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:c7f6576cb582b70274ab4e121533682bf9e1e85606090b784fd6fa72919ece1b
+oid sha256:58460501797c790fa42a6dac359f3a82eec702922ddb2ae8758f766ec563f568
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86583866ef4f655e415ffd2fc6026e8f510eed33f0e70141bebb561e29acf21
+oid sha256:ad1dfe453f6e2a27967e6bcab08462355d39ffd65f9b88468e9cfa0d23c50d29
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6faccaa58ca1dc71c664fe731fd38f758c540c1e67c9a37b64f4e11c53d89c3
+oid sha256:ef0bc15308c4e2d7a9d7eb21b7efe66e17ef733cf9c40a47c74490075c4bb179
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b26333112dfba8220ddeb8e0b83926d3f12ed7d746db8ee6cdcf49f09ab3bcac
+oid sha256:c739a670c495e55cc1154b2d031dd316ccbe5fa2f51e0baae75301344f234379
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e5610cbac4525de9f773cab006dd4dca9d6774d033535e478e049ee41485a0
+oid sha256:fdc92baf2f6ec86e86cb9b50b13ac850fc5784032dc47cbc6eefb2a0d6b3716e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa22e1a58ccd4395f4df9a32c7f317e80b6b5653df9345261874e3781c68a5d
+oid sha256:601b22613d2d8a193cfc8f0c3d57f2454c986fca2033fb8e04c5fec07b7e9fec
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.763106346130371,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01601986463214386,
+  "best_metric": 11.761113166809082,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03203972926428772,
   "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": 209.58,
       "eval_steps_per_second": 54.491,
       "step": 25
+    },
+    {
+      "epoch": 0.016660659217429614,
+      "grad_norm": 0.02223326452076435,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 11.7637,
+      "step": 26
+    },
+    {
+      "epoch": 0.017301453802715368,
+      "grad_norm": 0.020472681149840355,
+      "learning_rate": 7.75e-05,
+      "loss": 11.7644,
+      "step": 27
+    },
+    {
+      "epoch": 0.01794224838800112,
+      "grad_norm": 0.023782216012477875,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 11.7642,
+      "step": 28
+    },
+    {
+      "epoch": 0.018583042973286876,
+      "grad_norm": 0.0240348968654871,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 11.765,
+      "step": 29
+    },
+    {
+      "epoch": 0.01922383755857263,
+      "grad_norm": 0.028316188603639603,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 11.7643,
+      "step": 30
+    },
+    {
+      "epoch": 0.019864632143858384,
+      "grad_norm": 0.02909417264163494,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 11.763,
+      "step": 31
+    },
+    {
+      "epoch": 0.020505426729144138,
+      "grad_norm": 0.029121633619070053,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 11.763,
+      "step": 32
+    },
+    {
+      "epoch": 0.02114622131442989,
+      "grad_norm": 0.0339232012629509,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 11.7627,
+      "step": 33
+    },
+    {
+      "epoch": 0.02178701589971565,
+      "grad_norm": 0.03640107810497284,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 11.7633,
+      "step": 34
+    },
+    {
+      "epoch": 0.022427810485001403,
+      "grad_norm": 0.03253023698925972,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 11.7621,
+      "step": 35
+    },
+    {
+      "epoch": 0.023068605070287157,
+      "grad_norm": 0.028020696714520454,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 11.7629,
+      "step": 36
+    },
+    {
+      "epoch": 0.02370939965557291,
+      "grad_norm": 0.031051475554704666,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 11.7626,
+      "step": 37
+    },
+    {
+      "epoch": 0.024350194240858665,
+      "grad_norm": 0.04053696244955063,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 11.7636,
+      "step": 38
+    },
+    {
+      "epoch": 0.02499098882614442,
+      "grad_norm": 0.029524900019168854,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.7634,
+      "step": 39
+    },
+    {
+      "epoch": 0.025631783411430173,
+      "grad_norm": 0.03623311594128609,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 11.7624,
+      "step": 40
+    },
+    {
+      "epoch": 0.026272577996715927,
+      "grad_norm": 0.03804594278335571,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 11.763,
+      "step": 41
+    },
+    {
+      "epoch": 0.02691337258200168,
+      "grad_norm": 0.03952088952064514,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7628,
+      "step": 42
+    },
+    {
+      "epoch": 0.027554167167287435,
+      "grad_norm": 0.037932537496089935,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 11.763,
+      "step": 43
+    },
+    {
+      "epoch": 0.028194961752573192,
+      "grad_norm": 0.04360462725162506,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 11.7623,
+      "step": 44
+    },
+    {
+      "epoch": 0.028835756337858946,
+      "grad_norm": 0.04510717839002609,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.762,
+      "step": 45
+    },
+    {
+      "epoch": 0.0294765509231447,
+      "grad_norm": 0.03812625631690025,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 11.762,
+      "step": 46
+    },
+    {
+      "epoch": 0.030117345508430454,
+      "grad_norm": 0.04157785326242447,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 11.7614,
+      "step": 47
+    },
+    {
+      "epoch": 0.030758140093716208,
+      "grad_norm": 0.044761281460523605,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.762,
+      "step": 48
+    },
+    {
+      "epoch": 0.03139893467900196,
+      "grad_norm": 0.04416681081056595,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 11.7618,
+      "step": 49
+    },
+    {
+      "epoch": 0.03203972926428772,
+      "grad_norm": 0.0453573577105999,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 11.7605,
+      "step": 50
+    },
+    {
+      "epoch": 0.03203972926428772,
+      "eval_loss": 11.761113166809082,
+      "eval_runtime": 0.2345,
+      "eval_samples_per_second": 213.264,
+      "eval_steps_per_second": 55.449,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 82301569466368.0,
+  "total_flos": 164654353481728.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null