Training in progress, step 100
Browse files- README.md +46 -21
- adapter_config.json +7 -7
- adapter_model.safetensors +2 -2
- all_results.json +16 -5
- eval_results.json +14 -0
- metrics.json +1 -0
- train_results.json +5 -5
- trainer_state.json +1134 -215
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -4,19 +4,28 @@ library_name: peft
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
base_model: mistralai/Mistral-7B-v0.1
|
|
|
|
|
|
|
| 7 |
model-index:
|
| 8 |
-
- name: Mistral-7B-v0.
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
# Mistral-7B-v0.
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -35,34 +44,50 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate:
|
| 39 |
- train_batch_size: 4
|
| 40 |
- eval_batch_size: 4
|
| 41 |
- seed: 42
|
| 42 |
-
- distributed_type: multi-GPU
|
| 43 |
-
- num_devices: 4
|
| 44 |
- gradient_accumulation_steps: 4
|
| 45 |
-
- total_train_batch_size:
|
| 46 |
-
- total_eval_batch_size: 16
|
| 47 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
- lr_scheduler_type: constant
|
| 49 |
- lr_scheduler_warmup_ratio: 0.03
|
| 50 |
-
-
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
-
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
|
| 67 |
|
| 68 |
### Framework versions
|
|
|
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
base_model: mistralai/Mistral-7B-v0.1
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
model-index:
|
| 10 |
+
- name: Mistral-7B-v0.1_district-court-db
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
+
# Mistral-7B-v0.1_district-court-db
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.0358
|
| 22 |
+
- Precision Micro: 0.8142
|
| 23 |
+
- Precision Macro: 0.7222
|
| 24 |
+
- Recall Micro: 0.8142
|
| 25 |
+
- Recall Macro: 0.7126
|
| 26 |
+
- F1 Micro: 0.8142
|
| 27 |
+
- F1 Macro: 0.7098
|
| 28 |
+
- Accuracy: 0.8142
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 44 |
### Training hyperparameters
|
| 45 |
|
| 46 |
The following hyperparameters were used during training:
|
| 47 |
+
- learning_rate: 3e-05
|
| 48 |
- train_batch_size: 4
|
| 49 |
- eval_batch_size: 4
|
| 50 |
- seed: 42
|
|
|
|
|
|
|
| 51 |
- gradient_accumulation_steps: 4
|
| 52 |
+
- total_train_batch_size: 16
|
|
|
|
| 53 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 54 |
- lr_scheduler_type: constant
|
| 55 |
- lr_scheduler_warmup_ratio: 0.03
|
| 56 |
+
- training_steps: 1450
|
| 57 |
|
| 58 |
### Training results
|
| 59 |
|
| 60 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision Micro | Precision Macro | Recall Micro | Recall Macro | F1 Micro | F1 Macro | Accuracy |
|
| 61 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------------:|:---------------:|:------------:|:------------:|:--------:|:--------:|:--------:|
|
| 62 |
+
| 0.1255 | 0.04 | 50 | 0.2459 | 0.2330 | 0.0980 | 0.2330 | 0.0939 | 0.2330 | 0.0773 | 0.2330 |
|
| 63 |
+
| 0.1076 | 0.08 | 100 | 0.1451 | 0.4075 | 0.1951 | 0.4075 | 0.1846 | 0.4075 | 0.1681 | 0.4075 |
|
| 64 |
+
| 0.066 | 0.12 | 150 | 0.1095 | 0.5387 | 0.3493 | 0.5387 | 0.2872 | 0.5387 | 0.2780 | 0.5387 |
|
| 65 |
+
| 0.0699 | 0.16 | 200 | 0.0901 | 0.6208 | 0.3837 | 0.6208 | 0.3992 | 0.6208 | 0.3798 | 0.6208 |
|
| 66 |
+
| 0.066 | 0.2 | 250 | 0.0883 | 0.6104 | 0.4544 | 0.6104 | 0.4312 | 0.6104 | 0.4135 | 0.6104 |
|
| 67 |
+
| 0.0452 | 0.24 | 300 | 0.0879 | 0.6877 | 0.5649 | 0.6877 | 0.5135 | 0.6877 | 0.5092 | 0.6877 |
|
| 68 |
+
| 0.0545 | 0.28 | 350 | 0.0761 | 0.6764 | 0.5194 | 0.6764 | 0.5288 | 0.6764 | 0.5040 | 0.6764 |
|
| 69 |
+
| 0.0647 | 0.32 | 400 | 0.0665 | 0.7340 | 0.6193 | 0.7340 | 0.5252 | 0.7340 | 0.5493 | 0.7340 |
|
| 70 |
+
| 0.056 | 0.36 | 450 | 0.0514 | 0.7396 | 0.6097 | 0.7396 | 0.5767 | 0.7396 | 0.5672 | 0.7396 |
|
| 71 |
+
| 0.0513 | 0.4 | 500 | 0.0479 | 0.7613 | 0.6384 | 0.7613 | 0.6145 | 0.7613 | 0.6020 | 0.7613 |
|
| 72 |
+
| 0.0501 | 0.44 | 550 | 0.0502 | 0.7509 | 0.6245 | 0.7509 | 0.6167 | 0.7509 | 0.6075 | 0.7509 |
|
| 73 |
+
| 0.0533 | 0.48 | 600 | 0.0481 | 0.7642 | 0.6500 | 0.7642 | 0.6139 | 0.7642 | 0.6073 | 0.7642 |
|
| 74 |
+
| 0.0462 | 0.52 | 650 | 0.0473 | 0.7481 | 0.5942 | 0.7481 | 0.5740 | 0.7481 | 0.5679 | 0.7481 |
|
| 75 |
+
| 0.0496 | 0.56 | 700 | 0.0419 | 0.7972 | 0.6678 | 0.7972 | 0.6480 | 0.7972 | 0.6518 | 0.7972 |
|
| 76 |
+
| 0.0614 | 0.6 | 750 | 0.0489 | 0.7774 | 0.6678 | 0.7774 | 0.6360 | 0.7774 | 0.6308 | 0.7774 |
|
| 77 |
+
| 0.0468 | 0.64 | 800 | 0.0443 | 0.7830 | 0.6435 | 0.7830 | 0.6816 | 0.7830 | 0.6494 | 0.7830 |
|
| 78 |
+
| 0.0477 | 0.68 | 850 | 0.0420 | 0.7972 | 0.7040 | 0.7972 | 0.6567 | 0.7972 | 0.6663 | 0.7972 |
|
| 79 |
+
| 0.0519 | 0.72 | 900 | 0.0463 | 0.7632 | 0.6519 | 0.7632 | 0.6291 | 0.7632 | 0.6292 | 0.7632 |
|
| 80 |
+
| 0.0453 | 0.76 | 950 | 0.0429 | 0.7802 | 0.6757 | 0.7802 | 0.6698 | 0.7802 | 0.6564 | 0.7802 |
|
| 81 |
+
| 0.0452 | 0.79 | 1000 | 0.0471 | 0.7377 | 0.6182 | 0.7377 | 0.6300 | 0.7377 | 0.6049 | 0.7377 |
|
| 82 |
+
| 0.0367 | 0.83 | 1050 | 0.0388 | 0.7981 | 0.6857 | 0.7981 | 0.6992 | 0.7981 | 0.6801 | 0.7981 |
|
| 83 |
+
| 0.0377 | 0.87 | 1100 | 0.0382 | 0.8 | 0.6636 | 0.8 | 0.6698 | 0.8000 | 0.6591 | 0.8 |
|
| 84 |
+
| 0.0429 | 0.91 | 1150 | 0.0398 | 0.7953 | 0.6924 | 0.7953 | 0.6441 | 0.7953 | 0.6466 | 0.7953 |
|
| 85 |
+
| 0.0451 | 0.95 | 1200 | 0.0378 | 0.7943 | 0.6713 | 0.7943 | 0.6538 | 0.7943 | 0.6535 | 0.7943 |
|
| 86 |
+
