End of training
Browse files- README.md +3 -3
- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Jun03_09-07-00_40d03c630f49/events.out.tfevents.1717415353.40d03c630f49.1.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +526 -85
README.md
CHANGED
|
@@ -22,7 +22,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
+
value: 0.8425624321389794
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.4046
|
| 36 |
+
- Accuracy: 0.8426
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy":
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.884169884169884,
|
| 3 |
+
"eval_accuracy": 0.8425624321389794,
|
| 4 |
+
"eval_loss": 0.4046495258808136,
|
| 5 |
+
"eval_runtime": 106.7707,
|
| 6 |
+
"eval_samples_per_second": 8.626,
|
| 7 |
+
"eval_steps_per_second": 0.272,
|
| 8 |
+
"total_flos": 2.0360358039744737e+18,
|
| 9 |
+
"train_loss": 0.45154881179332734,
|
| 10 |
+
"train_runtime": 9581.2043,
|
| 11 |
+
"train_samples_per_second": 8.649,
|
| 12 |
+
"train_steps_per_second": 0.067
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy":
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.884169884169884,
|
| 3 |
+
"eval_accuracy": 0.8425624321389794,
|
| 4 |
+
"eval_loss": 0.4046495258808136,
|
| 5 |
+
"eval_runtime": 106.7707,
|
| 6 |
+
"eval_samples_per_second": 8.626,
|
| 7 |
+
"eval_steps_per_second": 0.272
|
| 8 |
}
|
runs/Jun03_09-07-00_40d03c630f49/events.out.tfevents.1717415353.40d03c630f49.1.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cf545dd3d90d66b2aed8c792e245fd50bcf9d8f2c78c83e654bcd7f8f3e3f7e
|
| 3 |
+
size 363
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.884169884169884,
|
| 3 |
+
"total_flos": 2.0360358039744737e+18,
|
| 4 |
+
"train_loss": 0.45154881179332734,
|
| 5 |
+
"train_runtime": 9581.2043,
|
| 6 |
+
"train_samples_per_second": 8.649,
|
| 7 |
+
"train_steps_per_second": 0.067
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,122 +1,563 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch":
|
| 13 |
-
"
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
-
"
|
| 17 |
-
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
},
|
| 20 |
{
|
| 21 |
-
"epoch": 2.
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"eval_steps_per_second": 0.512,
|
| 27 |
-
"step": 2
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch":
|
| 31 |
-
"
|
| 32 |
-
"
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
|
| 36 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
},
|
| 38 |
{
|
| 39 |
"epoch": 4.0,
|
| 40 |
-
"eval_accuracy": 0.
|
| 41 |
-
"eval_loss": 0.
|
| 42 |
-
"eval_runtime":
|
| 43 |
-
"eval_samples_per_second":
|
| 44 |
-
"eval_steps_per_second": 0.
|
| 45 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
},
|
| 47 |
{
|
| 48 |
-
"epoch":
|
| 49 |
-
"eval_accuracy":
|
| 50 |
-
"eval_loss": 0.
|
| 51 |
-
"eval_runtime":
|
| 52 |
-
"eval_samples_per_second":
|
| 53 |
-
"eval_steps_per_second": 0.
|
| 54 |
-
"step":
|
| 55 |
},
|
| 56 |
{
|
| 57 |
-
"epoch":
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
"eval_steps_per_second": 0.436,
|
| 63 |
-
"step": 6
|
| 64 |
},
|
| 65 |
{
|
| 66 |
-
"epoch":
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
"
|
| 71 |
-
|
| 72 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 8.0,
|
| 76 |
-
"eval_accuracy":
|
| 77 |
-
"eval_loss": 0.
|
| 78 |
-
"eval_runtime":
|
| 79 |
-
"eval_samples_per_second":
|
| 80 |
-
"eval_steps_per_second": 0.
