Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0da2a584b7c7191eec890b07b4d512485316e897a1b9675e75a4f7d220087eb6
+oid sha256:0437544740f11c78da0e5f7a340807cb40d8444a94a3728be539d74f234d714c
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f93301d9f4183f1be4d4d189893234ad5817303e3c36e6c42755357ef0088ee
+oid sha256:5d78745ad7e40209a8132772ad95cfee70c4b421e2de309a452625d7de09dfaa
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9f72e34ed71a50660a4e64a676c226fa689202a884d87d3a1834ccb413e695
+oid sha256:5812d3b8b5a5a5fe940d8f3e98b9bddd3322ee43a2c376a382d7dfb55bf272d4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8e8e0306d8900f326d249b35e11a038b6d586eb91c53b5e975ee8a62d91932c
+oid sha256:be59c9eb1c94429bb371f8d3e55592f5287b7a0571b066f25d178a0dad9f3fe1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a111b09b893e8d249d5d9357fc649c34d7048a3c4588eb67530c6df532049983
+oid sha256:4e7a6381b1971e114049beac19c63773049d6249a3c3bb9ca53eb363c02914b4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caa6748ba247109ef2138ae358634a4d14d25bfcfde660ec3b51147cdd5cecb3
+oid sha256:ac83e9832abd3f71c8aa6503e269900d4f10673fbfe04f250943f24894f90543
 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": 0.4331847131252289,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.8048289738430584,
+  "best_metric": 0.3067149817943573,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.6096579476861166,
   "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": 102.816,
       "eval_steps_per_second": 26.732,
       "step": 25
+    },
+    {
+      "epoch": 0.8370221327967807,
+      "grad_norm": 2.261975049972534,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4783,
+      "step": 26
+    },
+    {
+      "epoch": 0.869215291750503,
+      "grad_norm": 1.3807170391082764,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.4561,
+      "step": 27
+    },
+    {
+      "epoch": 0.9014084507042254,
+      "grad_norm": 1.5317381620407104,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4011,
+      "step": 28
+    },
+    {
+      "epoch": 0.9336016096579477,
+      "grad_norm": 2.0689496994018555,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4196,
+      "step": 29
+    },
+    {
+      "epoch": 0.96579476861167,
+      "grad_norm": 2.0331664085388184,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4052,
+      "step": 30
+    },
+    {
+      "epoch": 0.9979879275653923,
+      "grad_norm": 5.181220531463623,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4492,
+      "step": 31
+    },
+    {
+      "epoch": 1.0301810865191148,
+      "grad_norm": 2.0923736095428467,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.544,
+      "step": 32
+    },
+    {
+      "epoch": 1.062374245472837,
+      "grad_norm": 1.3229002952575684,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4147,
+      "step": 33
+    },
+    {
+      "epoch": 1.0945674044265594,
+      "grad_norm": 1.0754610300064087,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3707,
+      "step": 34
+    },
+    {
+      "epoch": 1.1267605633802817,
+      "grad_norm": 0.7933202981948853,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3393,
+      "step": 35
+    },
+    {
+      "epoch": 1.158953722334004,
+      "grad_norm": 0.7941595315933228,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3655,
+      "step": 36
+    },
+    {
+      "epoch": 1.1911468812877264,
+      "grad_norm": 1.1384649276733398,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.332,
+      "step": 37
+    },
+    {
+      "epoch": 1.2233400402414487,
+      "grad_norm": 1.9317988157272339,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.397,
+      "step": 38
+    },
+    {
+      "epoch": 1.255533199195171,
+      "grad_norm": 1.4935693740844727,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.2746,
+      "step": 39
+    },
+    {
+      "epoch": 1.2877263581488934,
+      "grad_norm": 1.1563270092010498,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.3031,
+      "step": 40
+    },
+    {
+      "epoch": 1.3199195171026157,
+      "grad_norm": 1.0263022184371948,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3415,
+      "step": 41
+    },
+    {
+      "epoch": 1.352112676056338,
+      "grad_norm": 0.9527009725570679,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.341,
+      "step": 42
+    },
+    {
+      "epoch": 1.3843058350100603,
+      "grad_norm": 0.8192784786224365,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3399,
+      "step": 43
+    },
+    {
+      "epoch": 1.4164989939637826,
+      "grad_norm": 0.9891771674156189,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.312,
+      "step": 44
+    },
+    {
+      "epoch": 1.448692152917505,
+      "grad_norm": 1.3020000457763672,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.349,
+      "step": 45
+    },
+    {
+      "epoch": 1.4808853118712273,
+      "grad_norm": 1.8249863386154175,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.325,
+      "step": 46
+    },
+    {
+      "epoch": 1.5130784708249498,
+      "grad_norm": 0.9550820589065552,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2643,
+      "step": 47
+    },
+    {
+      "epoch": 1.545271629778672,
+      "grad_norm": 1.160873293876648,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3217,
+      "step": 48
+    },
+    {
+      "epoch": 1.5774647887323945,
+      "grad_norm": 1.0742133855819702,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.2941,
+      "step": 49
+    },
+    {
+      "epoch": 1.6096579476861166,
+      "grad_norm": 0.9035133719444275,
+      "learning_rate": 1e-05,
+      "loss": 0.2899,
+      "step": 50
+    },
+    {
+      "epoch": 1.6096579476861166,
+      "eval_loss": 0.3067149817943573,
+      "eval_runtime": 0.4865,
+      "eval_samples_per_second": 102.782,
+      "eval_steps_per_second": 26.723,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null