Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046722a4c51f9c54a501bd13020a24f8fe3582bf2f02e15e54ea796dbcb365bd
+oid sha256:37fbe3540b9c504c6798ba24b9f1096ffba70d5e960c19ede6130ccad899e3bb
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c75392d70a5db25de5e0347048e524a38224d3eb7ac2d3b59301cd94c661aadd
+oid sha256:67948995c81a49c60850112722c05d10b4cd200e03e8d6fa2424e1498932492d
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cf2db96717d6ec52cf8ff49f535bac4f251eac0651cdc3e9d1732a7f79de112
+oid sha256:5f0a40dbc07018ad1c847442ff39c42f57174e0bdc972f3b736a31043e102faa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a976cdbd49589ea6d6fdd08d2b7390ff1e7d9ecd31eb40af4bbb04d151df7f
+oid sha256:159344398c1079b21117aba7c2bc01dcdc0ee50a1f61b098a111a6b804e6b9b3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b642f481cf39ff26470caf3a9f0c5d39e63ee62605c84771c3c35364169a01d8
+oid sha256:f86e450b1d0d3b9a8b1e5e7e5012dec1d050dd5d5724f2da57ad64e179524746
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f67eebeb40515a0a0a28760acf89cb4de3b7f80410048b9b2e6565061bcf6772
+oid sha256:10d9366e8b6affc1df78003ffd496bd37abf60eb2a282b9ea0c5f08f0fe6ad72
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09031e244e5c89e52b3c3bb662b54db8a85996e54bd9c77222030648f1c7db3
+oid sha256:93ce236cdfc3570e60fc168a599f38d18a8345a454926b769bf6e4e2c224361f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.9314546585083,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2295081967213113,
+  "epoch": 3.1256830601092895,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,76 @@
       "eval_samples_per_second": 367.084,
       "eval_steps_per_second": 95.442,
       "step": 25
+    },
+    {
+      "epoch": 2.3169398907103824,
+      "grad_norm": 0.056846752762794495,
+      "learning_rate": 2.5531266972462177e-05,
+      "loss": 13.2342,
+      "step": 26
+    },
+    {
+      "epoch": 2.4043715846994536,
+      "grad_norm": 0.037951644510030746,
+      "learning_rate": 2.2431968285271844e-05,
+      "loss": 11.6904,
+      "step": 27
+    },
+    {
+      "epoch": 2.4918032786885247,
+      "grad_norm": 0.061074282974004745,
+      "learning_rate": 1.9627610736574575e-05,
+      "loss": 10.4965,
+      "step": 28
+    },
+    {
+      "epoch": 2.579234972677596,
+      "grad_norm": 0.04677893966436386,
+      "learning_rate": 1.7143591022596845e-05,
+      "loss": 12.9265,
+      "step": 29
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.05003131181001663,
+      "learning_rate": 1.5002404810528451e-05,
+      "loss": 12.5836,
+      "step": 30
+    },
+    {
+      "epoch": 2.7540983606557377,
+      "grad_norm": 0.052657756954431534,
+      "learning_rate": 1.3223443014276737e-05,
+      "loss": 10.8171,
+      "step": 31
+    },
+    {
+      "epoch": 2.841530054644809,
+      "grad_norm": 0.04703788459300995,
+      "learning_rate": 1.1822816187347623e-05,
+      "loss": 12.1961,
+      "step": 32
+    },
+    {
+      "epoch": 2.92896174863388,
+      "grad_norm": 0.05965609848499298,
+      "learning_rate": 1.08132086231782e-05,
+      "loss": 12.6582,
+      "step": 33
+    },
+    {
+      "epoch": 3.0382513661202184,
+      "grad_norm": 0.10015369951725006,
+      "learning_rate": 1.0203763484211195e-05,
+      "loss": 21.296,
+      "step": 34
+    },
+    {
+      "epoch": 3.1256830601092895,
+      "grad_norm": 0.04435504972934723,
+      "learning_rate": 1e-05,
+      "loss": 11.454,
+      "step": 35
     }
   ],
   "logging_steps": 1,
@@ -221,12 +291,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 521247129600.0,
+  "total_flos": 729745981440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null