| 0.0347 | 0.99 | 1250 | 0.0413 | 0.7840 | 0.6735 | 0.7840 | 0.6450 | 0.7840 | 0.6331 | 0.7840 |
|
| 87 |
+
| 0.0378 | 1.03 | 1300 | 0.0377 | 0.8047 | 0.7109 | 0.8047 | 0.6387 | 0.8047 | 0.6489 | 0.8047 |
|
| 88 |
+
| 0.0357 | 1.07 | 1350 | 0.0386 | 0.8028 | 0.6899 | 0.8028 | 0.6559 | 0.8028 | 0.6649 | 0.8028 |
|
| 89 |
+
| 0.0418 | 1.11 | 1400 | 0.0368 | 0.7962 | 0.7114 | 0.7962 | 0.6942 | 0.7962 | 0.6910 | 0.7962 |
|
| 90 |
+
| 0.0293 | 1.15 | 1450 | 0.0358 | 0.8142 | 0.7222 | 0.8142 | 0.7126 | 0.8142 | 0.7098 | 0.8142 |
|
| 91 |
|
| 92 |
|
| 93 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -10,22 +10,22 @@
|
|
| 10 |
"layers_to_transform": null,
|
| 11 |
"loftq_config": {},
|
| 12 |
"lora_alpha": 16,
|
| 13 |
-
"lora_dropout": 0.
|
| 14 |
"megatron_config": null,
|
| 15 |
"megatron_core": "megatron.core",
|
| 16 |
"modules_to_save": null,
|
| 17 |
"peft_type": "LORA",
|
| 18 |
-
"r":
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
"up_proj",
|
|
|
|
| 25 |
"v_proj",
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"down_proj"
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
|
|
|
| 10 |
"layers_to_transform": null,
|
| 11 |
"loftq_config": {},
|
| 12 |
"lora_alpha": 16,
|
| 13 |
+
"lora_dropout": 0.1,
|
| 14 |
"megatron_config": null,
|
| 15 |
"megatron_core": "megatron.core",
|
| 16 |
"modules_to_save": null,
|
| 17 |
"peft_type": "LORA",
|
| 18 |
+
"r": 64,
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
+
"down_proj",
|
| 23 |
+
"q_proj",
|
| 24 |
"up_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
"v_proj",
|
| 27 |
+
"k_proj",
|
| 28 |
+
"o_proj"
|
|
|
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de172eb1895ddad38b31177541cc496db1488c1268ec9191549df799bb83dab1
|
| 3 |
+
size 335605144
|
all_results.json
CHANGED
|
@@ -1,7 +1,18 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
| 6 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.15,
|
| 3 |
+
"eval_accuracy": 0.8141509433962264,
|
| 4 |
+
"eval_f1_macro": 0.7097996478763092,
|
| 5 |
+
"eval_f1_micro": 0.8141509433962264,
|
| 6 |
+
"eval_loss": 0.035770244896411896,
|
| 7 |
+
"eval_precision_macro": 0.7222302630120379,
|
| 8 |
+
"eval_precision_micro": 0.8141509433962264,
|
| 9 |
+
"eval_recall_macro": 0.7125706602249756,
|
| 10 |
+
"eval_recall_micro": 0.8141509433962264,
|
| 11 |
+
"eval_runtime": 66.7734,
|
| 12 |
+
"eval_samples_per_second": 15.875,
|
| 13 |
+
"eval_steps_per_second": 3.969,
|
| 14 |
+
"train_loss": 0.07879953698865298,
|
| 15 |
+
"train_runtime": 5948.326,
|
| 16 |
+
"train_samples_per_second": 3.9,
|
| 17 |
+
"train_steps_per_second": 0.244
|
| 18 |
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.15,
|
| 3 |
+
"eval_accuracy": 0.8141509433962264,
|
| 4 |
+
"eval_f1_macro": 0.7097996478763092,
|
| 5 |
+
"eval_f1_micro": 0.8141509433962264,
|
| 6 |
+
"eval_loss": 0.035770244896411896,
|
| 7 |
+
"eval_precision_macro": 0.7222302630120379,
|
| 8 |
+
"eval_precision_micro": 0.8141509433962264,
|
| 9 |
+
"eval_recall_macro": 0.7125706602249756,
|
| 10 |
+
"eval_recall_micro": 0.8141509433962264,
|
| 11 |
+
"eval_runtime": 66.7734,
|
| 12 |
+
"eval_samples_per_second": 15.875,
|
| 13 |
+
"eval_steps_per_second": 3.969
|
| 14 |
+
}
|
metrics.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"run_name": "./output", "train_runtime": 5948.326, "train_samples_per_second": 3.9, "train_steps_per_second": 0.244, "train_loss": 0.07879953698865298, "epoch": 1.15, "eval_loss": 0.035770244896411896, "eval_precision_micro": 0.8141509433962264, "eval_precision_macro": 0.7222302630120379, "eval_recall_micro": 0.8141509433962264, "eval_recall_macro": 0.7125706602249756, "eval_f1_micro": 0.8141509433962264, "eval_f1_macro": 0.7097996478763092, "eval_accuracy": 0.8141509433962264, "eval_runtime": 66.7734, "eval_samples_per_second": 15.875, "eval_steps_per_second": 3.969}
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.15,
|
| 3 |
+
"train_loss": 0.07879953698865298,
|
| 4 |
+
"train_runtime": 5948.326,
|
| 5 |
+
"train_samples_per_second": 3.9,
|
| 6 |
+
"train_steps_per_second": 0.244
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,415 +1,1334 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 1.
|
| 5 |
"eval_steps": 50,
|
| 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": 0.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss":
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss":
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss":
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss":
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss":
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
-
"epoch": 0.
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
"
|
| 46 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
"step": 50
|
| 48 |
},
|
| 49 |
{
|
| 50 |
-
"epoch": 0.
|
| 51 |
-
"learning_rate":
|
| 52 |
-
"loss":
|
| 53 |
"step": 60
|
| 54 |
},
|
| 55 |
{
|
| 56 |
-
"epoch": 0.
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss":
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
-
"epoch": 0.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss":
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"learning_rate":
|
| 70 |
-
"loss":
|
| 71 |
"step": 90
|
| 72 |
},
|
| 73 |
{
|
| 74 |
-
"epoch": 0.
|
| 75 |
-
"learning_rate":
|
| 76 |
-
"loss":
|
| 77 |
"step": 100
|
| 78 |
},
|
| 79 |
{
|
| 80 |
-
"epoch": 0.