|
| 81 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 82 |
},
|
| 83 |
{
|
| 84 |
-
"epoch":
|
| 85 |
-
"
|
| 86 |
-
"
|
| 87 |
-
"
|
| 88 |
-
"
|
| 89 |
-
"eval_steps_per_second": 0.531,
|
| 90 |
-
"step": 9
|
| 91 |
},
|
| 92 |
{
|
| 93 |
-
"epoch":
|
| 94 |
-
"grad_norm":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
"learning_rate": 0.0,
|
| 96 |
-
"loss": 0.
|
| 97 |
-
"step":
|
| 98 |
},
|
| 99 |
{
|
| 100 |
-
"epoch":
|
| 101 |
-
"eval_accuracy":
|
| 102 |
-
"eval_loss": 0.
|
| 103 |
-
"eval_runtime":
|
| 104 |
-
"eval_samples_per_second":
|
| 105 |
-
"eval_steps_per_second": 0.
|
| 106 |
-
"step":
|
| 107 |
},
|
| 108 |
{
|
| 109 |
-
"epoch":
|
| 110 |
-
"step":
|
| 111 |
-
"total_flos":
|
| 112 |
-
"train_loss": 0.
|
| 113 |
-
"train_runtime":
|
| 114 |
-
"train_samples_per_second":
|
| 115 |
-
"train_steps_per_second": 0.
|
| 116 |
}
|
| 117 |
],
|
| 118 |
"logging_steps": 10,
|
| 119 |
-
"max_steps":
|
| 120 |
"num_input_tokens_seen": 0,
|
| 121 |
"num_train_epochs": 10,
|
| 122 |
"save_steps": 500,
|
|
@@ -132,7 +573,7 @@
|
|
| 132 |
"attributes": {}
|
| 133 |
}
|
| 134 |
},
|
| 135 |
-
"total_flos":
|
| 136 |
"train_batch_size": 32,
|
| 137 |
"trial_name": null,
|
| 138 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8425624321389794,
|
| 3 |
+
"best_model_checkpoint": "swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification/checkpoint-453",
|
| 4 |
+
"epoch": 9.884169884169884,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 640,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.15444015444015444,
|
| 13 |
+
"grad_norm": 6.145582675933838,
|
| 14 |
+
"learning_rate": 7.8125e-06,
|
| 15 |
+
"loss": 1.1143,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.3088803088803089,
|
| 20 |
+
"grad_norm": 4.804866313934326,
|
| 21 |
+
"learning_rate": 1.5625e-05,
|
| 22 |
+
"loss": 0.9049,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.46332046332046334,
|
| 27 |
+
"grad_norm": 4.023855686187744,
|
| 28 |
+
"learning_rate": 2.34375e-05,
|
| 29 |
+
"loss": 0.8321,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.6177606177606177,
|
| 34 |
+
"grad_norm": 5.751364707946777,
|
| 35 |
+
"learning_rate": 3.125e-05,
|
| 36 |
+
"loss": 0.7323,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7722007722007722,
|
| 41 |
+
"grad_norm": 4.711376667022705,
|
| 42 |
+
"learning_rate": 3.90625e-05,
|
| 43 |
+
"loss": 0.6296,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.9266409266409267,
|
| 48 |
+
"grad_norm": 5.55043363571167,
|
| 49 |
+
"learning_rate": 4.6875e-05,
|
| 50 |
+
"loss": 0.5809,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.9884169884169884,
|
| 55 |
+
"eval_accuracy": 0.7937024972855592,
|
| 56 |
+
"eval_loss": 0.5023894309997559,
|
| 57 |
+
"eval_runtime": 107.4922,
|
| 58 |
+
"eval_samples_per_second": 8.568,
|
| 59 |
+
"eval_steps_per_second": 0.27,
|
| 60 |
+
"step": 64
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 1.0810810810810811,
|
| 64 |
+
"grad_norm": 4.052460670471191,
|
| 65 |
+
"learning_rate": 4.947916666666667e-05,
|
| 66 |
+
"loss": 0.5564,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.2355212355212355,
|
| 71 |
