Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e744f69a20998b7c4cac0e7522ad75960187d35f426b77da2d7214b5f0fe8c2
+oid sha256:f64ec1511b19d17226b80ba569807be85d2c24608aacbf58538f18bd0c051523
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d53b640c9f385db8dda6af15e93e7f5e75a55e03f439a9a904fa069d1eae77
+oid sha256:c3da6b9311ee779335be9752e6b93e853cce9870b947a723513a09811588a581
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96f8737cfb8db410f7609929b1100e41fb71b2e7c9ebcaedbc99749bfae8d136
+oid sha256:e2f9a16272a3cf8b3f1cae03bfecd2ca0eecf3988b16f6a69c40e2c47b39a4fc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18f0a2b45c5d96299cc18b8c2fdd020291b44a88965a3e92e77045fc7f91267e
+oid sha256:4c8e96229eb8c5c66147bcf1025f2ac62ccb2fbf8cb8a140e4042a08295438b8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3b6f9b42743fcf3f1d34a78560664ac4aad943dee9280f45acc8f7108a33a43
+oid sha256:c1375358d9a695670af23e33bb8f1c2710512e5495e0f2736d0cee705784aeb1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb1fab8035824296cdbe662b0971c8e62c67afaac0d7d5ba86b970c77b5af2b
+oid sha256:9ff1d0deeb41f4600ea1371b03f2a948b92e13a536aeeae1d92332cad54240ff
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
+oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7727236747741699,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.017726960491036805,
+  "best_metric": 0.7449390292167664,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.02659044073655521,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 34.927,
       "eval_steps_per_second": 9.081,
       "step": 50
+    },
+    {
+      "epoch": 0.018081499700857543,
+      "grad_norm": 0.724443793296814,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 0.9597,
+      "step": 51
+    },
+    {
+      "epoch": 0.018436038910678278,
+      "grad_norm": 0.7282636761665344,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 0.9182,
+      "step": 52
+    },
+    {
+      "epoch": 0.018790578120499012,
+      "grad_norm": 0.6671382188796997,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 0.7908,
+      "step": 53
+    },
+    {
+      "epoch": 0.01914511733031975,
+      "grad_norm": 0.7780370116233826,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 0.8091,
+      "step": 54
+    },
+    {
+      "epoch": 0.019499656540140485,
+      "grad_norm": 0.810192346572876,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 0.7749,
+      "step": 55
+    },
+    {
+      "epoch": 0.019854195749961223,
+      "grad_norm": 0.7341954112052917,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 0.6715,
+      "step": 56
+    },
+    {
+      "epoch": 0.020208734959781958,
+      "grad_norm": 0.7532359957695007,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 0.6982,
+      "step": 57
+    },
+    {
+      "epoch": 0.020563274169602696,
+      "grad_norm": 0.7728514075279236,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 0.668,
+      "step": 58
+    },
+    {
+      "epoch": 0.02091781337942343,
+      "grad_norm": 0.6659958958625793,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 0.5427,
+      "step": 59
+    },
+    {
+      "epoch": 0.021272352589244165,
+      "grad_norm": 0.6720303893089294,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 0.466,
+      "step": 60
+    },
+    {
+      "epoch": 0.021626891799064903,
+      "grad_norm": 0.6820637583732605,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 0.429,
+      "step": 61
+    },
+    {
+      "epoch": 0.021981431008885638,
+      "grad_norm": 0.8596479892730713,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.4649,
+      "step": 62
+    },
+    {
+      "epoch": 0.022335970218706376,
+      "grad_norm": 0.6639199256896973,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 0.5984,
+      "step": 63
+    },
+    {
+      "epoch": 0.02269050942852711,
+      "grad_norm": 0.7899975180625916,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 1.0047,
+      "step": 64
+    },
+    {
+      "epoch": 0.02304504863834785,
+      "grad_norm": 0.878670871257782,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 0.9028,
+      "step": 65
+    },
+    {
+      "epoch": 0.023399587848168583,
+      "grad_norm": 1.0611952543258667,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 0.925,
+      "step": 66
+    },
+    {
+      "epoch": 0.023754127057989318,
+      "grad_norm": 0.7318688631057739,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 0.7136,
+      "step": 67
+    },
+    {
+      "epoch": 0.024108666267810056,
+      "grad_norm": 0.7990502715110779,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 0.6471,
+      "step": 68
+    },
+    {
+      "epoch": 0.02446320547763079,
+      "grad_norm": 0.7018380761146545,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 0.7014,
+      "step": 69
+    },
+    {
+      "epoch": 0.02481774468745153,
+      "grad_norm": 0.6606969833374023,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 0.6384,
+      "step": 70
+    },
+    {
+      "epoch": 0.025172283897272264,
+      "grad_norm": 0.7007325291633606,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 0.4989,
+      "step": 71
+    },
+    {
+      "epoch": 0.025526823107093,
+      "grad_norm": 0.7680234313011169,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 0.5995,
+      "step": 72
+    },
+    {
+      "epoch": 0.025881362316913736,
+      "grad_norm": 0.712881326675415,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 0.4674,
+      "step": 73
+    },
+    {
+      "epoch": 0.02623590152673447,
+      "grad_norm": 0.7732957005500793,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 0.5283,
+      "step": 74
+    },
+    {
+      "epoch": 0.02659044073655521,
+      "grad_norm": 0.6836099028587341,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 0.3073,
+      "step": 75
+    },
+    {
+      "epoch": 0.02659044073655521,
+      "eval_loss": 0.7449390292167664,
+      "eval_runtime": 1.4311,
+      "eval_samples_per_second": 34.938,
+      "eval_steps_per_second": 9.084,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.624936571695268e+17,
+  "total_flos": 8.436965477019812e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null