Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fafb81d90584f2e0e2921e8aaf3aa3e1c7d70b652bcfed28ae4ce6d92814a1c
+oid sha256:55dfbe1dc53fc298268e690577b96427378c308a34b28f6f04c151e163837ffe
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0efe61cc9f5b79b89eb5f9c59e71fb554a540c05057f6e9b10ae3ce91e4d39cd
+oid sha256:d0d4b37698dc8a10bbf53e57b1bbec0e33114c582cf404980970eda0735373e8
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dae74460292902058edc4bf99de8059883ff00ba6f0e854a4adb8a89b93bafb
+oid sha256:cbed55ed9ec3a53dc4a32e6ff3e5dbe90225f97ca39fa446122055c3c57386b5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:895441bd87416764d337c63f539cda908bc5c59bed156c93c05324507f415780
+oid sha256:b1cc2ba7e9cc2e7c7236b85beec9eff9e41ca72e95eef13d7e678accb0427657
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28272c33cff6585b5c57a5561e6646ec89af1424448f12805062a5522fb2017b
+oid sha256:f2e8dc30579b3b44497a1ae17ffb5d55c50bc7b8f0facd8e36321825691e7e0c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80a802e45f317c7d0b1d4bf7d6e34a2ff6fd98d61aa4cff1e2b134ce650a7c5
+oid sha256:12c828fd0ee2fb682a16c08a85523bfb536fee080ad9784f61b0b47ccb788291
 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": 11.927356719970703,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.062315002336812586,
+  "best_metric": 11.92679214477539,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12463000467362517,
   "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": 250.105,
       "eval_steps_per_second": 65.027,
       "step": 25
+    },
+    {
+      "epoch": 0.06480760243028509,
+      "grad_norm": 0.027307763695716858,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9309,
+      "step": 26
+    },
+    {
+      "epoch": 0.0673002025237576,
+      "grad_norm": 0.02421778067946434,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9311,
+      "step": 27
+    },
+    {
+      "epoch": 0.0697928026172301,
+      "grad_norm": 0.02540089190006256,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9309,
+      "step": 28
+    },
+    {
+      "epoch": 0.0722854027107026,
+      "grad_norm": 0.019033024087548256,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.931,
+      "step": 29
+    },
+    {
+      "epoch": 0.07477800280417511,
+      "grad_norm": 0.02582223154604435,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.931,
+      "step": 30
+    },
+    {
+      "epoch": 0.0772706028976476,
+      "grad_norm": 0.027421683073043823,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9311,
+      "step": 31
+    },
+    {
+      "epoch": 0.07976320299112011,
+      "grad_norm": 0.0327715128660202,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9297,
+      "step": 32
+    },
+    {
+      "epoch": 0.08225580308459261,
+      "grad_norm": 0.02419387362897396,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9295,
+      "step": 33
+    },
+    {
+      "epoch": 0.08474840317806512,
+      "grad_norm": 0.023017315194010735,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9282,
+      "step": 34
+    },
+    {
+      "epoch": 0.08724100327153762,
+      "grad_norm": 0.0338151752948761,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9288,
+      "step": 35
+    },
+    {
+      "epoch": 0.08973360336501013,
+      "grad_norm": 0.02851535566151142,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9279,
+      "step": 36
+    },
+    {
+      "epoch": 0.09222620345848263,
+      "grad_norm": 0.04185821861028671,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.929,
+      "step": 37
+    },
+    {
+      "epoch": 0.09471880355195514,
+      "grad_norm": 0.03193657100200653,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.931,
+      "step": 38
+    },
+    {
+      "epoch": 0.09721140364542763,
+      "grad_norm": 0.03217791020870209,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9304,
+      "step": 39
+    },
+    {
+      "epoch": 0.09970400373890013,
+      "grad_norm": 0.031128505244851112,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9307,
+      "step": 40
+    },
+    {
+      "epoch": 0.10219660383237264,
+      "grad_norm": 0.03158225491642952,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9304,
+      "step": 41
+    },
+    {
+      "epoch": 0.10468920392584515,
+      "grad_norm": 0.034790318459272385,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.929,
+      "step": 42
+    },
+    {
+      "epoch": 0.10718180401931765,
+      "grad_norm": 0.037614643573760986,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9298,
+      "step": 43
+    },
+    {
+      "epoch": 0.10967440411279016,
+      "grad_norm": 0.03061523847281933,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9292,
+      "step": 44
+    },
+    {
+      "epoch": 0.11216700420626266,
+      "grad_norm": 0.03246842697262764,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9296,
+      "step": 45
+    },
+    {
+      "epoch": 0.11465960429973517,
+      "grad_norm": 0.02890903502702713,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9288,
+      "step": 46
+    },
+    {
+      "epoch": 0.11715220439320767,
+      "grad_norm": 0.026723528280854225,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9302,
+      "step": 47
+    },
+    {
+      "epoch": 0.11964480448668016,
+      "grad_norm": 0.027072373777627945,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9284,
+      "step": 48
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 0.04512767866253853,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9276,
+      "step": 49
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "grad_norm": 0.051480695605278015,
+      "learning_rate": 1e-05,
+      "loss": 11.9278,
+      "step": 50
+    },
+    {
+      "epoch": 0.12463000467362517,
+      "eval_loss": 11.92679214477539,
+      "eval_runtime": 0.1966,
+      "eval_samples_per_second": 254.37,
+      "eval_steps_per_second": 66.136,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null