+
"grad_norm": 4.5774359703063965,
|
| 72 |
+
"learning_rate": 4.8611111111111115e-05,
|
| 73 |
+
"loss": 0.5529,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.3899613899613898,
|
| 78 |
+
"grad_norm": 7.030020713806152,
|
| 79 |
+
"learning_rate": 4.774305555555556e-05,
|
| 80 |
+
"loss": 0.5762,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.5444015444015444,
|
| 85 |
+
"grad_norm": 4.231429100036621,
|
| 86 |
+
"learning_rate": 4.6875e-05,
|
| 87 |
+
"loss": 0.5017,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.698841698841699,
|
| 92 |
+
"grad_norm": 3.0762908458709717,
|
| 93 |
+
"learning_rate": 4.6006944444444444e-05,
|
| 94 |
+
"loss": 0.5173,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.8532818532818531,
|
| 99 |
+
"grad_norm": 3.419095039367676,
|
| 100 |
+
"learning_rate": 4.5138888888888894e-05,
|
| 101 |
+
"loss": 0.5326,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.9922779922779923,
|
| 106 |
+
"eval_accuracy": 0.8132464712269273,
|
| 107 |
+
"eval_loss": 0.4402076005935669,
|
| 108 |
+
"eval_runtime": 106.2614,
|
| 109 |
+
"eval_samples_per_second": 8.667,
|
| 110 |
+
"eval_steps_per_second": 0.273,
|
| 111 |
+
"step": 129
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.0077220077220077,
|
| 115 |
+
"grad_norm": 4.168376445770264,
|
| 116 |
+
"learning_rate": 4.4270833333333337e-05,
|
| 117 |
+
"loss": 0.5082,
|
| 118 |
+
"step": 130
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.1621621621621623,
|
| 122 |
+
"grad_norm": 4.488511562347412,
|
| 123 |
+
"learning_rate": 4.340277777777778e-05,
|
| 124 |
+
"loss": 0.4642,
|
| 125 |
+
"step": 140
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.3166023166023164,
|
| 129 |
+
"grad_norm": 3.359255313873291,
|
| 130 |
+
"learning_rate": 4.253472222222222e-05,
|
| 131 |
+
"loss": 0.4952,
|
| 132 |
+
"step": 150
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"epoch": 2.471042471042471,
|
| 136 |
+
"grad_norm": 4.701355457305908,
|
| 137 |
+
"learning_rate": 4.166666666666667e-05,
|
| 138 |
+
"loss": 0.4925,
|
| 139 |
+
"step": 160
|
|
|
|
|
|
|
| 140 |
},
|
| 141 |
{
|
| 142 |
+
"epoch": 2.6254826254826256,
|
| 143 |
+
"grad_norm": 4.631283283233643,
|
| 144 |
+
"learning_rate": 4.0798611111111115e-05,
|
| 145 |
+
"loss": 0.4795,
|
| 146 |
+
"step": 170
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.7799227799227797,
|
| 150 |
+
"grad_norm": 4.823609352111816,
|
| 151 |
+
"learning_rate": 3.993055555555556e-05,
|
| 152 |
+
"loss": 0.4878,
|
| 153 |
+
"step": 180
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.9343629343629343,
|
| 157 |
+
"grad_norm": 3.890035390853882,
|
| 158 |
+
"learning_rate": 3.90625e-05,
|
| 159 |
+
"loss": 0.4626,
|
| 160 |
+
"step": 190
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.9961389961389964,
|
| 164 |
+
"eval_accuracy": 0.8284473398479913,
|
| 165 |
+
"eval_loss": 0.4243987202644348,
|
| 166 |
+
"eval_runtime": 107.2966,
|
| 167 |
+
"eval_samples_per_second": 8.584,
|
| 168 |
+
"eval_steps_per_second": 0.27,
|
| 169 |
+
"step": 194
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 3.088803088803089,
|
| 173 |
+
"grad_norm": 3.165153741836548,
