Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:907422df75fba5847568c6e364258bbc9641693e835cdf4b3cae4193839c3c58
+oid sha256:186e0907618cf45e6eb2d9b5c7149239446b910c8ce78273d687177e38775675
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b15f1d01c79bcda1d47ab47f3925e52418721318ac4ae993c1dc4428fab3379
+oid sha256:2ef18be7228903235eca64a5dd9b717a5ed1a5261ba88fbb615251cef3c5835d
 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:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.763199806213379,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01601986463214386,
+  "best_metric": 11.762414932250977,
+  "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": 248.443,
       "eval_steps_per_second": 64.595,
       "step": 25
+    },
+    {
+      "epoch": 0.016660659217429614,
+      "grad_norm": 0.021041374653577805,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.7638,
+      "step": 26
+    },
+    {
+      "epoch": 0.017301453802715368,
+      "grad_norm": 0.020159004256129265,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7645,
+      "step": 27
+    },
+    {
+      "epoch": 0.01794224838800112,
+      "grad_norm": 0.02223449945449829,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7643,
+      "step": 28
+    },
+    {
+      "epoch": 0.018583042973286876,
+      "grad_norm": 0.02316456288099289,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7651,
+      "step": 29
+    },
+    {
+      "epoch": 0.01922383755857263,
+      "grad_norm": 0.026051953434944153,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.7645,
+      "step": 30
+    },
+    {
+      "epoch": 0.019864632143858384,
+      "grad_norm": 0.02636219933629036,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.7633,
+      "step": 31
+    },
+    {
+      "epoch": 0.020505426729144138,
+      "grad_norm": 0.026028776541352272,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.7633,
+      "step": 32
+    },
+    {
+      "epoch": 0.02114622131442989,
+      "grad_norm": 0.03129247948527336,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.7631,
+      "step": 33
+    },
+    {
+      "epoch": 0.02178701589971565,
+      "grad_norm": 0.030745303258299828,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.7637,
+      "step": 34
+    },
+    {
+      "epoch": 0.022427810485001403,
+      "grad_norm": 0.028258973732590675,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.7625,
+      "step": 35
+    },
+    {
+      "epoch": 0.023068605070287157,
+      "grad_norm": 0.025046132504940033,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7632,
+      "step": 36
+    },
+    {
+      "epoch": 0.02370939965557291,
+      "grad_norm": 0.02668956108391285,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.763,
+      "step": 37
+    },
+    {
+      "epoch": 0.024350194240858665,
+      "grad_norm": 0.035616256296634674,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.7639,
+      "step": 38
+    },
+    {
+      "epoch": 0.02499098882614442,
+      "grad_norm": 0.025154443457722664,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.7639,
+      "step": 39
+    },
+    {
+      "epoch": 0.025631783411430173,
+      "grad_norm": 0.028521809726953506,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7631,
+      "step": 40
+    },
+    {
+      "epoch": 0.026272577996715927,
+      "grad_norm": 0.03062279336154461,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.7638,
+      "step": 41
+    },
+    {
+      "epoch": 0.02691337258200168,
+      "grad_norm": 0.03084789216518402,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7638,
+      "step": 42
+    },
+    {
+      "epoch": 0.027554167167287435,
+      "grad_norm": 0.02840966358780861,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.764,
+      "step": 43
+    },
+    {
+      "epoch": 0.028194961752573192,
+      "grad_norm": 0.033411767333745956,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.7633,
+      "step": 44
+    },
+    {
+      "epoch": 0.028835756337858946,
+      "grad_norm": 0.034258123487234116,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.7631,
+      "step": 45
+    },
+    {
+      "epoch": 0.0294765509231447,
+      "grad_norm": 0.027682367712259293,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.7631,
+      "step": 46
+    },
+    {
+      "epoch": 0.030117345508430454,
+      "grad_norm": 0.030619610100984573,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.7626,
+      "step": 47
+    },
+    {
+      "epoch": 0.030758140093716208,
+      "grad_norm": 0.032262783497571945,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7633,
+      "step": 48
+    },
+    {
+      "epoch": 0.03139893467900196,
+      "grad_norm": 0.033579230308532715,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.763,
+      "step": 49
+    },
+    {
+      "epoch": 0.03203972926428772,
+      "grad_norm": 0.03474806621670723,
+      "learning_rate": 1e-05,
+      "loss": 11.7618,
+      "step": 50
+    },
+    {
+      "epoch": 0.03203972926428772,
+      "eval_loss": 11.762414932250977,
+      "eval_runtime": 0.1947,
+      "eval_samples_per_second": 256.82,
+      "eval_steps_per_second": 66.773,
+      "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": 82301569466368.0,
+  "total_flos": 164654353481728.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null