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:b6d0bf920c733e8b304796dea91c98df3ec348d110d9427b885e65452936fb9e
+oid sha256:9c876d931b21a4876866a0faab68bd6d13805b645b0748ce2287b1cdd0fc70f7
 size 261131840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0857205097546514ef2a02969d4d45767f4b69e6725ff54c6e7d2db697f4c454
+oid sha256:7b6d60d2beb211a29b17c588f7ed7bc00df6bcdb582fd43c9821e1a7b7e1e3ad
 size 522406650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45136dbdd62c35321595e96a6bdbd4749874ef22c29a3b3c22300c91720cc6d1
+oid sha256:1ebccf94a3797b5ef815af2b527782eecdd95b5f0d48af13629920ad1e1c6307
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f71c63316d90592fbd8ceece707c9dd9ff8808bd363bc93c970224b6d11db6d
+oid sha256:72ea8e16b5cc8e782f1f4e69d41fe07c53bdaecba9738fcadf21b6d22fb5775f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f133ea18573806a789f8215784ccc6efa61dee6310ebae69745884e61603947e
+oid sha256:e813a1ec2b1e56285516d8a3ad433d7cd30653085db766ef1a1fc6ad301df78c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:888d987e45bf2bcb2f393683cb3f4042015af62c88eeb7986df27fa7889a56dd
+oid sha256:a4678681759c4d503ed0d80478a6a856abd1138668c3e5e085f9b79e1d487834
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.024727992087042534,
+  "epoch": 0.04945598417408507,
   "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": 16.1,
       "eval_steps_per_second": 4.186,
       "step": 25
+    },
+    {
+      "epoch": 0.025717111770524232,
+      "grad_norm": 0.005930684041231871,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.026706231454005934,
+      "grad_norm": 0.000554934493266046,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.027695351137487636,
+      "grad_norm": 0.000434371002484113,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.028684470820969338,
+      "grad_norm": 0.00038748563383705914,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.02967359050445104,
+      "grad_norm": 0.00020503619452938437,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.03066271018793274,
+      "grad_norm": 0.00018179230391979218,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.03165182987141444,
+      "grad_norm": 0.00015180310583673418,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.032640949554896145,
+      "grad_norm": 9.859587589744478e-05,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.033630069238377844,
+      "grad_norm": 5.5495173000963405e-05,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0001,
+      "step": 34
+    },
+    {
+      "epoch": 0.03461918892185954,
+      "grad_norm": 2.0611228137568105e-06,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.03560830860534125,
+      "grad_norm": 0.0,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.036597428288822946,
+      "grad_norm": 0.0,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.03758654797230465,
+      "grad_norm": 0.008622519671916962,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0001,
+      "step": 38
+    },
+    {
+      "epoch": 0.03857566765578635,
+      "grad_norm": 0.0009911018423736095,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.03956478733926805,
+      "grad_norm": 0.0003509419329930097,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.040553907022749754,
+      "grad_norm": 0.000303212262224406,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.04154302670623145,
+      "grad_norm": 0.0001914541790029034,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.04253214638971316,
+      "grad_norm": 0.0001312332460656762,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.043521266073194856,
+      "grad_norm": 0.00010561131784925237,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.04451038575667656,
+      "grad_norm": 9.838654659688473e-05,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.04549950544015826,
+      "grad_norm": 2.881192631321028e-05,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.04648862512363996,
+      "grad_norm": 3.0320079531520605e-06,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0001,
+      "step": 47
+    },
+    {
+      "epoch": 0.04747774480712166,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.04846686449060336,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.04945598417408507,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.04945598417408507,
+      "eval_loss": NaN,
+      "eval_runtime": 3.1076,
+      "eval_samples_per_second": 16.089,
+      "eval_steps_per_second": 4.183,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.6328593194601677e+17,
+  "total_flos": 5.264074128154952e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null