Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b87b845f869a3e28140b23b6aed13a56e4555771c4ff5de9a2c7397a7571365
+oid sha256:97ace1ae4534dfce6f8a1da861f0b5cb8393db250586db704c85190f7b26a5d3
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4307b0deb9f09a6a4478684d581a945e481a2f507c3adea1c3d7cb9d8c48ecc4
+oid sha256:6b0495df8aae0d308276452722af31d843356970c9ac1efca8195b6324ae3e8c
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdb4ead5fc24a5f412ddcefd63e0cf7f5963d0109059d04a1141f6698ae90507
+oid sha256:aeb993afd7d86d37619a166c14d0c09204156979472dd61566ff1c223913dda7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7cd8242bce343b58afc69a71f9669f0f3d2f095acfec3819758117335beb19
+oid sha256:70dad106f69b9081c87dc0d31fe31130a051063d176115f6276e70594d668489
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3badb95fb973c442be6eb2f8ebc320bf2b5626cb95cd429b5869148297d81103
+oid sha256:b98743212a74c4df92777c14ea2081f25a0ec96d4a27201f92695333ced4b516
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c540cc21308fee70881d32c864847b5dc9f18df214a3cb889e186ffc50e7791
+oid sha256:393061e2a59449af0d66039cda5a0668b0e4966eae1b42dc9bd712a727cc46e4
 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": 11.764338493347168,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3629764065335753,
+  "best_metric": 11.762595176696777,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7259528130671506,
   "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": 323.82,
       "eval_steps_per_second": 84.193,
       "step": 25
+    },
+    {
+      "epoch": 0.37749546279491836,
+      "grad_norm": 0.03273957595229149,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.7629,
+      "step": 26
+    },
+    {
+      "epoch": 0.39201451905626133,
+      "grad_norm": 0.03591519221663475,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7638,
+      "step": 27
+    },
+    {
+      "epoch": 0.40653357531760437,
+      "grad_norm": 0.03769417852163315,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7638,
+      "step": 28
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.03959864750504494,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7632,
+      "step": 29
+    },
+    {
+      "epoch": 0.4355716878402904,
+      "grad_norm": 0.0384114570915699,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.7634,
+      "step": 30
+    },
+    {
+      "epoch": 0.4500907441016334,
+      "grad_norm": 0.043950121849775314,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.7624,
+      "step": 31
+    },
+    {
+      "epoch": 0.4646098003629764,
+      "grad_norm": 0.0419909842312336,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.763,
+      "step": 32
+    },
+    {
+      "epoch": 0.4791288566243194,
+      "grad_norm": 0.049478158354759216,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.7621,
+      "step": 33
+    },
+    {
+      "epoch": 0.49364791288566245,
+      "grad_norm": 0.05043622851371765,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.7621,
+      "step": 34
+    },
+    {
+      "epoch": 0.5081669691470054,
+      "grad_norm": 0.054947227239608765,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.7627,
+      "step": 35
+    },
+    {
+      "epoch": 0.5226860254083484,
+      "grad_norm": 0.04828513413667679,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7625,
+      "step": 36
+    },
+    {
+      "epoch": 0.5372050816696915,
+      "grad_norm": 0.053075019270181656,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.763,
+      "step": 37
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.039661288261413574,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.7631,
+      "step": 38
+    },
+    {
+      "epoch": 0.5662431941923775,
+      "grad_norm": 0.0446428544819355,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.7629,
+      "step": 39
+    },
+    {
+      "epoch": 0.5807622504537205,
+      "grad_norm": 0.04789067059755325,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.762,
+      "step": 40
+    },
+    {
+      "epoch": 0.5952813067150635,
+      "grad_norm": 0.044995371252298355,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.7621,
+      "step": 41
+    },
+    {
+      "epoch": 0.6098003629764065,
+      "grad_norm": 0.048021722584962845,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7626,
+      "step": 42
+    },
+    {
+      "epoch": 0.6243194192377496,
+      "grad_norm": 0.04975919798016548,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.7628,
+      "step": 43
+    },
+    {
+      "epoch": 0.6388384754990926,
+      "grad_norm": 0.05071737989783287,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.7614,
+      "step": 44
+    },
+    {
+      "epoch": 0.6533575317604355,
+      "grad_norm": 0.05162530392408371,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.7615,
+      "step": 45
+    },
+    {
+      "epoch": 0.6678765880217786,
+      "grad_norm": 0.05929640680551529,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.7618,
+      "step": 46
+    },
+    {
+      "epoch": 0.6823956442831216,
+      "grad_norm": 0.0559273362159729,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.7615,
+      "step": 47
+    },
+    {
+      "epoch": 0.6969147005444646,
+      "grad_norm": 0.06553119421005249,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7608,
+      "step": 48
+    },
+    {
+      "epoch": 0.7114337568058077,
+      "grad_norm": 0.06088912487030029,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.7609,
+      "step": 49
+    },
+    {
+      "epoch": 0.7259528130671506,
+      "grad_norm": 0.056244444102048874,
+      "learning_rate": 1e-05,
+      "loss": 11.7624,
+      "step": 50
+    },
+    {
+      "epoch": 0.7259528130671506,
+      "eval_loss": 11.762595176696777,
+      "eval_runtime": 0.1679,
+      "eval_samples_per_second": 297.873,
+      "eval_steps_per_second": 77.447,
+      "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": 85937793531904.0,
+  "total_flos": 171619514318848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null