learning_rate": 1e-05,
+      "loss": 2.1762,
+      "step": 50
+    },
+    {
+      "epoch": 0.04060089321965083,
+      "eval_loss": 2.078681707382202,
+      "eval_runtime": 3.4922,
+      "eval_samples_per_second": 14.318,
+      "eval_steps_per_second": 3.723,
+      "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": 3.0082871460049715e+17,
+  "total_flos": 6.024034403242476e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null