|
| 174 |
+
"learning_rate": 3.8194444444444444e-05,
|
| 175 |
+
"loss": 0.4434,
|
| 176 |
+
"step": 200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.2432432432432434,
|
| 180 |
+
"grad_norm": 3.860111713409424,
|
| 181 |
+
"learning_rate": 3.7326388888888893e-05,
|
| 182 |
+
"loss": 0.4383,
|
| 183 |
+
"step": 210
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 3.3976833976833976,
|
| 187 |
+
"grad_norm": 7.453273296356201,
|
| 188 |
+
"learning_rate": 3.6458333333333336e-05,
|
| 189 |
+
"loss": 0.4432,
|
| 190 |
+
"step": 220
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.552123552123552,
|
| 194 |
+
"grad_norm": 5.200356483459473,
|
| 195 |
+
"learning_rate": 3.559027777777778e-05,
|
| 196 |
+
"loss": 0.4766,
|
| 197 |
+
"step": 230
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.7065637065637067,
|
| 201 |
+
"grad_norm": 4.4838433265686035,
|
| 202 |
+
"learning_rate": 3.472222222222222e-05,
|
| 203 |
+
"loss": 0.4428,
|
| 204 |
+
"step": 240
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.861003861003861,
|
| 208 |
+
"grad_norm": 3.7621071338653564,
|
| 209 |
+
"learning_rate": 3.385416666666667e-05,
|
| 210 |
+
"loss": 0.4778,
|
| 211 |
+
"step": 250
|
| 212 |
},
|
| 213 |
{
|
| 214 |
"epoch": 4.0,
|
| 215 |
+
"eval_accuracy": 0.8273615635179153,
|
| 216 |
+
"eval_loss": 0.42337119579315186,
|
| 217 |
+
"eval_runtime": 106.8233,
|
| 218 |
+
"eval_samples_per_second": 8.622,
|
| 219 |
+
"eval_steps_per_second": 0.271,
|
| 220 |
+
"step": 259
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 4.015444015444015,
|
| 224 |
+
"grad_norm": 4.093021869659424,
|
| 225 |
+
"learning_rate": 3.2986111111111115e-05,
|
| 226 |
+
"loss": 0.4306,
|
| 227 |
+
"step": 260
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.1698841698841695,
|
| 231 |
+
"grad_norm": 3.669459581375122,
|
| 232 |
+
"learning_rate": 3.211805555555556e-05,
|
| 233 |
+
"loss": 0.4606,
|
| 234 |
+
"step": 270
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.324324324324325,
|
| 238 |
+
"grad_norm": 4.8231892585754395,
|
| 239 |
+
"learning_rate": 3.125e-05,
|
| 240 |
+
"loss": 0.3992,
|
| 241 |
+
"step": 280
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 4.478764478764479,
|
| 245 |
+
"grad_norm": 4.587674617767334,
|
| 246 |
+
"learning_rate": 3.0381944444444444e-05,
|
| 247 |
+
"loss": 0.4024,
|
| 248 |
+
"step": 290
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.633204633204633,
|
| 252 |
+
"grad_norm": 9.029142379760742,
|
| 253 |
+
"learning_rate": 2.951388888888889e-05,
|
| 254 |
+
"loss": 0.4408,
|
| 255 |
+
"step": 300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.787644787644788,
|
| 259 |
+
"grad_norm": 3.7836337089538574,
|
| 260 |
+
"learning_rate": 2.8645833333333333e-05,
|
| 261 |
+
"loss": 0.4332,
|
| 262 |
+
"step": 310
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 4.942084942084942,
|
| 266 |
+
"grad_norm": 5.781239032745361,
|
| 267 |
+
"learning_rate": 2.777777777777778e-05,
|
| 268 |
+
"loss": 0.4109,
|
| 269 |
+
"step": 320
|
| 270 |
},
|
| 271 |
{
|
| 272 |
+
"epoch": 4.988416988416988,
|
| 273 |
+
"eval_accuracy": 0.8306188925081434,
|
| 274 |
+