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
"step": 100
|
| 86 |
},
|
| 87 |
{
|
| 88 |
-
"epoch": 0.
|
| 89 |
-
"learning_rate":
|
| 90 |
-
"loss":
|
| 91 |
"step": 110
|
| 92 |
},
|
| 93 |
{
|
| 94 |
-
"epoch": 0.
|
| 95 |
-
"learning_rate":
|
| 96 |
-
"loss":
|
| 97 |
"step": 120
|
| 98 |
},
|
| 99 |
{
|
| 100 |
-
"epoch": 0.
|
| 101 |
-
"learning_rate":
|
| 102 |
-
"loss":
|
| 103 |
"step": 130
|
| 104 |
},
|
| 105 |
{
|
| 106 |
-
"epoch": 0.
|
| 107 |
-
"learning_rate":
|
| 108 |
-
"loss":
|
| 109 |
"step": 140
|
| 110 |
},
|
| 111 |
{
|
| 112 |
-
"epoch": 0.
|
| 113 |
-
"learning_rate":
|
| 114 |
-
"loss":
|
| 115 |
"step": 150
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch": 0.
|
| 119 |
-
"
|
| 120 |
-
"
|
| 121 |
-
"
|
| 122 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 0.
|
| 127 |
-
"learning_rate":
|
| 128 |
-
"loss":
|
| 129 |
"step": 160
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 0.
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss":
|
| 135 |
"step": 170
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"learning_rate":
|
| 140 |
-
"loss":
|
| 141 |
"step": 180
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch": 0.
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss":
|
| 147 |
"step": 190
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 0.
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss":
|
| 153 |
"step": 200
|
| 154 |
},
|
| 155 |
{
|
| 156 |
-
"epoch": 0.
|
| 157 |
-
"
|
| 158 |
-
"
|
| 159 |
-
"
|
| 160 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 161 |
"step": 200
|
| 162 |
},
|
| 163 |
{
|
| 164 |
-
"epoch": 0.
|
| 165 |
-
"learning_rate":
|
| 166 |
-
"loss":
|
| 167 |
"step": 210
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch": 0.
|
| 171 |
-
"learning_rate":
|
| 172 |
-
"loss":
|
| 173 |
"step": 220
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch": 0.
|
| 177 |
-
"learning_rate":
|
| 178 |
-
"loss":
|
| 179 |
"step": 230
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch": 0.
|
| 183 |
-
"learning_rate":
|
| 184 |
-
"loss":
|
| 185 |
"step": 240
|
| 186 |
},
|
| 187 |
{
|
| 188 |
-
"epoch": 0.
|
| 189 |
-
"learning_rate":
|
| 190 |
-
"loss":
|
| 191 |
"step": 250
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"
|
| 196 |
-
"
|
| 197 |
-
"
|
| 198 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 199 |
"step": 250
|
| 200 |
},
|
| 201 |
{
|
| 202 |
-
"epoch":
|
| 203 |
-
"learning_rate":
|
| 204 |
-
"loss":
|
| 205 |
"step": 260
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch":
|
| 209 |
-
"learning_rate":
|
| 210 |
-
"loss":
|
| 211 |
"step": 270
|
| 212 |
},
|
| 213 |
{
|
| 214 |
-
"epoch":
|
| 215 |
-
"learning_rate":
|
| 216 |
-
"loss":
|
| 217 |
"step": 280
|
| 218 |
},
|
| 219 |
{
|
| 220 |
-
"epoch":
|
| 221 |
-
"learning_rate":
|
| 222 |
-
"loss":
|
| 223 |
"step": 290
|
| 224 |
},
|
| 225 |
{
|
| 226 |
-
"epoch":
|
| 227 |
-
"learning_rate":
|
| 228 |
-
"loss":
|
| 229 |
"step": 300
|
| 230 |
},
|
| 231 |
{
|
| 232 |
-
"epoch":
|
| 233 |
-
"
|
| 234 |
-
"
|
| 235 |
-
"
|
| 236 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss":
|
| 243 |
"step": 310
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch":
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss":
|
| 249 |
"step": 320
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch":
|
| 253 |
-
"learning_rate":
|
| 254 |
-
"loss":
|
| 255 |
"step": 330
|
| 256 |
},
|
| 257 |
{
|
| 258 |
-
"epoch":
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss":
|
| 261 |
"step": 340
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch":
|
| 265 |
-
"learning_rate":
|
| 266 |
-
"loss":
|
| 267 |
"step": 350
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch":
|
| 271 |
-
"
|
| 272 |
-
"
|
| 273 |
-
"
|
| 274 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 275 |
"step": 350
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch":
|
| 279 |
-
"learning_rate":
|
| 280 |
-
"loss":
|
| 281 |
"step": 360
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch":
|
| 285 |
-
"learning_rate":
|
| 286 |
-
"loss":
|
| 287 |
"step": 370
|
| 288 |
},
|
| 289 |
{
|
| 290 |
-
"epoch":
|
| 291 |
-
"learning_rate":
|
| 292 |
-
"loss":
|
| 293 |
"step": 380
|
| 294 |
},
|
| 295 |
{
|
| 296 |
-
"epoch":
|
| 297 |
-
"learning_rate":
|
| 298 |
-
"loss":
|
| 299 |
"step": 390
|
| 300 |
},
|
| 301 |
{
|
| 302 |
-
"epoch":
|
| 303 |
-
"learning_rate":
|
| 304 |
-
"loss":
|
| 305 |
"step": 400
|
| 306 |
},
|
| 307 |
{
|
| 308 |
-
"epoch":
|
| 309 |
-
"
|
| 310 |
-
"
|
| 311 |
-
"
|
| 312 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 313 |
"step": 400
|
| 314 |
},
|
| 315 |
{
|
| 316 |
-
"epoch":
|
| 317 |
-
"learning_rate":
|
| 318 |
-
"loss":
|
| 319 |
"step": 410
|
| 320 |
},
|
| 321 |
{
|
| 322 |
-
"epoch":
|
| 323 |
-
"learning_rate":
|
| 324 |
-
"loss":
|
| 325 |
"step": 420
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch":
|
| 329 |
-
"learning_rate":
|
| 330 |
-
"loss":
|
| 331 |
"step": 430
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch":
|
| 335 |
-
"learning_rate":
|
| 336 |
-
"loss":
|
| 337 |
"step": 440
|
| 338 |
},
|
| 339 |
{
|
| 340 |
-
"epoch":
|
| 341 |
-
"learning_rate":
|
| 342 |
-
"loss":
|
| 343 |
"step": 450
|
| 344 |
},
|
| 345 |
{
|
| 346 |
-
"epoch":
|
| 347 |
-
"
|
| 348 |
-
"
|
| 349 |
-
"
|
| 350 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 351 |
"step": 450
|
| 352 |
},
|
| 353 |
{
|
| 354 |
