Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:345324c01e603c3118e880adf57e170f07462d781f2cd0f824a184edd15de965
+oid sha256:b1bf82de85afffebb6eecbca557ae607cd3295ba4f64e66ff708a5776872d4ff
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a61708154ce18afcccae1233165e0112d9328b95d7bf510df0890a02556b1c0
+oid sha256:67b49cc73333a06e8c05430caa0ee9aad8d4a4cf8df375fdc12704355b4da875
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0121bcf22939a0ba55abb82e8db3b1e4947607644e27af068146bf50932b5af
+oid sha256:f0e749722f6b264e9e7ac135b3c9b509ac3b12588108c07978891fd2cb18ce91
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee37cbe17e000153446b008f8a0c9b7858589cefce0dc9cce432e2ac2bf7ee32
+oid sha256:88b8b5e24d97718cd4b0207f3b7dc7f0e7b1a5573e7256d921db0654a52c901c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b1c088a108c3e3eb639ec74e7a7334c93f7e412ff8c260fee9e9baed84abd4
+oid sha256:a86618d8925c69704f73a197dfce732c86f342084806a01889473cf33aba76a4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe186a7c1995beaf5b36885042915cf3378e9671d2b40b20fc9c439f6fe1603
+oid sha256:d83103cb11397e0f528e1fd63f6e0d930b05b6566b6282d491eed6c65a53b6a2
 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": 2.9354588985443115,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09746588693957114,
+  "best_metric": 2.859468698501587,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1949317738791423,
   "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": 28.425,
       "eval_steps_per_second": 7.39,
       "step": 25
+    },
+    {
+      "epoch": 0.10136452241715399,
+      "grad_norm": 0.28435713052749634,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.7583,
+      "step": 26
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.3302833139896393,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.7186,
+      "step": 27
+    },
+    {
+      "epoch": 0.10916179337231968,
+      "grad_norm": 0.37060415744781494,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.7439,
+      "step": 28
+    },
+    {
+      "epoch": 0.11306042884990253,
+      "grad_norm": 0.37979695200920105,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.7777,
+      "step": 29
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "grad_norm": 0.36751940846443176,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.719,
+      "step": 30
+    },
+    {
+      "epoch": 0.12085769980506822,
+      "grad_norm": 0.3829987943172455,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.7896,
+      "step": 31
+    },
+    {
+      "epoch": 0.12475633528265107,
+      "grad_norm": 0.4021106958389282,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.731,
+      "step": 32
+    },
+    {
+      "epoch": 0.1286549707602339,
+      "grad_norm": 0.44854679703712463,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.7024,
+      "step": 33
+    },
+    {
+      "epoch": 0.13255360623781676,
+      "grad_norm": 0.49962687492370605,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.7642,
+      "step": 34
+    },
+    {
+      "epoch": 0.1364522417153996,
+      "grad_norm": 0.5894955992698669,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.7013,
+      "step": 35
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 0.7012891173362732,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.7387,
+      "step": 36
+    },
+    {
+      "epoch": 0.1442495126705653,
+      "grad_norm": 1.5239250659942627,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.2031,
+      "step": 37
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.5231661796569824,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.7886,
+      "step": 38
+    },
+    {
+      "epoch": 0.15204678362573099,
+      "grad_norm": 0.3127061128616333,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.6986,
+      "step": 39
+    },
+    {
+      "epoch": 0.15594541910331383,
+      "grad_norm": 0.30186259746551514,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.7358,
+      "step": 40
+    },
+    {
+      "epoch": 0.15984405458089668,
+      "grad_norm": 0.32524609565734863,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.7544,
+      "step": 41
+    },
+    {
+      "epoch": 0.16374269005847952,
+      "grad_norm": 0.3468033969402313,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.8003,
+      "step": 42
+    },
+    {
+      "epoch": 0.16764132553606237,
+      "grad_norm": 0.35150423645973206,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.7102,
+      "step": 43
+    },
+    {
+      "epoch": 0.17153996101364521,
+      "grad_norm": 0.36665645241737366,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.7094,
+      "step": 44
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.3968718945980072,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.6526,
+      "step": 45
+    },
+    {
+      "epoch": 0.1793372319688109,
+      "grad_norm": 0.44515466690063477,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.725,
+      "step": 46
+    },
+    {
+      "epoch": 0.18323586744639375,
+      "grad_norm": 0.488920658826828,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.739,
+      "step": 47
+    },
+    {
+      "epoch": 0.1871345029239766,
+      "grad_norm": 0.6259700059890747,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.8396,
+      "step": 48
+    },
+    {
+      "epoch": 0.19103313840155944,
+      "grad_norm": 0.9088934659957886,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.5351,
+      "step": 49
+    },
+    {
+      "epoch": 0.1949317738791423,
+      "grad_norm": 4.3960280418396,
+      "learning_rate": 1e-05,
+      "loss": 2.3839,
+      "step": 50
+    },
+    {
+      "epoch": 0.1949317738791423,
+      "eval_loss": 2.859468698501587,
+      "eval_runtime": 1.7859,
+      "eval_samples_per_second": 27.997,
+      "eval_steps_per_second": 7.279,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null