"eval_loss": 0.4197309613227844,
|
| 275 |
+
"eval_runtime": 106.1724,
|
| 276 |
+
"eval_samples_per_second": 8.675,
|
| 277 |
+
"eval_steps_per_second": 0.273,
|
| 278 |
+
"step": 323
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 5.096525096525096,
|
| 282 |
+
"grad_norm": 4.933718204498291,
|
| 283 |
+
"learning_rate": 2.6909722222222222e-05,
|
| 284 |
+
"loss": 0.4144,
|
| 285 |
+
"step": 330
|
|
|
|
|
|
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 5.250965250965251,
|
| 289 |
+
"grad_norm": 4.699091911315918,
|
| 290 |
+
"learning_rate": 2.604166666666667e-05,
|
| 291 |
+
"loss": 0.4191,
|
| 292 |
+
"step": 340
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 5.405405405405405,
|
| 296 |
+
"grad_norm": 5.412081718444824,
|
| 297 |
+
"learning_rate": 2.517361111111111e-05,
|
| 298 |
+
"loss": 0.4314,
|
| 299 |
+
"step": 350
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 5.559845559845559,
|
| 303 |
+
"grad_norm": 3.4998362064361572,
|
| 304 |
+
"learning_rate": 2.4305555555555558e-05,
|
| 305 |
+
"loss": 0.3793,
|
| 306 |
+
"step": 360
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 5.714285714285714,
|
| 310 |
+
"grad_norm": 3.954893112182617,
|
| 311 |
+
"learning_rate": 2.34375e-05,
|
| 312 |
+
"loss": 0.3815,
|
| 313 |
+
"step": 370
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 5.8687258687258685,
|
| 317 |
+
"grad_norm": 4.797443866729736,
|
| 318 |
+
"learning_rate": 2.2569444444444447e-05,
|
| 319 |
+
"loss": 0.3764,
|
| 320 |
+
"step": 380
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 5.992277992277993,
|
| 324 |
+
"eval_accuracy": 0.8295331161780674,
|
| 325 |
+
"eval_loss": 0.4095376133918762,
|
| 326 |
+
"eval_runtime": 106.8074,
|
| 327 |
+
"eval_samples_per_second": 8.623,
|
| 328 |
+
"eval_steps_per_second": 0.272,
|
| 329 |
+
"step": 388
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 6.023166023166024,
|
| 333 |
+
"grad_norm": 6.05122709274292,
|
| 334 |
+
"learning_rate": 2.170138888888889e-05,
|
| 335 |
+
"loss": 0.3947,
|
| 336 |
+
"step": 390
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 6.177606177606178,
|
| 340 |
+
"grad_norm": 4.6088666915893555,
|
| 341 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 342 |
+
"loss": 0.3712,
|
| 343 |
+
"step": 400
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 6.332046332046332,
|
| 347 |
+
"grad_norm": 3.9029107093811035,
|
| 348 |
+
"learning_rate": 1.996527777777778e-05,
|
| 349 |
+
"loss": 0.359,
|
| 350 |
+
"step": 410
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.486486486486487,
|
| 354 |
+
"grad_norm": 4.032750129699707,
|
| 355 |
+
"learning_rate": 1.9097222222222222e-05,
|
| 356 |
+
"loss": 0.4075,
|
| 357 |
+
"step": 420
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 6.640926640926641,
|
| 361 |
+
"grad_norm": 4.65377140045166,
|
| 362 |
+
"learning_rate": 1.8229166666666668e-05,
|
| 363 |
+
"loss": 0.3921,
|
| 364 |
+
"step": 430
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 6.795366795366795,
|
| 368 |
+
"grad_norm": 5.404110908508301,
|
| 369 |
+
"learning_rate": 1.736111111111111e-05,
|
| 370 |
+
"loss": 0.3905,
|
| 371 |
+
"step": 440