-
"epoch":
|
| 355 |
-
"learning_rate":
|
| 356 |
-
"loss":
|
| 357 |
"step": 460
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch":
|
| 361 |
-
"learning_rate":
|
| 362 |
-
"loss":
|
| 363 |
"step": 470
|
| 364 |
},
|
| 365 |
{
|
| 366 |
-
"epoch":
|
| 367 |
-
"learning_rate":
|
| 368 |
-
"loss":
|
| 369 |
"step": 480
|
| 370 |
},
|
| 371 |
{
|
| 372 |
-
"epoch":
|
| 373 |
-
"learning_rate":
|
| 374 |
-
"loss":
|
| 375 |
"step": 490
|
| 376 |
},
|
| 377 |
{
|
| 378 |
-
"epoch":
|
| 379 |
-
"learning_rate":
|
| 380 |
-
"loss":
|
| 381 |
"step": 500
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch":
|
| 385 |
-
"
|
| 386 |
-
"
|
| 387 |
-
"
|
| 388 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 389 |
"step": 500
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch":
|
| 393 |
-
"learning_rate":
|
| 394 |
-
"loss":
|
| 395 |
"step": 510
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch":
|
| 399 |
-
"
|
| 400 |
-
"
|
| 401 |
-
"
|
| 402 |
-
|
| 403 |
-
|
| 404 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 405 |
}
|
| 406 |
],
|
| 407 |
"logging_steps": 10,
|
| 408 |
-
"max_steps":
|
| 409 |
"num_input_tokens_seen": 0,
|
| 410 |
"num_train_epochs": 2,
|
| 411 |
-
"save_steps":
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 4,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.1523941982912775,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 1450,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 3e-05,
|
| 14 |
+
"loss": 2.0927,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 3e-05,
|
| 20 |
+
"loss": 0.267,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 3e-05,
|
| 26 |
+
"loss": 0.1926,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 3e-05,
|
| 32 |
+
"loss": 0.1601,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"learning_rate": 3e-05,
|
| 38 |
+
"loss": 0.1255,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.04,
|
| 43 |
+
"eval_accuracy": 0.2330188679245283,
|
| 44 |
+
"eval_f1_macro": 0.07731831394851697,
|
| 45 |
+
"eval_f1_micro": 0.2330188679245283,
|
| 46 |
+
"eval_loss": 0.24590551853179932,
|
| 47 |
+
"eval_precision_macro": 0.09801465635567799,
|
| 48 |
+
"eval_precision_micro": 0.2330188679245283,
|
| 49 |
+
"eval_recall_macro": 0.0939265996231733,
|
| 50 |
+
"eval_recall_micro": 0.2330188679245283,
|
| 51 |
+
"eval_runtime": 67.1714,
|
| 52 |
+
"eval_samples_per_second": 15.781,
|
| 53 |
+
"eval_steps_per_second": 3.945,
|
| 54 |
"step": 50
|
| 55 |
},
|
| 56 |
{
|
| 57 |
+
"epoch": 0.05,
|
| 58 |
+
"learning_rate": 3e-05,
|
| 59 |
+
"loss": 0.6981,
|
| 60 |
"step": 60
|
| 61 |
},
|
| 62 |
{
|
| 63 |
+
"epoch": 0.06,
|
| 64 |
+
"learning_rate": 3e-05,
|
| 65 |
+
"loss": 0.1356,
|
| 66 |
"step": 70
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"epoch": 0.06,
|
| 70 |
+
"learning_rate": 3e-05,
|
| 71 |
+
"loss": 0.0993,
|
| 72 |
"step": 80
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.07,
|
| 76 |
+
"learning_rate": 3e-05,
|
| 77 |
+
"loss": 0.1038,
|
| 78 |
"step": 90
|
| 79 |
},
|
| 80 |
{
|
| 81 |
+
"epoch": 0.08,
|
| 82 |
+
"learning_rate": 3e-05,
|
| 83 |
+
"loss": 0.1076,
|
| 84 |
"step": 100
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 0.08,
|
| 88 |
+
"eval_accuracy": 0.4075471698113208,
|
| 89 |
+
"eval_f1_macro": 0.1681261191284492,
|
| 90 |
+
"eval_f1_micro": 0.4075471698113208,
|
| 91 |
+
"eval_loss": 0.14505280554294586,
|
| 92 |
+
"eval_precision_macro": 0.19505399860785297,
|
| 93 |
+
"eval_precision_micro": 0.4075471698113208,
|
| 94 |
+
"eval_recall_macro": 0.18462138174503467,
|
| 95 |
+
"eval_recall_micro": 0.4075471698113208,
|
| 96 |
+
"eval_runtime": 67.1009,
|
| 97 |
+
"eval_samples_per_second": 15.797,
|
| 98 |
+
"eval_steps_per_second": 3.949,
|
| 99 |
"step": 100
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"epoch": 0.09,
|
| 103 |
+
"learning_rate": 3e-05,
|
| 104 |
+
"loss": 0.331,
|
| 105 |
"step": 110
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 0.1,
|
| 109 |
+
"learning_rate": 3e-05,
|
| 110 |
+
"loss": 0.0809,
|
| 111 |
"step": 120
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 0.1,
|
| 115 |
+
"learning_rate": 3e-05,
|
| 116 |
+
"loss": 0.0812,
|
| 117 |
"step": 130
|
| 118 |
},
|
| 119 |
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"learning_rate": 3e-05,
|
| 122 |
+
"loss": 0.0601,
|
| 123 |
"step": 140
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 0.12,
|
| 127 |
+
"learning_rate": 3e-05,
|
| 128 |
+
"loss": 0.066,
|
| 129 |
"step": 150
|
| 130 |
},
|
| 131 |
{
|
| 132 |
+
"epoch": 0.12,
|
| 133 |
+
"eval_accuracy": 0.5386792452830189,
|
| 134 |
+
"eval_f1_macro": 0.2780127225833117,
|
| 135 |
+
"eval_f1_micro": 0.5386792452830189,
|
| 136 |
+
"eval_loss": 0.10953618586063385,
|
| 137 |
+
"eval_precision_macro": 0.3493311966119182,
|
| 138 |
+
"eval_precision_micro": 0.5386792452830189,
|
| 139 |
+
"eval_recall_macro": 0.2871523900319283,
|
| 140 |
+
"eval_recall_micro": 0.5386792452830189,
|
| 141 |
+
"eval_runtime": 67.0903,
|
| 142 |
+
"eval_samples_per_second": 15.8,
|
| 143 |
+
"eval_steps_per_second": 3.95,
|
| 144 |
"step": 150
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 0.13,
|
| 148 |
+
"learning_rate": 3e-05,
|
| 149 |
+
"loss": 0.2732,
|
| 150 |
"step": 160
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 0.14,
|
| 154 |
+
"learning_rate": 3e-05,
|
| 155 |
+
"loss": 0.0754,
|
| 156 |
"step": 170
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.14,
