Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:077928d6ff4c80eeac65f6fea72c6bda6c34bc2094c6966ab601383e0f3cbe71
+oid sha256:d864edf03ad525152b610034e8ad694535b90ec4b71b0be901cabff29f27e396
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbb9cd04cf667f9cb9b7cf93a9c9c31e4a5b418fa287c0af2d1c4b3f08ff5d1b
+oid sha256:831c6a708f125d4eeafe866a7a71e194b006f311dff79038a3614a831d46cbb1
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c271fb5c073f7847d965c511f9b4533afb801c7bcaa0b30596cfd393357e04
+oid sha256:66b307030e07ed8552b719b147330286fef78e0c146e123ad511de2d3e53d69a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1c5cb0bd229cef1d7b53f7b5b7adf5c1d404e9d4960a3e391a64834a33b916
+oid sha256:44001af3ba3ed1ca087428b810bc2c0de898580d8145d945a30c87d1f685bf27
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51bcccc78d82357868cdee7f1038b8985e7a0754063793e22e8c1360325cb0df
+oid sha256:3f519cc9126970242334a0dcb8f1bf647ba826f053c0d42555b8b6bc1c12c9de
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2dee79c5b250a575bd3e4fbd5a7424b54b6522dd1f7390134c9fd42fdb654e
+oid sha256:a8e40ba9ec1ba8fd4cf5fb774f6f57986435ac058acf5ca1ed12fd889c163174
 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": 1.6289045810699463,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.966183574879227,
+  "best_metric": 1.372193455696106,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9347826086956523,
   "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": 39.41,
       "eval_steps_per_second": 10.247,
       "step": 25
+    },
+    {
+      "epoch": 1.0072463768115942,
+      "grad_norm": 2.7831952571868896,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.0748,
+      "step": 26
+    },
+    {
+      "epoch": 1.0458937198067633,
+      "grad_norm": 2.014694929122925,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.9726,
+      "step": 27
+    },
+    {
+      "epoch": 1.0845410628019323,
+      "grad_norm": 1.541536569595337,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.9017,
+      "step": 28
+    },
+    {
+      "epoch": 1.1231884057971016,
+      "grad_norm": 3.653707504272461,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.7134,
+      "step": 29
+    },
+    {
+      "epoch": 1.1618357487922706,
+      "grad_norm": 4.211123943328857,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.4641,
+      "step": 30
+    },
+    {
+      "epoch": 1.2004830917874396,
+      "grad_norm": 3.187204360961914,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.4011,
+      "step": 31
+    },
+    {
+      "epoch": 1.2391304347826086,
+      "grad_norm": 2.7480978965759277,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.4607,
+      "step": 32
+    },
+    {
+      "epoch": 1.2777777777777777,
+      "grad_norm": 2.39614200592041,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.0324,
+      "step": 33
+    },
+    {
+      "epoch": 1.316425120772947,
+      "grad_norm": 3.0056447982788086,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.8739,
+      "step": 34
+    },
+    {
+      "epoch": 1.355072463768116,
+      "grad_norm": 3.2308599948883057,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.811,
+      "step": 35
+    },
+    {
+      "epoch": 1.393719806763285,
+      "grad_norm": 2.4190244674682617,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.4012,
+      "step": 36
+    },
+    {
+      "epoch": 1.432367149758454,
+      "grad_norm": 2.9130115509033203,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.3067,
+      "step": 37
+    },
+    {
+      "epoch": 1.471014492753623,
+      "grad_norm": 2.56050443649292,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.4833,
+      "step": 38
+    },
+    {
+      "epoch": 1.5096618357487923,
+      "grad_norm": 2.319148540496826,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.7662,
+      "step": 39
+    },
+    {
+      "epoch": 1.5483091787439613,
+      "grad_norm": 2.010082721710205,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.786,
+      "step": 40
+    },
+    {
+      "epoch": 1.5869565217391304,
+      "grad_norm": 2.326204299926758,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.7224,
+      "step": 41
+    },
+    {
+      "epoch": 1.6256038647342996,
+      "grad_norm": 2.6092209815979004,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.4101,
+      "step": 42
+    },
+    {
+      "epoch": 1.6642512077294684,
+      "grad_norm": 3.253211498260498,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.175,
+      "step": 43
+    },
+    {
+      "epoch": 1.7028985507246377,
+      "grad_norm": 2.6981844902038574,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1852,
+      "step": 44
+    },
+    {
+      "epoch": 1.7415458937198067,
+      "grad_norm": 2.8664114475250244,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.5638,
+      "step": 45
+    },
+    {
+      "epoch": 1.7801932367149758,
+      "grad_norm": 2.2756621837615967,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.8545,
+      "step": 46
+    },
+    {
+      "epoch": 1.818840579710145,
+      "grad_norm": 2.5986602306365967,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.6885,
+      "step": 47
+    },
+    {
+      "epoch": 1.857487922705314,
+      "grad_norm": 2.4868955612182617,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.3364,
+      "step": 48
+    },
+    {
+      "epoch": 1.896135265700483,
+      "grad_norm": 2.897385835647583,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.144,
+      "step": 49
+    },
+    {
+      "epoch": 1.9347826086956523,
+      "grad_norm": 2.7919833660125732,
+      "learning_rate": 1e-05,
+      "loss": 1.1587,
+      "step": 50
+    },
+    {
+      "epoch": 1.9347826086956523,
+      "eval_loss": 1.372193455696106,
+      "eval_runtime": 1.263,
+      "eval_samples_per_second": 39.59,
+      "eval_steps_per_second": 10.293,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null