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 6.94980694980695,
|
| 375 |
+
"grad_norm": 4.541908264160156,
|
| 376 |
+
"learning_rate": 1.6493055555555557e-05,
|
| 377 |
+
"loss": 0.3725,
|
| 378 |
+
"step": 450
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 6.996138996138996,
|
| 382 |
+
"eval_accuracy": 0.8425624321389794,
|
| 383 |
+
"eval_loss": 0.4046495258808136,
|
| 384 |
+
"eval_runtime": 105.8848,
|
| 385 |
+
"eval_samples_per_second": 8.698,
|
| 386 |
+
"eval_steps_per_second": 0.274,
|
| 387 |
+
"step": 453
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 7.104247104247104,
|
| 391 |
+
"grad_norm": 4.969923496246338,
|
| 392 |
+
"learning_rate": 1.5625e-05,
|
| 393 |
+
"loss": 0.375,
|
| 394 |
+
"step": 460
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 7.258687258687258,
|
| 398 |
+
"grad_norm": 4.746829986572266,
|
| 399 |
+
"learning_rate": 1.4756944444444445e-05,
|
| 400 |
+
"loss": 0.3536,
|
| 401 |
+
"step": 470
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 7.413127413127413,
|
| 405 |
+
"grad_norm": 6.098570823669434,
|
| 406 |
+
"learning_rate": 1.388888888888889e-05,
|
| 407 |
+
"loss": 0.3418,
|
| 408 |
+
"step": 480
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 7.5675675675675675,
|
| 412 |
+
"grad_norm": 9.79119873046875,
|
| 413 |
+
"learning_rate": 1.3020833333333334e-05,
|
| 414 |
+
"loss": 0.3769,
|
| 415 |
+
"step": 490
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 7.722007722007722,
|
| 419 |
+
"grad_norm": 7.424502849578857,
|
| 420 |
+
"learning_rate": 1.2152777777777779e-05,
|
| 421 |
+
"loss": 0.3598,
|
| 422 |
+
"step": 500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 7.876447876447877,
|
| 426 |
+
"grad_norm": 3.9304542541503906,
|
| 427 |
+
"learning_rate": 1.1284722222222223e-05,
|
| 428 |
+
"loss": 0.3583,
|
| 429 |
+
"step": 510
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 8.0,
|
| 433 |
+
"eval_accuracy": 0.8371335504885994,
|
| 434 |
+
"eval_loss": 0.4108859896659851,
|
| 435 |
+
"eval_runtime": 107.4011,
|
| 436 |
+
"eval_samples_per_second": 8.575,
|
| 437 |
+
"eval_steps_per_second": 0.27,
|
| 438 |
+
"step": 518
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 8.03088803088803,
|
| 442 |
+
"grad_norm": 4.0118632316589355,
|
| 443 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 444 |
+
"loss": 0.36,
|
| 445 |
+
"step": 520
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 8.185328185328185,
|
| 449 |
+
"grad_norm": 6.711050510406494,
|
| 450 |
+
"learning_rate": 9.548611111111111e-06,
|
| 451 |
+
"loss": 0.3427,
|
| 452 |
+
"step": 530
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 8.339768339768339,
|
| 456 |
+
"grad_norm": 4.516994476318359,
|
| 457 |
+
"learning_rate": 8.680555555555556e-06,
|
| 458 |
+
"loss": 0.3335,
|
| 459 |
+
"step": 540
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 8.494208494208495,
|
| 463 |
+
"grad_norm": 7.737695217132568,
|
| 464 |
+
"learning_rate": 7.8125e-06,
|
| 465 |
+
"loss": 0.3658,
|
| 466 |
+
"step": 550
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 8.64864864864865,
|
| 470 |
+
"grad_norm": 5.0886759757995605,
|
| 471 |
+