|
| 160 |
+
"learning_rate": 3e-05,
|
| 161 |
+
"loss": 0.0649,
|
| 162 |
"step": 180
|
| 163 |
},
|
| 164 |
{
|
| 165 |
+
"epoch": 0.15,
|
| 166 |
+
"learning_rate": 3e-05,
|
| 167 |
+
"loss": 0.0674,
|
| 168 |
"step": 190
|
| 169 |
},
|
| 170 |
{
|
| 171 |
+
"epoch": 0.16,
|
| 172 |
+
"learning_rate": 3e-05,
|
| 173 |
+
"loss": 0.0699,
|
| 174 |
"step": 200
|
| 175 |
},
|
| 176 |
{
|
| 177 |
+
"epoch": 0.16,
|
| 178 |
+
"eval_accuracy": 0.620754716981132,
|
| 179 |
+
"eval_f1_macro": 0.3797608124202816,
|
| 180 |
+
"eval_f1_micro": 0.620754716981132,
|
| 181 |
+
"eval_loss": 0.09009388834238052,
|
| 182 |
+
"eval_precision_macro": 0.3837197141355178,
|
| 183 |
+
"eval_precision_micro": 0.620754716981132,
|
| 184 |
+
"eval_recall_macro": 0.39915842112719735,
|
| 185 |
+
"eval_recall_micro": 0.620754716981132,
|
| 186 |
+
"eval_runtime": 67.0671,
|
| 187 |
+
"eval_samples_per_second": 15.805,
|
| 188 |
+
"eval_steps_per_second": 3.951,
|
| 189 |
"step": 200
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 0.17,
|
| 193 |
+
"learning_rate": 3e-05,
|
| 194 |
+
"loss": 0.1946,
|
| 195 |
"step": 210
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 0.17,
|
| 199 |
+
"learning_rate": 3e-05,
|
| 200 |
+
"loss": 0.0657,
|
| 201 |
"step": 220
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 0.18,
|
| 205 |
+
"learning_rate": 3e-05,
|
| 206 |
+
"loss": 0.0547,
|
| 207 |
"step": 230
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 0.19,
|
| 211 |
+
"learning_rate": 3e-05,
|
| 212 |
+
"loss": 0.0615,
|
| 213 |
"step": 240
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 0.2,
|
| 217 |
+
"learning_rate": 3e-05,
|
| 218 |
+
"loss": 0.066,
|
| 219 |
"step": 250
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.2,
|
| 223 |
+
"eval_accuracy": 0.6103773584905661,
|
| 224 |
+
"eval_f1_macro": 0.41348516498355786,
|
| 225 |
+
"eval_f1_micro": 0.6103773584905661,
|
| 226 |
+
"eval_loss": 0.08832413703203201,
|
| 227 |
+
"eval_precision_macro": 0.45439839834135715,
|
| 228 |
+
"eval_precision_micro": 0.6103773584905661,
|
| 229 |
+
"eval_recall_macro": 0.4312111435526721,
|
| 230 |
+
"eval_recall_micro": 0.6103773584905661,
|
| 231 |
+
"eval_runtime": 66.9345,
|
| 232 |
+
"eval_samples_per_second": 15.836,
|
| 233 |
+
"eval_steps_per_second": 3.959,
|
| 234 |
"step": 250
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 0.21,
|
| 238 |
+
"learning_rate": 3e-05,
|
| 239 |
+
"loss": 0.1494,
|
| 240 |
"step": 260
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 0.21,
|
| 244 |
+
"learning_rate": 3e-05,
|
| 245 |
+
"loss": 0.0655,
|
| 246 |
"step": 270
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 0.22,
|
| 250 |
+
"learning_rate": 3e-05,
|
| 251 |
+
"loss": 0.06,
|
| 252 |
"step": 280
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 0.23,
|
| 256 |
+
"learning_rate": 3e-05,
|
| 257 |
+
"loss": 0.0616,
|
| 258 |
"step": 290
|
| 259 |
},
|
| 260 |
{
|
| 261 |
+
"epoch": 0.24,
|
| 262 |
+
"learning_rate": 3e-05,
|
| 263 |
+
"loss": 0.0452,
|
| 264 |
"step": 300
|
| 265 |
},
|
| 266 |
{
|
| 267 |
+
"epoch": 0.24,
|
| 268 |
+
"eval_accuracy": 0.6877358490566038,
|
| 269 |
+
"eval_f1_macro": 0.5091555575082085,
|
| 270 |
+
"eval_f1_micro": 0.6877358490566038,
|
| 271 |
+
"eval_loss": 0.08789286762475967,
|
| 272 |
+
"eval_precision_macro": 0.5649217974276287,
|
| 273 |
+
"eval_precision_micro": 0.6877358490566038,
|
| 274 |
+
"eval_recall_macro": 0.513496327466451,
|
| 275 |
+
"eval_recall_micro": 0.6877358490566038,
|
| 276 |
+
"eval_runtime": 67.1619,
|
| 277 |
+
"eval_samples_per_second": 15.783,
|
| 278 |
+
"eval_steps_per_second": 3.946,
|
| 279 |
"step": 300
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 0.25,
|
| 283 |
+
"learning_rate": 3e-05,
|
| 284 |
+
"loss": 0.1535,
|
| 285 |
"step": 310
|
| 286 |
},
|
| 287 |
{
|
| 288 |
+
"epoch": 0.25,
|
| 289 |
+
"learning_rate": 3e-05,
|
| 290 |
+
"loss": 0.0731,
|
| 291 |
"step": 320
|
| 292 |
},
|
| 293 |
{
|
| 294 |
+
"epoch": 0.26,
|
| 295 |
+
"learning_rate": 3e-05,
|
| 296 |
+
"loss": 0.044,
|
| 297 |
"step": 330
|
| 298 |
},
|
| 299 |
{
|
| 300 |
+
"epoch": 0.27,
|
| 301 |
+
"learning_rate": 3e-05,
|
| 302 |
+
"loss": 0.053,
|
| 303 |
"step": 340
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 0.28,
|
| 307 |
+
"learning_rate": 3e-05,
|
| 308 |
+
"loss": 0.0545,
|
| 309 |
"step": 350
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 0.28,
|
| 313 |
+
"eval_accuracy": 0.6764150943396227,
|
| 314 |
+
"eval_f1_macro": 0.503999030020007,
|
| 315 |
+
"eval_f1_micro": 0.6764150943396227,
|
| 316 |
+
"eval_loss": 0.07607663422822952,
|
| 317 |
+
"eval_precision_macro": 0.5194445629359009,
|
| 318 |
+
"eval_precision_micro": 0.6764150943396227,
|
| 319 |
+
"eval_recall_macro": 0.5287937722322651,
|
| 320 |
+
"eval_recall_micro": 0.6764150943396227,
|
| 321 |
+
"eval_runtime": 67.2353,
|
| 322 |
+
"eval_samples_per_second": 15.766,
|
| 323 |
+
"eval_steps_per_second": 3.941,
|
| 324 |
"step": 350
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 0.29,
|
| 328 |
+
"learning_rate": 3e-05,
|
| 329 |
+
"loss": 0.1543,
|
| 330 |
"step": 360
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"epoch": 0.29,
|
| 334 |
+
"learning_rate": 3e-05,
|
| 335 |
+
"loss": 0.0609,
|
| 336 |
"step": 370
|
| 337 |
},
|
| 338 |
{
|
| 339 |
+
"epoch": 0.3,
|
| 340 |
+
"learning_rate": 3e-05,
|
| 341 |
+
"loss": 0.0479,
|
| 342 |
"step": 380
|
| 343 |
},
|
| 344 |
