Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e8dbce7aad02405fe8fabe1559911b8f26f929c3fdabc9dbdd17039fd4a3b6
+oid sha256:b26bf245c06c4725608a67574a8366856f7769caf8048ae734c32129a9c71ab2
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f86f20ec1ec1918883a755fa401dbda9dcdb408b5238494f96ca06b4ec8c0e4
+oid sha256:8b19e52dd143e6af8cfd11f19a7d01712860ce1b4f83d905176f49115562770e
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:859a89733a0f19db48e79aae86660d0420c9d31b3b6976e03d7e9111b6126889
+oid sha256:5a778c3d3993a96084c802d9d59bfe215c97dab181335161ad04bdbc6b414588
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9900db17e6e4fc13aa494320972e17c34bdbc2b175d7b26ac407b71a71a506
+oid sha256:215045760bb10458c36ff879e589cf673f5363d67ac86c453f1435924909145c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291111ce5b4e341d3a6141411c95058559bea8287b3b45b3594d68ada42bcd9b
+oid sha256:8302e9ac496c13897f2c4a9fd190e4882b1eb0f431e2047ab3a12bc980261ca0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c1c00f49142280d24edaaf013d27865244a29ddd6f2cebc8a6f72bbf1a9aabf
+oid sha256:489f29702e3b9c3a96a1a37289986d1bdd60c6a2ba12c194c6ab89942e733951
 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": 0.0008296275627799332,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5979073243647235,
+  "best_metric": 0.0002391961170360446,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2062780269058295,
   "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": 11.088,
       "eval_steps_per_second": 2.883,
       "step": 25
+    },
+    {
+      "epoch": 0.6218236173393124,
+      "grad_norm": 0.012360863387584686,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0005,
+      "step": 26
+    },
+    {
+      "epoch": 0.6457399103139013,
+      "grad_norm": 0.030168309807777405,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.001,
+      "step": 27
+    },
+    {
+      "epoch": 0.6696562032884903,
+      "grad_norm": 0.01952563412487507,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0006,
+      "step": 28
+    },
+    {
+      "epoch": 0.6935724962630793,
+      "grad_norm": 0.025816479697823524,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0001,
+      "step": 29
+    },
+    {
+      "epoch": 0.7174887892376681,
+      "grad_norm": 0.023305699229240417,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0003,
+      "step": 30
+    },
+    {
+      "epoch": 0.7414050822122571,
+      "grad_norm": 0.042270027101039886,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.004,
+      "step": 31
+    },
+    {
+      "epoch": 0.7653213751868461,
+      "grad_norm": 0.013639895245432854,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0011,
+      "step": 32
+    },
+    {
+      "epoch": 0.7892376681614349,
+      "grad_norm": 0.015320922248065472,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0009,
+      "step": 33
+    },
+    {
+      "epoch": 0.8131539611360239,
+      "grad_norm": 0.017550518736243248,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0004,
+      "step": 34
+    },
+    {
+      "epoch": 0.8370702541106129,
+      "grad_norm": 0.018104810267686844,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0007,
+      "step": 35
+    },
+    {
+      "epoch": 0.8609865470852018,
+      "grad_norm": 0.024184156209230423,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0011,
+      "step": 36
+    },
+    {
+      "epoch": 0.8849028400597907,
+      "grad_norm": 0.026356741786003113,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.001,
+      "step": 37
+    },
+    {
+      "epoch": 0.9088191330343797,
+      "grad_norm": 0.014368100091814995,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0003,
+      "step": 38
+    },
+    {
+      "epoch": 0.9327354260089686,
+      "grad_norm": 0.01398097537457943,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0003,
+      "step": 39
+    },
+    {
+      "epoch": 0.9566517189835575,
+      "grad_norm": 0.01466523390263319,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0001,
+      "step": 40
+    },
+    {
+      "epoch": 0.9805680119581465,
+      "grad_norm": 0.014875360764563084,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0002,
+      "step": 41
+    },
+    {
+      "epoch": 1.014947683109118,
+      "grad_norm": 0.02478068880736828,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0065,
+      "step": 42
+    },
+    {
+      "epoch": 1.038863976083707,
+      "grad_norm": 0.009487264789640903,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0005,
+      "step": 43
+    },
+    {
+      "epoch": 1.062780269058296,
+      "grad_norm": 0.010159480385482311,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0004,
+      "step": 44
+    },
+    {
+      "epoch": 1.086696562032885,
+      "grad_norm": 0.009533469565212727,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0003,
+      "step": 45
+    },
+    {
+      "epoch": 1.1106128550074739,
+      "grad_norm": 0.008421096950769424,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0002,
+      "step": 46
+    },
+    {
+      "epoch": 1.1345291479820627,
+      "grad_norm": 0.00984017550945282,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0003,
+      "step": 47
+    },
+    {
+      "epoch": 1.1584454409566518,
+      "grad_norm": 0.014092501252889633,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0002,
+      "step": 48
+    },
+    {
+      "epoch": 1.1823617339312407,
+      "grad_norm": 0.003745349822565913,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0001,
+      "step": 49
+    },
+    {
+      "epoch": 1.2062780269058295,
+      "grad_norm": 0.0038105223793536425,
+      "learning_rate": 1e-05,
+      "loss": 0.0001,
+      "step": 50
+    },
+    {
+      "epoch": 1.2062780269058295,
+      "eval_loss": 0.0002391961170360446,
+      "eval_runtime": 4.1649,
+      "eval_samples_per_second": 12.005,
+      "eval_steps_per_second": 3.121,
+      "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": 3.390293917554442e+17,
+  "total_flos": 6.757792457246638e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null