Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650dedbd65ed8ada61c79194d2074e4cae4211f8b2eaa1a07d5dd25721dca9de
+oid sha256:39f6ec5e695e0730d16c8bb003fcfd5805616e05fddeeda39984d29d791a38b1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae290d789bc3b4ea00a8baa3fb410e5726ecec42af635b57ec17873076aa4b6f
+oid sha256:e6337cd4486db553bfbe3b8530ce7a5ab95dcaf30b97219bf7c1a66f07fa5469
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34874f8d33b21b775453e0e71fd545173fed77e5dc8d98049f935fc48988e3c9
+oid sha256:6d96ac5570a23b49612b916e40caa01313627a6ad3907270e44de694a974fba7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1af827c40fe6080db8759e4c450a7f819cf211b52e79cab130bdc4dcea3da8d0
+oid sha256:0803f76bd021d5bd7af4ddd99e73972cc87bed5ceeb3889069b0f848867f63c6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d92a579c1c03ff65126c0649b5701a3cdc954e57da14cc6eb91319f9be0ca0e2
+oid sha256:893de1b728c80c56bd0d133dfc8fc0f650d6aef025b59ce550dee8a21cfecb7b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af40746b50805262a21c422db8c8a3d45e005933131d3305576c77b6eeba21f
+oid sha256:4cdf4e9bd31db603a1231a8b08e4d9667cf917751dd5226f69670717e4c36d3a
 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": 0.062130194157361984,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.041390728476821195,
+  "best_metric": 0.04558004438877106,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08278145695364239,
   "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": 10.553,
       "eval_steps_per_second": 2.744,
       "step": 25
+    },
+    {
+      "epoch": 0.04304635761589404,
+      "grad_norm": 18.362220764160156,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.9944,
+      "step": 26
+    },
+    {
+      "epoch": 0.04470198675496689,
+      "grad_norm": 14.467948913574219,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.5698,
+      "step": 27
+    },
+    {
+      "epoch": 0.046357615894039736,
+      "grad_norm": 10.935425758361816,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.431,
+      "step": 28
+    },
+    {
+      "epoch": 0.048013245033112585,
+      "grad_norm": 13.532536506652832,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2851,
+      "step": 29
+    },
+    {
+      "epoch": 0.04966887417218543,
+      "grad_norm": 12.513880729675293,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9102,
+      "step": 30
+    },
+    {
+      "epoch": 0.05132450331125828,
+      "grad_norm": 11.555468559265137,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9628,
+      "step": 31
+    },
+    {
+      "epoch": 0.052980132450331126,
+      "grad_norm": 9.1250638961792,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9299,
+      "step": 32
+    },
+    {
+      "epoch": 0.054635761589403975,
+      "grad_norm": 9.583466529846191,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.6304,
+      "step": 33
+    },
+    {
+      "epoch": 0.056291390728476824,
+      "grad_norm": 8.946598052978516,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.604,
+      "step": 34
+    },
+    {
+      "epoch": 0.057947019867549666,
+      "grad_norm": 7.715593338012695,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3239,
+      "step": 35
+    },
+    {
+      "epoch": 0.059602649006622516,
+      "grad_norm": 6.425172328948975,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1904,
+      "step": 36
+    },
+    {
+      "epoch": 0.061258278145695365,
+      "grad_norm": 2.9484758377075195,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1138,
+      "step": 37
+    },
+    {
+      "epoch": 0.06291390728476821,
+      "grad_norm": 8.604011535644531,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7746,
+      "step": 38
+    },
+    {
+      "epoch": 0.06456953642384106,
+      "grad_norm": 10.981115341186523,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.4488,
+      "step": 39
+    },
+    {
+      "epoch": 0.06622516556291391,
+      "grad_norm": 11.29909610748291,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.3395,
+      "step": 40
+    },
+    {
+      "epoch": 0.06788079470198675,
+      "grad_norm": 9.1647367477417,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.0193,
+      "step": 41
+    },
+    {
+      "epoch": 0.0695364238410596,
+      "grad_norm": 9.12201976776123,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8432,
+      "step": 42
+    },
+    {
+      "epoch": 0.07119205298013245,
+      "grad_norm": 7.879044055938721,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6872,
+      "step": 43
+    },
+    {
+      "epoch": 0.0728476821192053,
+      "grad_norm": 8.544329643249512,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6767,
+      "step": 44
+    },
+    {
+      "epoch": 0.07450331125827815,
+      "grad_norm": 12.571453094482422,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.7462,
+      "step": 45
+    },
+    {
+      "epoch": 0.076158940397351,
+      "grad_norm": 11.54553508758545,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.597,
+      "step": 46
+    },
+    {
+      "epoch": 0.07781456953642384,
+      "grad_norm": 8.826517105102539,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.5232,
+      "step": 47
+    },
+    {
+      "epoch": 0.07947019867549669,
+      "grad_norm": 4.924127101898193,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1508,
+      "step": 48
+    },
+    {
+      "epoch": 0.08112582781456953,
+      "grad_norm": 9.258513450622559,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.2354,
+      "step": 49
+    },
+    {
+      "epoch": 0.08278145695364239,
+      "grad_norm": 3.3494489192962646,
+      "learning_rate": 1e-05,
+      "loss": 0.0511,
+      "step": 50
+    },
+    {
+      "epoch": 0.08278145695364239,
+      "eval_loss": 0.04558004438877106,
+      "eval_runtime": 4.7215,
+      "eval_samples_per_second": 10.59,
+      "eval_steps_per_second": 2.753,
+      "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": 2.8307787998035968e+17,
+  "total_flos": 5.659789468945613e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null