Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bde9be1b8c3140fb04ec27cb11a05124342c8ba4e491af2f4fc238465af2b5c
+oid sha256:5ab1492a272796896a1fa9898968f2118dc772ca0d64c2d5f86b93fe834864da
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4756d0eab4ed189241f377c07acc156ebf4b01476ffc8b69075c88c2114ac699
+oid sha256:f239e57b942ee647b17dac8c1945f09f3b95d620188816a6171b8769d8b54205
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5f2e2bdb5f9347c6488573f4667e028dcc445e98cb15d98763f2bd4040df601
+oid sha256:8b1ac2c82891b027eedc66f777d086405e7b2042df7fade010998384934d96a4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad18e395e4c173ebd8d13ec812b9f2de705d975b9455b70c13c90133ee0adc0e
+oid sha256:d373e4d8b7227f20c87a02bd9850a7a3a4ac824c2bf7db64daad6969c78c0d8c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29e89e0e13229f35fbf9ea5d93ed50d14db103c2f00e4eea3013bc38f5427c0f
+oid sha256:e576adba8e76aec4ab2b83c120502ddf3a568d54069b72db37b39dce27cd0c4f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c77879e60ee9918dca9ee74444f4facc22549bc4b33e1f3b4ec2567a13d5235
+oid sha256:d9b8e19246f26d1beff5836f967c56b08321b799609c46355c1b08adb27aa430
 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": 0.07491393387317657,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.33444816053511706,
+  "best_metric": 0.06366079300642014,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6688963210702341,
   "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": 24.49,
       "eval_steps_per_second": 6.367,
       "step": 25
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.2125326544046402,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0277,
+      "step": 26
+    },
+    {
+      "epoch": 0.3612040133779264,
+      "grad_norm": 0.2617689371109009,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0363,
+      "step": 27
+    },
+    {
+      "epoch": 0.3745819397993311,
+      "grad_norm": 0.3152575194835663,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0425,
+      "step": 28
+    },
+    {
+      "epoch": 0.3879598662207358,
+      "grad_norm": 0.3223755359649658,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0452,
+      "step": 29
+    },
+    {
+      "epoch": 0.4013377926421405,
+      "grad_norm": 0.3094390034675598,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0455,
+      "step": 30
+    },
+    {
+      "epoch": 0.41471571906354515,
+      "grad_norm": 0.59200119972229,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0743,
+      "step": 31
+    },
+    {
+      "epoch": 0.4280936454849498,
+      "grad_norm": 0.4043537676334381,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0678,
+      "step": 32
+    },
+    {
+      "epoch": 0.4414715719063545,
+      "grad_norm": 0.5670768618583679,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0713,
+      "step": 33
+    },
+    {
+      "epoch": 0.45484949832775917,
+      "grad_norm": 0.5830342769622803,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0739,
+      "step": 34
+    },
+    {
+      "epoch": 0.4682274247491639,
+      "grad_norm": 0.6221596002578735,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0888,
+      "step": 35
+    },
+    {
+      "epoch": 0.4816053511705686,
+      "grad_norm": 1.2166249752044678,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1063,
+      "step": 36
+    },
+    {
+      "epoch": 0.49498327759197325,
+      "grad_norm": 0.6762146353721619,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1332,
+      "step": 37
+    },
+    {
+      "epoch": 0.5083612040133779,
+      "grad_norm": 0.3584815561771393,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0427,
+      "step": 38
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.2325064241886139,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0389,
+      "step": 39
+    },
+    {
+      "epoch": 0.5351170568561873,
+      "grad_norm": 0.35842856764793396,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0469,
+      "step": 40
+    },
+    {
+      "epoch": 0.5484949832775919,
+      "grad_norm": 0.22800928354263306,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0406,
+      "step": 41
+    },
+    {
+      "epoch": 0.5618729096989966,
+      "grad_norm": 0.3128259479999542,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0479,
+      "step": 42
+    },
+    {
+      "epoch": 0.5752508361204013,
+      "grad_norm": 0.33522772789001465,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0537,
+      "step": 43
+    },
+    {
+      "epoch": 0.5886287625418061,
+      "grad_norm": 0.3280828297138214,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0474,
+      "step": 44
+    },
+    {
+      "epoch": 0.6020066889632107,
+      "grad_norm": 0.37720221281051636,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0659,
+      "step": 45
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.4423535168170929,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0666,
+      "step": 46
+    },
+    {
+      "epoch": 0.6287625418060201,
+      "grad_norm": 0.470283180475235,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0855,
+      "step": 47
+    },
+    {
+      "epoch": 0.6421404682274248,
+      "grad_norm": 0.67109215259552,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1084,
+      "step": 48
+    },
+    {
+      "epoch": 0.6555183946488294,
+      "grad_norm": 0.5484521389007568,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.091,
+      "step": 49
+    },
+    {
+      "epoch": 0.6688963210702341,
+      "grad_norm": 0.7168601751327515,
+      "learning_rate": 1e-05,
+      "loss": 0.1054,
+      "step": 50
+    },
+    {
+      "epoch": 0.6688963210702341,
+      "eval_loss": 0.06366079300642014,
+      "eval_runtime": 2.0413,
+      "eval_samples_per_second": 24.495,
+      "eval_steps_per_second": 6.369,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null