"learning_rate": 6.944444444444445e-06,
|
| 472 |
+
"loss": 0.3635,
|
| 473 |
+
"step": 560
|
| 474 |
},
|
| 475 |
{
|
| 476 |
+
"epoch": 8.803088803088803,
|
| 477 |
+
"grad_norm": 3.6143264770507812,
|
| 478 |
+
"learning_rate": 6.076388888888889e-06,
|
| 479 |
+
"loss": 0.3493,
|
| 480 |
+
"step": 570
|
|
|
|
|
|
|
| 481 |
},
|
| 482 |
{
|
| 483 |
+
"epoch": 8.957528957528957,
|
| 484 |
+
"grad_norm": 4.734116554260254,
|
| 485 |
+
"learning_rate": 5.208333333333334e-06,
|
| 486 |
+
"loss": 0.3451,
|
| 487 |
+
"step": 580
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 8.988416988416988,
|
| 491 |
+
"eval_accuracy": 0.8349619978284474,
|
| 492 |
+
"eval_loss": 0.4170722961425781,
|
| 493 |
+
"eval_runtime": 108.6012,
|
| 494 |
+
"eval_samples_per_second": 8.481,
|
| 495 |
+
"eval_steps_per_second": 0.267,
|
| 496 |
+
"step": 582
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 9.111969111969112,
|
| 500 |
+
"grad_norm": 4.281556129455566,
|
| 501 |
+
"learning_rate": 4.340277777777778e-06,
|
| 502 |
+
"loss": 0.3268,
|
| 503 |
+
"step": 590
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 9.266409266409266,
|
| 507 |
+
"grad_norm": 3.9609580039978027,
|
| 508 |
+
"learning_rate": 3.4722222222222224e-06,
|
| 509 |
+
"loss": 0.371,
|
| 510 |
+
"step": 600
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 9.420849420849422,
|
| 514 |
+
"grad_norm": 5.559605598449707,
|
| 515 |
+
"learning_rate": 2.604166666666667e-06,
|
| 516 |
+
"loss": 0.3446,
|
| 517 |
+
"step": 610
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 9.575289575289576,
|
| 521 |
+
"grad_norm": 4.212625980377197,
|
| 522 |
+
"learning_rate": 1.7361111111111112e-06,
|
| 523 |
+
"loss": 0.3206,
|
| 524 |
+
"step": 620
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 9.72972972972973,
|
| 528 |
+
"grad_norm": 3.9171366691589355,
|
| 529 |
+
"learning_rate": 8.680555555555556e-07,
|
| 530 |
+
"loss": 0.3654,
|
| 531 |
+
"step": 630
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 9.884169884169884,
|
| 535 |
+
"grad_norm": 5.055610179901123,
|
| 536 |
"learning_rate": 0.0,
|
| 537 |
+
"loss": 0.3351,
|
| 538 |
+
"step": 640
|
| 539 |
},
|
| 540 |
{
|
| 541 |
+
"epoch": 9.884169884169884,
|
| 542 |
+
"eval_accuracy": 0.8403908794788274,
|
| 543 |
+
"eval_loss": 0.41527804732322693,
|
| 544 |
+
"eval_runtime": 106.36,
|
| 545 |
+
"eval_samples_per_second": 8.659,
|
| 546 |
+
"eval_steps_per_second": 0.273,
|
| 547 |
+
"step": 640
|
| 548 |
},
|
| 549 |
{
|
| 550 |
+
"epoch": 9.884169884169884,
|
| 551 |
+
"step": 640,
|
| 552 |
+
"total_flos": 2.0360358039744737e+18,
|
| 553 |
+
"train_loss": 0.45154881179332734,
|
| 554 |
+
"train_runtime": 9581.2043,
|
| 555 |
+
"train_samples_per_second": 8.649,
|
| 556 |
+
"train_steps_per_second": 0.067
|
| 557 |
}
|
| 558 |
],
|
| 559 |
"logging_steps": 10,
|
| 560 |
+
"max_steps": 640,
|
| 561 |
"num_input_tokens_seen": 0,
|
| 562 |
"num_train_epochs": 10,
|
| 563 |
"save_steps": 500,
|
|
|
|
| 573 |
"attributes": {}
|
| 574 |
}
|
| 575 |
},
|
| 576 |
+
"total_flos": 2.0360358039744737e+18,
|
| 577 |
"train_batch_size": 32,
|
| 578 |
"trial_name": null,
|
| 579 |
"trial_params": null
|