Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35115f6f73ac4a4094f8e747638deccb1827f1282fadf0cd03ed5b486fe6e3cd
+oid sha256:6e272739c9445fb5a14cc09fe3793487da1620dac3eafb1e4c5036ea47e36d51
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2550d2b9599eba4a3b706c6dd3e70c18c1f24c0a7f859455e46a90bbca1aadf
+oid sha256:a2dbd19604af0f0be327a5cc18e5b63a044856aaec1cfb145ffe0f57d5fd2439
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f2270feded0d36ad846e09faa4e24938bcda0afe934744c513ad897176568c
+oid sha256:b08f8169d14f698613be7d9725ee9c9e08b0dfe3d39fc06c081d11358185a820
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df007af7f74a154ba6a2cf795d203cd54dfd0f2834aa782669a0c21f83495390
+oid sha256:8130d11b6bc113ca41b1320af37c2a991b8d3f3538d7481db06e48d89c792ebb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0edeb080c5229c6b7a8c70c54df849a0a89ea3a9f7af2eed759fcc8ea5e7a934
+oid sha256:977e6950c88bcf9ff6299db55dae71d314f72c3582ac08cad105e0b8445c6d32
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30dd81f1a7c96ceb9c3bc97d1f2c3f5df995a0e2a0e6ed564c6fdd061152c685
+oid sha256:8bd8ef9cd904e147b95d951959d0cc04cc34755065faf2f257e15afc5d96040b
 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": 10.323394775390625,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5128205128205128,
+  "best_metric": 10.302452087402344,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0256410256410255,
   "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": 521.472,
       "eval_steps_per_second": 135.583,
       "step": 25
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.35155364871025085,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3635,
+      "step": 26
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.3796391189098358,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3495,
+      "step": 27
+    },
+    {
+      "epoch": 0.5743589743589743,
+      "grad_norm": 0.38944631814956665,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3472,
+      "step": 28
+    },
+    {
+      "epoch": 0.5948717948717949,
+      "grad_norm": 0.3875417411327362,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3383,
+      "step": 29
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.4149477183818817,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3198,
+      "step": 30
+    },
+    {
+      "epoch": 0.6358974358974359,
+      "grad_norm": 0.42636293172836304,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3185,
+      "step": 31
+    },
+    {
+      "epoch": 0.6564102564102564,
+      "grad_norm": 0.43451759219169617,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3118,
+      "step": 32
+    },
+    {
+      "epoch": 0.676923076923077,
+      "grad_norm": 0.4598996341228485,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3206,
+      "step": 33
+    },
+    {
+      "epoch": 0.6974358974358974,
+      "grad_norm": 0.45923203229904175,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3161,
+      "step": 34
+    },
+    {
+      "epoch": 0.717948717948718,
+      "grad_norm": 0.477365642786026,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3025,
+      "step": 35
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.49920061230659485,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3202,
+      "step": 36
+    },
+    {
+      "epoch": 0.7589743589743589,
+      "grad_norm": 0.4537535011768341,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.325,
+      "step": 37
+    },
+    {
+      "epoch": 0.7794871794871795,
+      "grad_norm": 0.4087854027748108,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3412,
+      "step": 38
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.44184836745262146,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3441,
+      "step": 39
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 0.4397507309913635,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3281,
+      "step": 40
+    },
+    {
+      "epoch": 0.841025641025641,
+      "grad_norm": 0.437427818775177,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3175,
+      "step": 41
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "grad_norm": 0.4404502511024475,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3258,
+      "step": 42
+    },
+    {
+      "epoch": 0.882051282051282,
+      "grad_norm": 0.4655083119869232,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3021,
+      "step": 43
+    },
+    {
+      "epoch": 0.9025641025641026,
+      "grad_norm": 0.4786524772644043,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.302,
+      "step": 44
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.5160654187202454,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.2986,
+      "step": 45
+    },
+    {
+      "epoch": 0.9435897435897436,
+      "grad_norm": 0.4955737888813019,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.2909,
+      "step": 46
+    },
+    {
+      "epoch": 0.9641025641025641,
+      "grad_norm": 0.5149694681167603,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.2978,
+      "step": 47
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "grad_norm": 0.5238509178161621,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3114,
+      "step": 48
+    },
+    {
+      "epoch": 1.005128205128205,
+      "grad_norm": 0.5735796093940735,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 12.8739,
+      "step": 49
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.46631649136543274,
+      "learning_rate": 1e-05,
+      "loss": 10.1867,
+      "step": 50
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "eval_loss": 10.302452087402344,
+      "eval_runtime": 0.0887,
+      "eval_samples_per_second": 563.575,
+      "eval_steps_per_second": 146.529,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null