{
|
| 345 |
+
"epoch": 0.31,
|
| 346 |
+
"learning_rate": 3e-05,
|
| 347 |
+
"loss": 0.0532,
|
| 348 |
"step": 390
|
| 349 |
},
|
| 350 |
{
|
| 351 |
+
"epoch": 0.32,
|
| 352 |
+
"learning_rate": 3e-05,
|
| 353 |
+
"loss": 0.0647,
|
| 354 |
"step": 400
|
| 355 |
},
|
| 356 |
{
|
| 357 |
+
"epoch": 0.32,
|
| 358 |
+
"eval_accuracy": 0.7339622641509433,
|
| 359 |
+
"eval_f1_macro": 0.5492932704438783,
|
| 360 |
+
"eval_f1_micro": 0.7339622641509433,
|
| 361 |
+
"eval_loss": 0.06653406471014023,
|
| 362 |
+
"eval_precision_macro": 0.6193164476598846,
|
| 363 |
+
"eval_precision_micro": 0.7339622641509433,
|
| 364 |
+
"eval_recall_macro": 0.5252411264940735,
|
| 365 |
+
"eval_recall_micro": 0.7339622641509433,
|
| 366 |
+
"eval_runtime": 67.4334,
|
| 367 |
+
"eval_samples_per_second": 15.719,
|
| 368 |
+
"eval_steps_per_second": 3.93,
|
| 369 |
"step": 400
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 0.33,
|
| 373 |
+
"learning_rate": 3e-05,
|
| 374 |
+
"loss": 0.104,
|
| 375 |
"step": 410
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 0.33,
|
| 379 |
+
"learning_rate": 3e-05,
|
| 380 |
+
"loss": 0.0458,
|
| 381 |
"step": 420
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 0.34,
|
| 385 |
+
"learning_rate": 3e-05,
|
| 386 |
+
"loss": 0.0552,
|
| 387 |
"step": 430
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 0.35,
|
| 391 |
+
"learning_rate": 3e-05,
|
| 392 |
+
"loss": 0.0512,
|
| 393 |
"step": 440
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 0.36,
|
| 397 |
+
"learning_rate": 3e-05,
|
| 398 |
+
"loss": 0.056,
|
| 399 |
"step": 450
|
| 400 |
},
|
| 401 |
{
|
| 402 |
+
"epoch": 0.36,
|
| 403 |
+
"eval_accuracy": 0.7396226415094339,
|
| 404 |
+
"eval_f1_macro": 0.5671730153967399,
|
| 405 |
+
"eval_f1_micro": 0.7396226415094339,
|
| 406 |
+
"eval_loss": 0.05136344954371452,
|
| 407 |
+
"eval_precision_macro": 0.6096698581228938,
|
| 408 |
+
"eval_precision_micro": 0.7396226415094339,
|
| 409 |
+
"eval_recall_macro": 0.5767264087198709,
|
| 410 |
+
"eval_recall_micro": 0.7396226415094339,
|
| 411 |
+
"eval_runtime": 66.8962,
|
| 412 |
+
"eval_samples_per_second": 15.845,
|
| 413 |
+
"eval_steps_per_second": 3.961,
|
| 414 |
"step": 450
|
| 415 |
},
|
| 416 |
{
|
| 417 |
+
"epoch": 0.37,
|
| 418 |
+
"learning_rate": 3e-05,
|
| 419 |
+
"loss": 0.0773,
|
| 420 |
"step": 460
|
| 421 |
},
|
| 422 |
{
|
| 423 |
+
"epoch": 0.37,
|
| 424 |
+
"learning_rate": 3e-05,
|
| 425 |
+
"loss": 0.0474,
|
| 426 |
"step": 470
|
| 427 |
},
|
| 428 |
{
|
| 429 |
+
"epoch": 0.38,
|
| 430 |
+
"learning_rate": 3e-05,
|
| 431 |
+
"loss": 0.0405,
|
| 432 |
"step": 480
|
| 433 |
},
|
| 434 |
{
|
| 435 |
+
"epoch": 0.39,
|
| 436 |
+
"learning_rate": 3e-05,
|
| 437 |
+
"loss": 0.0461,
|
| 438 |
"step": 490
|
| 439 |
},
|
| 440 |
{
|
| 441 |
+
"epoch": 0.4,
|
| 442 |
+
"learning_rate": 3e-05,
|
| 443 |
+
"loss": 0.0513,
|
| 444 |
"step": 500
|
| 445 |
},
|
| 446 |
{
|
| 447 |
+
"epoch": 0.4,
|
| 448 |
+
"eval_accuracy": 0.7613207547169811,
|
| 449 |
+
"eval_f1_macro": 0.601977568492687,
|
| 450 |
+
"eval_f1_micro": 0.761320754716981,
|
| 451 |
+
"eval_loss": 0.047934673726558685,
|
| 452 |
+
"eval_precision_macro": 0.638418606498986,
|
| 453 |
+
"eval_precision_micro": 0.7613207547169811,
|
| 454 |
+
"eval_recall_macro": 0.6145296570629574,
|
| 455 |
+
"eval_recall_micro": 0.7613207547169811,
|
| 456 |
+
"eval_runtime": 66.9411,
|
| 457 |
+
"eval_samples_per_second": 15.835,
|
| 458 |
+
"eval_steps_per_second": 3.959,
|
| 459 |
"step": 500
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 0.41,
|
| 463 |
+
"learning_rate": 3e-05,
|
| 464 |
+
"loss": 0.0788,
|
| 465 |
"step": 510
|
| 466 |
},
|
| 467 |
{
|
| 468 |
+
"epoch": 0.41,
|
| 469 |
+
"learning_rate": 3e-05,
|
| 470 |
+
"loss": 0.0495,
|
| 471 |
+
"step": 520
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.42,
|
| 475 |
+
"learning_rate": 3e-05,
|
| 476 |
+
"loss": 0.0552,
|
| 477 |
+
"step": 530
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.43,
|
| 481 |
+
"learning_rate": 3e-05,
|
| 482 |
+
"loss": 0.0415,
|
| 483 |
+
"step": 540
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.44,
|
| 487 |
+
"learning_rate": 3e-05,
|
| 488 |
+
"loss": 0.0501,
|
| 489 |
+
"step": 550
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.44,
|
| 493 |
+
"eval_accuracy": 0.7509433962264151,
|
| 494 |
+
"eval_f1_macro": 0.6074975120648255,
|
| 495 |
+
"eval_f1_micro": 0.7509433962264151,
|
| 496 |
+
"eval_loss": 0.05019384250044823,
|
| 497 |
+
"eval_precision_macro": 0.624502704252128,
|
| 498 |
+
"eval_precision_micro": 0.7509433962264151,
|
| 499 |
+
"eval_recall_macro": 0.6167049341328479,
|
| 500 |
+
"eval_recall_micro": 0.7509433962264151,
|
| 501 |
+
"eval_runtime": 67.3498,
|
| 502 |
+
"eval_samples_per_second": 15.739,
|
| 503 |
+
"eval_steps_per_second": 3.935,
|
| 504 |
+
"step": 550
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.45,
|
| 508 |
+
"learning_rate": 3e-05,
|
| 509 |
+
"loss": 0.0633,
|
| 510 |
+
"step": 560
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.45,
|
| 514 |
+
"learning_rate": 3e-05,
|
| 515 |
+
"loss": 0.0484,
|
| 516 |
+
"step": 570
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.46,
|
| 520 |
+
"learning_rate": 3e-05,
|
| 521 |
+
"loss": 0.0418,
|
| 522 |
+
"step": 580
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.47,
|
| 526 |
+
"learning_rate": 3e-05,
|
| 527 |
+
"loss": 0.0524,
|
| 528 |
+
"step": 590
