Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61953bf87007612f526190d60d420759ca3bca80a428d55631c4c8e65f066b15
+oid sha256:8e22e8670f08a48ee91a9d2b17c34622147a4ca269479729190179a9079bff12
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e59148d5646527adeb13496883259f0fd792ec3f3512b1444a792912a5ed8d
+oid sha256:c70853287b33fb4594376e57669b76064d9b17d39e4c2943bd7f874b7ab451b0
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db4592d261f39fb6a0ed73269d82da2bf09d18fe57e19113ef7f75b5a6f7da5e
+oid sha256:1a3549ddf5b3cc41a86b409756485f9107cfb16b31d815b7131e12162d3f3fba
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:979ffd0d398a69b3c5c003f4b72e32ac96f1abed6dfdb57c8904d3f1bc1dd143
+oid sha256:29bd001a9daa5f48a23e66163e7523a3b07f80401d1fb3681785bc3638904b1c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:856460b31fcd589a1434ed503497bfad6c1994e7031367989aff2211d70ae807
+oid sha256:c1a883a130f7f7d6f0ad426e39e022919f289b9b56c1ec57ff28d539329fc289
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783a50b06e874f37590067bd113307bf423af8fe94fc1a9bb5ce2db765727025
+oid sha256:a3492ca94267cb973cb7ac128a3106408e80588d99c2d183a436115d7217a8ea
 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": 2.4509410858154297,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012486732846350752,
+  "best_metric": 2.378668785095215,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.024973465692701504,
   "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": 24.135,
       "eval_steps_per_second": 6.275,
       "step": 25
+    },
+    {
+      "epoch": 0.012986202160204782,
+      "grad_norm": 0.6144657731056213,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.4403,
+      "step": 26
+    },
+    {
+      "epoch": 0.013485671474058812,
+      "grad_norm": 0.6540758013725281,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.546,
+      "step": 27
+    },
+    {
+      "epoch": 0.013985140787912843,
+      "grad_norm": 0.6950146555900574,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.5025,
+      "step": 28
+    },
+    {
+      "epoch": 0.014484610101766873,
+      "grad_norm": 0.7563838958740234,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.4834,
+      "step": 29
+    },
+    {
+      "epoch": 0.014984079415620903,
+      "grad_norm": 0.63536536693573,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.4584,
+      "step": 30
+    },
+    {
+      "epoch": 0.015483548729474933,
+      "grad_norm": 0.6436273455619812,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.516,
+      "step": 31
+    },
+    {
+      "epoch": 0.015983018043328964,
+      "grad_norm": 0.5594193935394287,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.3996,
+      "step": 32
+    },
+    {
+      "epoch": 0.016482487357182992,
+      "grad_norm": 0.566197395324707,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.4535,
+      "step": 33
+    },
+    {
+      "epoch": 0.016981956671037024,
+      "grad_norm": 0.5854701995849609,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.402,
+      "step": 34
+    },
+    {
+      "epoch": 0.017481425984891052,
+      "grad_norm": 0.6294066309928894,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.4151,
+      "step": 35
+    },
+    {
+      "epoch": 0.017980895298745084,
+      "grad_norm": 0.7285234928131104,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.5356,
+      "step": 36
+    },
+    {
+      "epoch": 0.018480364612599113,
+      "grad_norm": 0.8491204380989075,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.5543,
+      "step": 37
+    },
+    {
+      "epoch": 0.018979833926453145,
+      "grad_norm": 0.5609738826751709,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.4468,
+      "step": 38
+    },
+    {
+      "epoch": 0.019479303240307173,
+      "grad_norm": 0.41892126202583313,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.5609,
+      "step": 39
+    },
+    {
+      "epoch": 0.019978772554161205,
+      "grad_norm": 0.47660011053085327,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.4739,
+      "step": 40
+    },
+    {
+      "epoch": 0.020478241868015234,
+      "grad_norm": 0.44640839099884033,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.4056,
+      "step": 41
+    },
+    {
+      "epoch": 0.020977711181869262,
+      "grad_norm": 0.5215767025947571,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.4235,
+      "step": 42
+    },
+    {
+      "epoch": 0.021477180495723294,
+      "grad_norm": 0.45160433650016785,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.4484,
+      "step": 43
+    },
+    {
+      "epoch": 0.021976649809577323,
+      "grad_norm": 0.4752783179283142,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.4746,
+      "step": 44
+    },
+    {
+      "epoch": 0.022476119123431355,
+      "grad_norm": 0.5033553838729858,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.3887,
+      "step": 45
+    },
+    {
+      "epoch": 0.022975588437285383,
+      "grad_norm": 0.6489120125770569,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.2315,
+      "step": 46
+    },
+    {
+      "epoch": 0.023475057751139415,
+      "grad_norm": 0.5699940919876099,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.3659,
+      "step": 47
+    },
+    {
+      "epoch": 0.023974527064993444,
+      "grad_norm": 0.5970814228057861,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.34,
+      "step": 48
+    },
+    {
+      "epoch": 0.024473996378847476,
+      "grad_norm": 0.7270641326904297,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.5688,
+      "step": 49
+    },
+    {
+      "epoch": 0.024973465692701504,
+      "grad_norm": 1.1712040901184082,
+      "learning_rate": 1e-05,
+      "loss": 2.6233,
+      "step": 50
+    },
+    {
+      "epoch": 0.024973465692701504,
+      "eval_loss": 2.378668785095215,
+      "eval_runtime": 2.0785,
+      "eval_samples_per_second": 24.056,
+      "eval_steps_per_second": 6.255,
+      "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": 8.129122235790131e+16,
+  "total_flos": 1.625316696124293e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null