Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b43af1ccbca611f872e810bc129355167f394af1b37909766ee514056703e96
+oid sha256:93cb1dd577a078e2abd78e88c0c3870146a9697e38d54c3fe09add3ce54202cb
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d690728189c9379020bce4a1a41b475c40b78f25ab59ed75181db13084ed40
+oid sha256:f39f05e9c35c3f045509ccd105fadd04c719eddac0d31f0953ec3ea65ac882c8
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b13d2a262ae04cdd505ced2ea807a1fd55c67648ff903ac8d42cf36817e8053
+oid sha256:0098e2ab0dc46afbc5ab7456e005dcce055855070a460f660747c402ff22aa8d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb75f3332443612e49b3a96df4d1d5b04a15460eea23b156d854ab3d6884310c
+oid sha256:729ca0f94e4f17bac9a044c6c20e3e557674ce151d8bcb2b153bcb52255bace2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bacf65e11e697ead6e8633da2b9d28c30441cdb6fe19647c82a15939e6e855b0
+oid sha256:45735c1ae4a233ff5a140d7d5ffe699a47c3cdd14b45a056318150f89a7d70ff
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4560ae5ee28ea6b1dbf97ac080d88bfbedc3882e80f05e21765702a17950309f
+oid sha256:c1a5ec3dde52cc9ca8b0ee1b12b519c2de762f296115b061666e7c818f949fcf
 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": 1.9283413887023926,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07955449482895784,
+  "best_metric": 1.695253610610962,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15910898965791567,
   "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": 9.579,
       "eval_steps_per_second": 2.49,
       "step": 25
+    },
+    {
+      "epoch": 0.08273667462211615,
+      "grad_norm": 0.9890863299369812,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5639,
+      "step": 26
+    },
+    {
+      "epoch": 0.08591885441527446,
+      "grad_norm": 1.1323376893997192,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.6863,
+      "step": 27
+    },
+    {
+      "epoch": 0.08910103420843278,
+      "grad_norm": 1.1532118320465088,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.7062,
+      "step": 28
+    },
+    {
+      "epoch": 0.09228321400159109,
+      "grad_norm": 1.093669056892395,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.6431,
+      "step": 29
+    },
+    {
+      "epoch": 0.0954653937947494,
+      "grad_norm": 1.0816657543182373,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.679,
+      "step": 30
+    },
+    {
+      "epoch": 0.09864757358790771,
+      "grad_norm": 1.047154426574707,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.6926,
+      "step": 31
+    },
+    {
+      "epoch": 0.10182975338106603,
+      "grad_norm": 1.1764827966690063,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.6937,
+      "step": 32
+    },
+    {
+      "epoch": 0.10501193317422435,
+      "grad_norm": 1.2118390798568726,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.667,
+      "step": 33
+    },
+    {
+      "epoch": 0.10819411296738266,
+      "grad_norm": 1.363329529762268,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.6462,
+      "step": 34
+    },
+    {
+      "epoch": 0.11137629276054097,
+      "grad_norm": 1.6293692588806152,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.6374,
+      "step": 35
+    },
+    {
+      "epoch": 0.11455847255369929,
+      "grad_norm": 1.8759685754776,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6814,
+      "step": 36
+    },
+    {
+      "epoch": 0.1177406523468576,
+      "grad_norm": 2.436602830886841,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.7842,
+      "step": 37
+    },
+    {
+      "epoch": 0.12092283214001591,
+      "grad_norm": 0.9495934844017029,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.4062,
+      "step": 38
+    },
+    {
+      "epoch": 0.12410501193317422,
+      "grad_norm": 0.7878849506378174,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.4344,
+      "step": 39
+    },
+    {
+      "epoch": 0.12728719172633254,
+      "grad_norm": 0.9332970380783081,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5444,
+      "step": 40
+    },
+    {
+      "epoch": 0.13046937151949084,
+      "grad_norm": 0.9588786959648132,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.5308,
+      "step": 41
+    },
+    {
+      "epoch": 0.13365155131264916,
+      "grad_norm": 0.9794378280639648,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.5138,
+      "step": 42
+    },
+    {
+      "epoch": 0.1368337311058075,
+      "grad_norm": 1.015647053718567,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.5075,
+      "step": 43
+    },
+    {
+      "epoch": 0.14001591089896578,
+      "grad_norm": 1.1811518669128418,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.6297,
+      "step": 44
+    },
+    {
+      "epoch": 0.1431980906921241,
+      "grad_norm": 1.2114378213882446,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.6206,
+      "step": 45
+    },
+    {
+      "epoch": 0.14638027048528243,
+      "grad_norm": 1.3410520553588867,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.6143,
+      "step": 46
+    },
+    {
+      "epoch": 0.14956245027844073,
+      "grad_norm": 1.5326932668685913,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.5577,
+      "step": 47
+    },
+    {
+      "epoch": 0.15274463007159905,
+      "grad_norm": 1.7534153461456299,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.6193,
+      "step": 48
+    },
+    {
+      "epoch": 0.15592680986475735,
+      "grad_norm": 2.285520076751709,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.6998,
+      "step": 49
+    },
+    {
+      "epoch": 0.15910898965791567,
+      "grad_norm": 3.172696590423584,
+      "learning_rate": 1e-05,
+      "loss": 1.851,
+      "step": 50
+    },
+    {
+      "epoch": 0.15910898965791567,
+      "eval_loss": 1.695253610610962,
+      "eval_runtime": 5.2366,
+      "eval_samples_per_second": 9.548,
+      "eval_steps_per_second": 2.483,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null