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.48,
|
| 532 |
+
"learning_rate": 3e-05,
|
| 533 |
+
"loss": 0.0533,
|
| 534 |
+
"step": 600
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.48,
|
| 538 |
+
"eval_accuracy": 0.7641509433962265,
|
| 539 |
+
"eval_f1_macro": 0.607265930345707,
|
| 540 |
+
"eval_f1_micro": 0.7641509433962265,
|
| 541 |
+
"eval_loss": 0.048058342188596725,
|
| 542 |
+
"eval_precision_macro": 0.6499724898555727,
|
| 543 |
+
"eval_precision_micro": 0.7641509433962265,
|
| 544 |
+
"eval_recall_macro": 0.6139175086252339,
|
| 545 |
+
"eval_recall_micro": 0.7641509433962265,
|
| 546 |
+
"eval_runtime": 66.897,
|
| 547 |
+
"eval_samples_per_second": 15.845,
|
| 548 |
+
"eval_steps_per_second": 3.961,
|
| 549 |
+
"step": 600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.48,
|
| 553 |
+
"learning_rate": 3e-05,
|
| 554 |
+
"loss": 0.0418,
|
| 555 |
+
"step": 610
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.49,
|
| 559 |
+
"learning_rate": 3e-05,
|
| 560 |
+
"loss": 0.0482,
|
| 561 |
+
"step": 620
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.5,
|
| 565 |
+
"learning_rate": 3e-05,
|
| 566 |
+
"loss": 0.0458,
|
| 567 |
+
"step": 630
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.51,
|
| 571 |
+
"learning_rate": 3e-05,
|
| 572 |
+
"loss": 0.0432,
|
| 573 |
+
"step": 640
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.52,
|
| 577 |
+
"learning_rate": 3e-05,
|
| 578 |
+
"loss": 0.0462,
|
| 579 |
+
"step": 650
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.52,
|
| 583 |
+
"eval_accuracy": 0.7481132075471698,
|
| 584 |
+
"eval_f1_macro": 0.5679477471859753,
|
| 585 |
+
"eval_f1_micro": 0.7481132075471698,
|
| 586 |
+
"eval_loss": 0.047320980578660965,
|
| 587 |
+
"eval_precision_macro": 0.5941670973495327,
|
| 588 |
+
"eval_precision_micro": 0.7481132075471698,
|
| 589 |
+
"eval_recall_macro": 0.5739727328111488,
|
| 590 |
+
"eval_recall_micro": 0.7481132075471698,
|
| 591 |
+
"eval_runtime": 67.2106,
|
| 592 |
+
"eval_samples_per_second": 15.771,
|
| 593 |
+
"eval_steps_per_second": 3.943,
|
| 594 |
+
"step": 650
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.52,
|
| 598 |
+
"learning_rate": 3e-05,
|
| 599 |
+
"loss": 0.0668,
|
| 600 |
+
"step": 660
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.53,
|
| 604 |
+
"learning_rate": 3e-05,
|
| 605 |
+
"loss": 0.0501,
|
| 606 |
+
"step": 670
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.54,
|
| 610 |
+
"learning_rate": 3e-05,
|
| 611 |
+
"loss": 0.0366,
|
| 612 |
+
"step": 680
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.55,
|
| 616 |
+
"learning_rate": 3e-05,
|
| 617 |
+
"loss": 0.0374,
|
| 618 |
+
"step": 690
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.56,
|
| 622 |
+
"learning_rate": 3e-05,
|
| 623 |
+
"loss": 0.0496,
|
| 624 |
+
"step": 700
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.56,
|
| 628 |
+
"eval_accuracy": 0.7971698113207547,
|
| 629 |
+
"eval_f1_macro": 0.6517694520426227,
|
| 630 |
+
"eval_f1_micro": 0.7971698113207546,
|
| 631 |
+
"eval_loss": 0.04193812981247902,
|
| 632 |
+
"eval_precision_macro": 0.6678204026981202,
|
| 633 |
+
"eval_precision_micro": 0.7971698113207547,
|
| 634 |
+
"eval_recall_macro": 0.6480125227888868,
|
| 635 |
+
"eval_recall_micro": 0.7971698113207547,
|
| 636 |
+
"eval_runtime": 67.3982,
|
| 637 |
+
"eval_samples_per_second": 15.727,
|
| 638 |
+
"eval_steps_per_second": 3.932,
|
| 639 |
+
"step": 700
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.56,
|
| 643 |
+
"learning_rate": 3e-05,
|
| 644 |
+
"loss": 0.0649,
|
| 645 |
+
"step": 710
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.57,
|
| 649 |
+
"learning_rate": 3e-05,
|
| 650 |
+
"loss": 0.0447,
|
| 651 |
+
"step": 720
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.58,
|
| 655 |
+
"learning_rate": 3e-05,
|
| 656 |
+
"loss": 0.0442,
|
| 657 |
+
"step": 730
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.59,
|
| 661 |
+
"learning_rate": 3e-05,
|
| 662 |
+
"loss": 0.037,
|
| 663 |
+
"step": 740
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.6,
|
| 667 |
+
"learning_rate": 3e-05,
|
| 668 |
+
"loss": 0.0614,
|
| 669 |
+
"step": 750
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.6,
|
| 673 |
+
"eval_accuracy": 0.7773584905660378,
|
| 674 |
+
"eval_f1_macro": 0.6308119664331103,
|
| 675 |
+
"eval_f1_micro": 0.7773584905660378,
|
| 676 |
+
"eval_loss": 0.04885416477918625,
|
| 677 |
+
"eval_precision_macro": 0.6677975283624125,
|
| 678 |
+
"eval_precision_micro": 0.7773584905660378,
|
| 679 |
+
"eval_recall_macro": 0.6360471775658058,
|
| 680 |
+
"eval_recall_micro": 0.7773584905660378,
|
| 681 |
+
"eval_runtime": 67.7832,
|
| 682 |
+
"eval_samples_per_second": 15.638,
|
| 683 |
+
"eval_steps_per_second": 3.91,
|
| 684 |
+
"step": 750
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.6,
|
| 688 |
+
"learning_rate": 3e-05,
|
| 689 |
+
"loss": 0.0649,
|
| 690 |
+
"step": 760
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.61,
|
| 694 |
+
"learning_rate": 3e-05,
|
| 695 |
+
"loss": 0.0426,
|
| 696 |
+
"step": 770
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.62,
|
| 700 |
+
"learning_rate": 3e-05,
|
| 701 |
+
"loss": 0.0347,
|
| 702 |
+
"step": 780
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.63,
|
| 706 |
+
"learning_rate": 3e-05,
|
| 707 |
+
"loss": 0.0414,
|
| 708 |
+
"step": 790
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 0.64,
|
| 712 |
+
