Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7935fc538612315456f3e6854825494b4ccc75b706c0265a54be8bdc35889574
+oid sha256:4f53f570ed3653cb2fc9c78f9195158da142a019cf241ebe3d4629a51ac4874a
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143ec2f87d3834fc9898627fbd9f20f89ac14a46a6af38be7461ec68d6c7e393
+oid sha256:e87837181772fde7c3915e0f274cb6f401041d742e13a8a06bd42586219c9b7f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0e44b57b8af2a80350c058aeb8c64d834b95902370ce455b83f6b2fb9753f6
+oid sha256:d26c1ba1b6f64d8858fc93230fbbe3233960f9b3d3d0cb875b6023ac566c4d0a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:422cf7b5b3091d709c0622f00d288b655bcb2dfcd8a161fefeb555521403d647
+oid sha256:eed759bf953ffa0f1ca393f5ae5446a788f0ab716410a0c731b21931cebde7c8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9232908a6e9250cf081f60238c243cf657b4ac92ed113c1e9b623ffe62d9df6c
+oid sha256:abb0723da420c896945d930632717eb036fd77328d9fd0fb9b597a6cb63824f9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4af3d1ca898d6bb006743061bd3443bc0f37fbfbec3aa48be30495e536fcaec
+oid sha256:82c29fe0821a6dab22b42ad5845bed47380da5a49d727435a5216e64a7a875fb
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.58062744140625,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.39254170755642787,
+  "best_metric": 0.4769541323184967,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7850834151128557,
   "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": 25.642,
       "eval_steps_per_second": 3.22,
       "step": 25
+    },
+    {
+      "epoch": 0.408243375858685,
+      "grad_norm": 36.78559112548828,
+      "learning_rate": 5e-05,
+      "loss": 0.8095,
+      "step": 26
+    },
+    {
+      "epoch": 0.4239450441609421,
+      "grad_norm": 91.48822784423828,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3609,
+      "step": 27
+    },
+    {
+      "epoch": 0.4396467124631992,
+      "grad_norm": 112.85855102539062,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.45,
+      "step": 28
+    },
+    {
+      "epoch": 0.4553483807654563,
+      "grad_norm": 35.0981559753418,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4484,
+      "step": 29
+    },
+    {
+      "epoch": 0.47105004906771347,
+      "grad_norm": 35.688232421875,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5243,
+      "step": 30
+    },
+    {
+      "epoch": 0.4867517173699706,
+      "grad_norm": 26.68511962890625,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4155,
+      "step": 31
+    },
+    {
+      "epoch": 0.5024533856722276,
+      "grad_norm": 31.952564239501953,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4639,
+      "step": 32
+    },
+    {
+      "epoch": 0.5181550539744848,
+      "grad_norm": 29.325927734375,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4836,
+      "step": 33
+    },
+    {
+      "epoch": 0.5338567222767419,
+      "grad_norm": 27.150094985961914,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4913,
+      "step": 34
+    },
+    {
+      "epoch": 0.549558390578999,
+      "grad_norm": 23.984006881713867,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4835,
+      "step": 35
+    },
+    {
+      "epoch": 0.5652600588812562,
+      "grad_norm": 25.365285873413086,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5018,
+      "step": 36
+    },
+    {
+      "epoch": 0.5809617271835132,
+      "grad_norm": 23.533668518066406,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5084,
+      "step": 37
+    },
+    {
+      "epoch": 0.5966633954857704,
+      "grad_norm": 20.562366485595703,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5959,
+      "step": 38
+    },
+    {
+      "epoch": 0.6123650637880275,
+      "grad_norm": 59.9564208984375,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.678,
+      "step": 39
+    },
+    {
+      "epoch": 0.6280667320902846,
+      "grad_norm": 125.5207748413086,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0832,
+      "step": 40
+    },
+    {
+      "epoch": 0.6437684003925417,
+      "grad_norm": 31.455310821533203,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4804,
+      "step": 41
+    },
+    {
+      "epoch": 0.6594700686947988,
+      "grad_norm": 30.415761947631836,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4456,
+      "step": 42
+    },
+    {
+      "epoch": 0.6751717369970559,
+      "grad_norm": 31.347658157348633,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.479,
+      "step": 43
+    },
+    {
+      "epoch": 0.6908734052993131,
+      "grad_norm": 24.028074264526367,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4125,
+      "step": 44
+    },
+    {
+      "epoch": 0.7065750736015701,
+      "grad_norm": 27.257251739501953,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4285,
+      "step": 45
+    },
+    {
+      "epoch": 0.7222767419038273,
+      "grad_norm": 35.830406188964844,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.519,
+      "step": 46
+    },
+    {
+      "epoch": 0.7379784102060843,
+      "grad_norm": 24.885379791259766,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4369,
+      "step": 47
+    },
+    {
+      "epoch": 0.7536800785083415,
+      "grad_norm": 27.403444290161133,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.5016,
+      "step": 48
+    },
+    {
+      "epoch": 0.7693817468105987,
+      "grad_norm": 26.06789779663086,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4896,
+      "step": 49
+    },
+    {
+      "epoch": 0.7850834151128557,
+      "grad_norm": 18.390460968017578,
+      "learning_rate": 0.0,
+      "loss": 0.4831,
+      "step": 50
+    },
+    {
+      "epoch": 0.7850834151128557,
+      "eval_loss": 0.4769541323184967,
+      "eval_runtime": 16.4718,
+      "eval_samples_per_second": 26.105,
+      "eval_steps_per_second": 3.278,
+      "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": 3.3417726519567974e+17,
+  "total_flos": 6.715371720246559e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null