Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8225d4b67bf9d4340ddd71045351f6254fcfcdd2335ebf05401ff4f9498d664c
+oid sha256:51e841bd9facfff5775b35decb2b99894cb633ac9f75269ecf9dd33eb3b545ec
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eac3f3d6763605b6d370a852b04ba2fa5af7cc1b3809f4df59b52c6b070f3c6f
+oid sha256:65ae0286c185cbbd95ae0cb200298960251d45934ee2b68a7f80206a87a46725
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46197d6df4884dc3b127209e57d433f6754b0ea469e1e5f63f4c0b0540448469
+oid sha256:c03ba4e63601d6d722fda47d3648e5e7b10cd0897583ba2061e4a63332acb38d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eb68d9f47ffdb3d6ce6ae6d4787a9f5136b521d56ffb25d3c16ed6f90e3d36f
+oid sha256:f0adda1d6d20f75e492b083ecbfbe8d10329c64f38ef35c626284e8fbf4d0765
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e2a5eca9ba49d81bd0d4f0cf648dc37580146dc53f55c51aed473c069d24fc
+oid sha256:ad32e828ab9a75c84d16adbe7d16389940233d9be8d78e912fb26a67d1c1aefa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adec7cb925100fa61a9971553f812d842f33c5f597327db5f36eb1886d6d0830
+oid sha256:daac3f6e764bcde76fc8ce597d9449272df4d0eea3084620cc2d2d9e4f4c4edf
 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": 10.949499130249023,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6097560975609756,
+  "best_metric": 10.90999984741211,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2195121951219512,
   "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": 632.81,
       "eval_steps_per_second": 164.531,
       "step": 25
+    },
+    {
+      "epoch": 0.6341463414634146,
+      "grad_norm": 13.815815925598145,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 174.8391,
+      "step": 26
+    },
+    {
+      "epoch": 0.6585365853658537,
+      "grad_norm": 13.100130081176758,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 174.8297,
+      "step": 27
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 13.180046081542969,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 174.8187,
+      "step": 28
+    },
+    {
+      "epoch": 0.7073170731707317,
+      "grad_norm": 12.005698204040527,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 175.1813,
+      "step": 29
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 12.096576690673828,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 175.0422,
+      "step": 30
+    },
+    {
+      "epoch": 0.7560975609756098,
+      "grad_norm": 11.68134880065918,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 175.1812,
+      "step": 31
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 12.187183380126953,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 174.8641,
+      "step": 32
+    },
+    {
+      "epoch": 0.8048780487804879,
+      "grad_norm": 12.428651809692383,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 174.5688,
+      "step": 33
+    },
+    {
+      "epoch": 0.8292682926829268,
+      "grad_norm": 12.642929077148438,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 174.5922,
+      "step": 34
+    },
+    {
+      "epoch": 0.8536585365853658,
+      "grad_norm": 12.03905963897705,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 174.6,
+      "step": 35
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 12.165921211242676,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 174.6328,
+      "step": 36
+    },
+    {
+      "epoch": 0.9024390243902439,
+      "grad_norm": 12.175124168395996,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 174.6594,
+      "step": 37
+    },
+    {
+      "epoch": 0.926829268292683,
+      "grad_norm": 12.341449737548828,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 174.3922,
+      "step": 38
+    },
+    {
+      "epoch": 0.9512195121951219,
+      "grad_norm": 12.094307899475098,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 174.4875,
+      "step": 39
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 12.679279327392578,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 174.3047,
+      "step": 40
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.593793869018555,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 174.2922,
+      "step": 41
+    },
+    {
+      "epoch": 1.024390243902439,
+      "grad_norm": 11.996077537536621,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 174.5672,
+      "step": 42
+    },
+    {
+      "epoch": 1.048780487804878,
+      "grad_norm": 12.248947143554688,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 174.4156,
+      "step": 43
+    },
+    {
+      "epoch": 1.0731707317073171,
+      "grad_norm": 12.989773750305176,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 174.1469,
+      "step": 44
+    },
+    {
+      "epoch": 1.0975609756097562,
+      "grad_norm": 11.868778228759766,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 174.5203,
+      "step": 45
+    },
+    {
+      "epoch": 1.1219512195121952,
+      "grad_norm": 11.858358383178711,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 174.4172,
+      "step": 46
+    },
+    {
+      "epoch": 1.146341463414634,
+      "grad_norm": 11.711751937866211,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 174.4203,
+      "step": 47
+    },
+    {
+      "epoch": 1.170731707317073,
+      "grad_norm": 12.023517608642578,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 174.2734,
+      "step": 48
+    },
+    {
+      "epoch": 1.1951219512195121,
+      "grad_norm": 12.9298677444458,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 173.8922,
+      "step": 49
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 11.806296348571777,
+      "learning_rate": 1e-05,
+      "loss": 174.325,
+      "step": 50
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "eval_loss": 10.90999984741211,
+      "eval_runtime": 0.0961,
+      "eval_samples_per_second": 520.291,
+      "eval_steps_per_second": 135.276,
+      "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": 2101346304000.0,
+  "total_flos": 4202692608000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null