Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eaaba4383f96e74ba7e976e59d6ce34beaec0c7c29785099fa09cf23ab8c9b9
+oid sha256:05c8e9d11e7fc919d670bda75c4932c0cfcc244e352468bfc14caca673e76985
 size 60599872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f19b6385778aaea396b2e46c49b57c668cfdc851ae4cb4793e0217b5163c2a7
+oid sha256:2d32b0c3e86e49304cbcac118466ea34278a89199fdc753c3951d5d4e0896156
 size 121392706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:305a5a4bd1932ee0fa7e5707300581b36feb7e9150618a8629ef7fdb4fdf7f44
+oid sha256:96e8f18e6aafaa8dd901e30cda750d2edb12d13926daa92dc0f5263b4b609f04
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc85fd830541e07aee2d432bdc7bc8741d7b9dea2e2c69c603b347b4ac1bf36a
+oid sha256:8203f27a0cd73250e1262825553bf6707967dc95c36a751fbb663c4908a3a1cb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd7745041fe1af15413e11dfea2c78e38a8061ce61d5a47f7fd7a4d7e06f3967
+oid sha256:0dcd4519d06e98e994e758d0dffc6a997c12d68bac8aadfe24e49fe67d47b92e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9681701fb3413302ecf9b137ff9209f2fd5f78092ab627d75e1e2fd30889321
+oid sha256:fa64fc5c261f7c924168aa49586df19ffb0d9d2ef2325e09958c545ca45d5734
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af915b3bd1f4e2109b462a6794b6020da77edbf1d90b3213a0a05f6b1d4f617
+oid sha256:9a2759c51def6f12ecf076b0cf2571dc6049a636d579f7f0a8bd8ae37daff96c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7816668152809143,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.9047619047619047,
+  "epoch": 3.0476190476190474,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,111 @@
       "eval_samples_per_second": 61.93,
       "eval_steps_per_second": 8.35,
       "step": 25
+    },
+    {
+      "epoch": 1.980952380952381,
+      "grad_norm": 1.8537710905075073,
+      "learning_rate": 2.991522876735154e-05,
+      "loss": 0.8075,
+      "step": 26
+    },
+    {
+      "epoch": 2.057142857142857,
+      "grad_norm": 4.3167877197265625,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 1.6816,
+      "step": 27
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 1.303170084953308,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.7296,
+      "step": 28
+    },
+    {
+      "epoch": 2.2095238095238097,
+      "grad_norm": 0.8555645942687988,
+      "learning_rate": 1.928936436551661e-05,
+      "loss": 0.7464,
+      "step": 29
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 1.9755239486694336,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 0.8273,
+      "step": 30
+    },
+    {
+      "epoch": 2.361904761904762,
+      "grad_norm": 0.9826189279556274,
+      "learning_rate": 1.3213804466343421e-05,
+      "loss": 0.7493,
+      "step": 31
+    },
+    {
+      "epoch": 2.4380952380952383,
+      "grad_norm": 1.0805027484893799,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 0.7082,
+      "step": 32
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 2.661658763885498,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 0.8094,
+      "step": 33
+    },
+    {
+      "epoch": 2.5904761904761906,
+      "grad_norm": 0.8846949934959412,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 0.76,
+      "step": 34
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.78202885389328,
+      "learning_rate": 4.2113336672471245e-06,
+      "loss": 0.7303,
+      "step": 35
+    },
+    {
+      "epoch": 2.742857142857143,
+      "grad_norm": 2.5152831077575684,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.8183,
+      "step": 36
+    },
+    {
+      "epoch": 2.819047619047619,
+      "grad_norm": 1.0229064226150513,
+      "learning_rate": 1.5299867030334814e-06,
+      "loss": 0.76,
+      "step": 37
+    },
+    {
+      "epoch": 2.895238095238095,
+      "grad_norm": 1.0677152872085571,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 0.7601,
+      "step": 38
+    },
+    {
+      "epoch": 2.9714285714285715,
+      "grad_norm": 0.9534644484519958,
+      "learning_rate": 1.7077534966650766e-07,
+      "loss": 0.8042,
+      "step": 39
+    },
+    {
+      "epoch": 3.0476190476190474,
+      "grad_norm": 3.0677850246429443,
+      "learning_rate": 0.0,
+      "loss": 1.4891,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -221,12 +326,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.54445405339648e+16,
+  "total_flos": 4.071126485434368e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null