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:ad942e79ec22114e0b664a022c6240b7d1c9cc4b5e90fe819b37f8f78baabc67
+oid sha256:16b8a8371f47ddb0a4fa1b21f19300682293d49478879e7a49f4698d33c1f2e3
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b51959e640d86809962d0fb7b0d0e4f6f372522878cd5a726edfdf38b296fc
+oid sha256:02887120bc9c7dbd9cb68c6a34f37d074a8c7b238477322a71e348a477c211a1
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c42bc169fff0f34623f0f820498f436b1c0ef03c2e38df9d8205521c1a7d2367
+oid sha256:0d1fb6ec6035a368fb30571005ccf5c3d36b3947c92349f2a47f2b3e3463bf33
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7825a1c372f998c605d2acafe4e0cb514ba157f7835861ec25c1f1acc1d6e91
+oid sha256:9331316a4ca49f2dd2ba0f4cc5f51d4b98e4c8db07666db47fb1f1916ec8511f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a091992568c8c134f7b3fae6d4eff22e7bd94dc18e7eedd7311437135874435
+oid sha256:568afa837c0da61a1844575130d90e48bf5949e2cc7b4c2cd96caf59bf7f9121
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f01e04c9a8c8545db8a49256f9d17b3952cb5ae8ead7c166aeaf402ca9dae718
+oid sha256:e928db9eebc9892c7d0b0366dcc524113bf283f57d7832d86a0eb7738cf6e772
 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": 2.7142794132232666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014761509364332502,
+  "best_metric": 1.9969189167022705,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.029523018728665005,
   "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": 100.026,
       "eval_steps_per_second": 26.007,
       "step": 25
+    },
+    {
+      "epoch": 0.015351969738905803,
+      "grad_norm": 5.699878215789795,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.2477,
+      "step": 26
+    },
+    {
+      "epoch": 0.0159424301134791,
+      "grad_norm": 7.3144612312316895,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.0987,
+      "step": 27
+    },
+    {
+      "epoch": 0.016532890488052402,
+      "grad_norm": 7.50764274597168,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.8751,
+      "step": 28
+    },
+    {
+      "epoch": 0.017123350862625702,
+      "grad_norm": 6.4948039054870605,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.6886,
+      "step": 29
+    },
+    {
+      "epoch": 0.017713811237199003,
+      "grad_norm": 13.463104248046875,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.9681,
+      "step": 30
+    },
+    {
+      "epoch": 0.018304271611772303,
+      "grad_norm": 9.158689498901367,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.7377,
+      "step": 31
+    },
+    {
+      "epoch": 0.018894731986345604,
+      "grad_norm": 6.033637046813965,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.7305,
+      "step": 32
+    },
+    {
+      "epoch": 0.019485192360918904,
+      "grad_norm": 10.262680053710938,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.6665,
+      "step": 33
+    },
+    {
+      "epoch": 0.020075652735492205,
+      "grad_norm": 8.832808494567871,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.6649,
+      "step": 34
+    },
+    {
+      "epoch": 0.020666113110065505,
+      "grad_norm": 7.658655643463135,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.4372,
+      "step": 35
+    },
+    {
+      "epoch": 0.021256573484638806,
+      "grad_norm": 5.869558811187744,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.7042,
+      "step": 36
+    },
+    {
+      "epoch": 0.021847033859212106,
+      "grad_norm": 6.306788921356201,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.7355,
+      "step": 37
+    },
+    {
+      "epoch": 0.022437494233785403,
+      "grad_norm": 5.178953647613525,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.4691,
+      "step": 38
+    },
+    {
+      "epoch": 0.023027954608358703,
+      "grad_norm": 6.899292469024658,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.3852,
+      "step": 39
+    },
+    {
+      "epoch": 0.023618414982932004,
+      "grad_norm": 7.314828872680664,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.3326,
+      "step": 40
+    },
+    {
+      "epoch": 0.024208875357505304,
+      "grad_norm": 5.12600564956665,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.2436,
+      "step": 41
+    },
+    {
+      "epoch": 0.024799335732078605,
+      "grad_norm": 6.7783918380737305,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.3238,
+      "step": 42
+    },
+    {
+      "epoch": 0.025389796106651905,
+      "grad_norm": 7.407707691192627,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.4676,
+      "step": 43
+    },
+    {
+      "epoch": 0.025980256481225206,
+      "grad_norm": 6.619644641876221,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.543,
+      "step": 44
+    },
+    {
+      "epoch": 0.026570716855798506,
+      "grad_norm": 6.882936000823975,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.381,
+      "step": 45
+    },
+    {
+      "epoch": 0.027161177230371807,
+      "grad_norm": 6.69130802154541,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.4668,
+      "step": 46
+    },
+    {
+      "epoch": 0.027751637604945107,
+      "grad_norm": 6.239401817321777,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.481,
+      "step": 47
+    },
+    {
+      "epoch": 0.028342097979518407,
+      "grad_norm": 5.6806960105896,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.6168,
+      "step": 48
+    },
+    {
+      "epoch": 0.028932558354091704,
+      "grad_norm": 6.273911952972412,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.7033,
+      "step": 49
+    },
+    {
+      "epoch": 0.029523018728665005,
+      "grad_norm": 10.321796417236328,
+      "learning_rate": 1e-05,
+      "loss": 2.8148,
+      "step": 50
+    },
+    {
+      "epoch": 0.029523018728665005,
+      "eval_loss": 1.9969189167022705,
+      "eval_runtime": 0.5013,
+      "eval_samples_per_second": 99.731,
+      "eval_steps_per_second": 25.93,
+      "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": 4.16708196040704e+16,
+  "total_flos": 8.33416392081408e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null