Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8196d2db9ecb4d6196786110d31a26f166cebe2bebc40a4afdb5bdcd47d87396
+oid sha256:bb35c6ea9d73a05f053d8c4853704ea64d0245a0d7e7c0d23ae578e25c5880db
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3c01158e42b3b58ead9b08bd9ffc42727f0079c57c5aa4154a07b80ff7725c3
+oid sha256:cbb229a182e65ae13c219bab2f97c47a4018c3f6d32f138204d1b5cf5b15e38d
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c7d05f76d5ef34c722199c275f7f3d2db1872717162c84ee3a32436e9a26ac8
+oid sha256:c71b4f2a614e7a6bf9168e59ac4f6ef5b6f5a40c1817d776754cee3cf1f22ee6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ff1399c96b19be5797e5ccd5818cb7427ffad8317d97b0062006f260a8b860f
+oid sha256:dd95c6927d8d3ba9ca8063b2d028920f7912f7c4471d19cd5cba0cbcd7b771df
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd96ea2af8ff71ec23c2aa57688cbf00b0902680695574cd623c5d5990594ae9
+oid sha256:be1c2d29c041ff30eff919d96ff69d6b094b7f805924847b9effc0299aeadb28
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b4ef4bcce5deb08d04e6713d4b5d3a9e810a4060bf2c68dc671d188e58e27a
+oid sha256:0e318e906ab04c9c229dcebbbd6083dd5676057fe74ef8979e370cdb2aec6817
 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": 0.3024834394454956,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2147074610842727,
+  "best_metric": 0.250135213136673,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4294149221685454,
   "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": 26.116,
       "eval_steps_per_second": 6.79,
       "step": 25
+    },
+    {
+      "epoch": 0.22329575952764358,
+      "grad_norm": 1.5792282819747925,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3402,
+      "step": 26
+    },
+    {
+      "epoch": 0.2318840579710145,
+      "grad_norm": 1.05101478099823,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3257,
+      "step": 27
+    },
+    {
+      "epoch": 0.2404723564143854,
+      "grad_norm": 1.035786747932434,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3294,
+      "step": 28
+    },
+    {
+      "epoch": 0.2490606548577563,
+      "grad_norm": 1.0826724767684937,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.3104,
+      "step": 29
+    },
+    {
+      "epoch": 0.2576489533011272,
+      "grad_norm": 0.639144778251648,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3057,
+      "step": 30
+    },
+    {
+      "epoch": 0.26623725174449814,
+      "grad_norm": 0.630906343460083,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.278,
+      "step": 31
+    },
+    {
+      "epoch": 0.274825550187869,
+      "grad_norm": 1.115294337272644,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.2595,
+      "step": 32
+    },
+    {
+      "epoch": 0.2834138486312399,
+      "grad_norm": 0.47555750608444214,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2681,
+      "step": 33
+    },
+    {
+      "epoch": 0.29200214707461086,
+      "grad_norm": 0.9514725804328918,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3414,
+      "step": 34
+    },
+    {
+      "epoch": 0.30059044551798175,
+      "grad_norm": 0.8921436071395874,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2927,
+      "step": 35
+    },
+    {
+      "epoch": 0.30917874396135264,
+      "grad_norm": 1.4115748405456543,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3358,
+      "step": 36
+    },
+    {
+      "epoch": 0.3177670424047236,
+      "grad_norm": 1.133245587348938,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3453,
+      "step": 37
+    },
+    {
+      "epoch": 0.3263553408480945,
+      "grad_norm": 1.1106758117675781,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.318,
+      "step": 38
+    },
+    {
+      "epoch": 0.33494363929146537,
+      "grad_norm": 1.7452747821807861,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3193,
+      "step": 39
+    },
+    {
+      "epoch": 0.3435319377348363,
+      "grad_norm": 1.925551176071167,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.3473,
+      "step": 40
+    },
+    {
+      "epoch": 0.3521202361782072,
+      "grad_norm": 0.773165762424469,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.2916,
+      "step": 41
+    },
+    {
+      "epoch": 0.3607085346215781,
+      "grad_norm": 0.8585931062698364,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3026,
+      "step": 42
+    },
+    {
+      "epoch": 0.369296833064949,
+      "grad_norm": 0.44937247037887573,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2761,
+      "step": 43
+    },
+    {
+      "epoch": 0.3778851315083199,
+      "grad_norm": 0.7727624773979187,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3183,
+      "step": 44
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 0.6559286713600159,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.285,
+      "step": 45
+    },
+    {
+      "epoch": 0.3950617283950617,
+      "grad_norm": 0.5505415201187134,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.2792,
+      "step": 46
+    },
+    {
+      "epoch": 0.40365002683843265,
+      "grad_norm": 0.9058887958526611,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2909,
+      "step": 47
+    },
+    {
+      "epoch": 0.41223832528180354,
+      "grad_norm": 0.9981274008750916,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3462,
+      "step": 48
+    },
+    {
+      "epoch": 0.42082662372517443,
+      "grad_norm": 1.426024079322815,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.385,
+      "step": 49
+    },
+    {
+      "epoch": 0.4294149221685454,
+      "grad_norm": 0.8514761328697205,
+      "learning_rate": 1e-05,
+      "loss": 0.3346,
+      "step": 50
+    },
+    {
+      "epoch": 0.4294149221685454,
+      "eval_loss": 0.250135213136673,
+      "eval_runtime": 1.9284,
+      "eval_samples_per_second": 25.928,
+      "eval_steps_per_second": 6.741,
+      "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": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null