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:a71533fe03d6d5298967c52fe8a3adcd9f58f9bfde5ea1ca92fded50af052345
+oid sha256:3e744f69a20998b7c4cac0e7522ad75960187d35f426b77da2d7214b5f0fe8c2
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97709bd8d8c4f3d5fbc7ea6c9b936a9128092e61fc480fb684fc8b8aa374bc4a
+oid sha256:b9d53b640c9f385db8dda6af15e93e7f5e75a55e03f439a9a904fa069d1eae77
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b6d31cc46b3fdac785b4e257da9a155cd9ffc56f4117a3380bad48dd22d6e21
+oid sha256:96f8737cfb8db410f7609929b1100e41fb71b2e7c9ebcaedbc99749bfae8d136
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d95845af24bb237001e703b7e7c7500ff206982797e8188e4d4583e54688da29
+oid sha256:18f0a2b45c5d96299cc18b8c2fdd020291b44a88965a3e92e77045fc7f91267e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9523f33dac34eaa51608e01e3a143afa57e5b297a1d3e88c82c8eac8e33a19
+oid sha256:d3b6f9b42743fcf3f1d34a78560664ac4aad943dee9280f45acc8f7108a33a43
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37851911ccb33a0de34736e35c192d969c66ca74673f9cfdb04e6055cfc12252
+oid sha256:1fb1fab8035824296cdbe662b0971c8e62c67afaac0d7d5ba86b970c77b5af2b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:107607e336ff02e6e3fc135f6b55fc089901c7172808564e7046a8e836a537c9
+oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7849562168121338,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008863480245518402,
+  "best_metric": 0.7727236747741699,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.017726960491036805,
   "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": 34.849,
       "eval_steps_per_second": 9.061,
       "step": 25
+    },
+    {
+      "epoch": 0.009218019455339139,
+      "grad_norm": 0.6689695119857788,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 1.0456,
+      "step": 26
+    },
+    {
+      "epoch": 0.009572558665159875,
+      "grad_norm": 0.8705013990402222,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 1.0945,
+      "step": 27
+    },
+    {
+      "epoch": 0.009927097874980612,
+      "grad_norm": 0.7108039259910583,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 1.0126,
+      "step": 28
+    },
+    {
+      "epoch": 0.010281637084801348,
+      "grad_norm": 0.8193414211273193,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 0.9494,
+      "step": 29
+    },
+    {
+      "epoch": 0.010636176294622083,
+      "grad_norm": 0.8473891019821167,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 0.7592,
+      "step": 30
+    },
+    {
+      "epoch": 0.010990715504442819,
+      "grad_norm": 0.7946711182594299,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 0.7088,
+      "step": 31
+    },
+    {
+      "epoch": 0.011345254714263555,
+      "grad_norm": 0.6517184972763062,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 0.6003,
+      "step": 32
+    },
+    {
+      "epoch": 0.011699793924084292,
+      "grad_norm": 0.6414614915847778,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 0.7046,
+      "step": 33
+    },
+    {
+      "epoch": 0.012054333133905028,
+      "grad_norm": 0.6361235976219177,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 0.5813,
+      "step": 34
+    },
+    {
+      "epoch": 0.012408872343725764,
+      "grad_norm": 0.7114998698234558,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 0.4539,
+      "step": 35
+    },
+    {
+      "epoch": 0.0127634115535465,
+      "grad_norm": 0.5631694793701172,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 0.4299,
+      "step": 36
+    },
+    {
+      "epoch": 0.013117950763367235,
+      "grad_norm": 0.6165447235107422,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 0.3928,
+      "step": 37
+    },
+    {
+      "epoch": 0.013472489973187972,
+      "grad_norm": 0.7139920592308044,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 0.7725,
+      "step": 38
+    },
+    {
+      "epoch": 0.013827029183008708,
+      "grad_norm": 0.7106257081031799,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 0.9712,
+      "step": 39
+    },
+    {
+      "epoch": 0.014181568392829445,
+      "grad_norm": 0.7304429411888123,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 0.8644,
+      "step": 40
+    },
+    {
+      "epoch": 0.014536107602650181,
+      "grad_norm": 0.6472069025039673,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 0.7419,
+      "step": 41
+    },
+    {
+      "epoch": 0.014890646812470917,
+      "grad_norm": 0.8418741822242737,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 0.7852,
+      "step": 42
+    },
+    {
+      "epoch": 0.015245186022291652,
+      "grad_norm": 0.7708389759063721,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.6849,
+      "step": 43
+    },
+    {
+      "epoch": 0.015599725232112388,
+      "grad_norm": 0.7205597758293152,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 0.6503,
+      "step": 44
+    },
+    {
+      "epoch": 0.015954264441933125,
+      "grad_norm": 0.731856107711792,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 0.645,
+      "step": 45
+    },
+    {
+      "epoch": 0.016308803651753863,
+      "grad_norm": 0.7058491110801697,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 0.5082,
+      "step": 46
+    },
+    {
+      "epoch": 0.016663342861574598,
+      "grad_norm": 0.7743491530418396,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 0.5277,
+      "step": 47
+    },
+    {
+      "epoch": 0.017017882071395332,
+      "grad_norm": 0.9558595418930054,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 0.5754,
+      "step": 48
+    },
+    {
+      "epoch": 0.01737242128121607,
+      "grad_norm": 0.8757135272026062,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 0.5726,
+      "step": 49
+    },
+    {
+      "epoch": 0.017726960491036805,
+      "grad_norm": 0.6394727230072021,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 0.3937,
+      "step": 50
+    },
+    {
+      "epoch": 0.017726960491036805,
+      "eval_loss": 0.7727236747741699,
+      "eval_runtime": 1.4316,
+      "eval_samples_per_second": 34.927,
+      "eval_steps_per_second": 9.081,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.812907666370724e+17,
+  "total_flos": 5.624936571695268e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null