"learning_rate": 3e-05,
|
| 713 |
+
"loss": 0.0468,
|
| 714 |
+
"step": 800
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.64,
|
| 718 |
+
"eval_accuracy": 0.7830188679245284,
|
| 719 |
+
"eval_f1_macro": 0.6493890925237205,
|
| 720 |
+
"eval_f1_micro": 0.7830188679245284,
|
| 721 |
+
"eval_loss": 0.044340912252664566,
|
| 722 |
+
"eval_precision_macro": 0.6435014283226803,
|
| 723 |
+
"eval_precision_micro": 0.7830188679245284,
|
| 724 |
+
"eval_recall_macro": 0.6816157451405587,
|
| 725 |
+
"eval_recall_micro": 0.7830188679245284,
|
| 726 |
+
"eval_runtime": 67.2351,
|
| 727 |
+
"eval_samples_per_second": 15.766,
|
| 728 |
+
"eval_steps_per_second": 3.941,
|
| 729 |
+
"step": 800
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.64,
|
| 733 |
+
"learning_rate": 3e-05,
|
| 734 |
+
"loss": 0.052,
|
| 735 |
+
"step": 810
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.65,
|
| 739 |
+
"learning_rate": 3e-05,
|
| 740 |
+
"loss": 0.0414,
|
| 741 |
+
"step": 820
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.66,
|
| 745 |
+
"learning_rate": 3e-05,
|
| 746 |
+
"loss": 0.0342,
|
| 747 |
+
"step": 830
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.67,
|
| 751 |
+
"learning_rate": 3e-05,
|
| 752 |
+
"loss": 0.0451,
|
| 753 |
+
"step": 840
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.68,
|
| 757 |
+
"learning_rate": 3e-05,
|
| 758 |
+
"loss": 0.0477,
|
| 759 |
+
"step": 850
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.68,
|
| 763 |
+
"eval_accuracy": 0.7971698113207547,
|
| 764 |
+
"eval_f1_macro": 0.6662808099368048,
|
| 765 |
+
"eval_f1_micro": 0.7971698113207546,
|
| 766 |
+
"eval_loss": 0.041995830833911896,
|
| 767 |
+
"eval_precision_macro": 0.7040157648486967,
|
| 768 |
+
"eval_precision_micro": 0.7971698113207547,
|
| 769 |
+
"eval_recall_macro": 0.6567342355863813,
|
| 770 |
+
"eval_recall_micro": 0.7971698113207547,
|
| 771 |
+
"eval_runtime": 67.3249,
|
| 772 |
+
"eval_samples_per_second": 15.745,
|
| 773 |
+
"eval_steps_per_second": 3.936,
|
| 774 |
+
"step": 850
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.68,
|
| 778 |
+
"learning_rate": 3e-05,
|
| 779 |
+
"loss": 0.0468,
|
| 780 |
+
"step": 860
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.69,
|
| 784 |
+
"learning_rate": 3e-05,
|
| 785 |
+
"loss": 0.0461,
|
| 786 |
+
"step": 870
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.7,
|
| 790 |
+
"learning_rate": 3e-05,
|
| 791 |
+
"loss": 0.0436,
|
| 792 |
+
"step": 880
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.71,
|
| 796 |
+
"learning_rate": 3e-05,
|
| 797 |
+
"loss": 0.0369,
|
| 798 |
+
"step": 890
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.72,
|
| 802 |
+
"learning_rate": 3e-05,
|
| 803 |
+
"loss": 0.0519,
|
| 804 |
+
"step": 900
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.72,
|
| 808 |
+
"eval_accuracy": 0.7632075471698113,
|
| 809 |
+
"eval_f1_macro": 0.6291599323302522,
|
| 810 |
+
"eval_f1_micro": 0.7632075471698113,
|
| 811 |
+
"eval_loss": 0.04627140238881111,
|
| 812 |
+
"eval_precision_macro": 0.6519385252086033,
|
| 813 |
+
"eval_precision_micro": 0.7632075471698113,
|
| 814 |
+
"eval_recall_macro": 0.6290591814696965,
|
| 815 |
+
"eval_recall_micro": 0.7632075471698113,
|
| 816 |
+
"eval_runtime": 67.0228,
|
| 817 |
+
"eval_samples_per_second": 15.816,
|
| 818 |
+
"eval_steps_per_second": 3.954,
|
| 819 |
+
"step": 900
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.72,
|
| 823 |
+
"learning_rate": 3e-05,
|
| 824 |
+
"loss": 0.0543,
|
| 825 |
+
"step": 910
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.73,
|
| 829 |
+
"learning_rate": 3e-05,
|
| 830 |
+
"loss": 0.0426,
|
| 831 |
+
"step": 920
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.74,
|
| 835 |
+
"learning_rate": 3e-05,
|
| 836 |
+
"loss": 0.0421,
|
| 837 |
+
"step": 930
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.75,
|
| 841 |
+
"learning_rate": 3e-05,
|
| 842 |
+
"loss": 0.0338,
|
| 843 |
+
"step": 940
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.76,
|
| 847 |
+
"learning_rate": 3e-05,
|
| 848 |
+
"loss": 0.0453,
|
| 849 |
+
"step": 950
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.76,
|
| 853 |
+
"eval_accuracy": 0.780188679245283,
|
| 854 |
+
"eval_f1_macro": 0.6564187596520696,
|
| 855 |
+
"eval_f1_micro": 0.780188679245283,
|
| 856 |
+
"eval_loss": 0.042860858142375946,
|
| 857 |
+
"eval_precision_macro": 0.67574812222591,
|
| 858 |
+
"eval_precision_micro": 0.780188679245283,
|
| 859 |
+
"eval_recall_macro": 0.6697872775950671,
|
| 860 |
+
"eval_recall_micro": 0.780188679245283,
|
| 861 |
+
"eval_runtime": 67.3483,
|
| 862 |
+
"eval_samples_per_second": 15.739,
|
| 863 |
+
"eval_steps_per_second": 3.935,
|
| 864 |
+
"step": 950
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.76,
|
| 868 |
+
"learning_rate": 3e-05,
|
| 869 |
+
"loss": 0.0554,
|
| 870 |
+
"step": 960
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.77,
|
| 874 |
+
"learning_rate": 3e-05,
|
| 875 |
+
"loss": 0.0397,
|
| 876 |
+
"step": 970
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.78,
|
| 880 |
+
"learning_rate": 3e-05,
|
| 881 |
+
"loss": 0.0407,
|
| 882 |
+
"step": 980
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.79,
|
| 886 |
+
"learning_rate": 3e-05,
|
| 887 |
+
"loss": 0.0361,
|
| 888 |
+
"step": 990
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 0.79,
|
| 892 |
+
"learning_rate": 3e-05,
|
| 893 |
+
"loss": 0.0452,
|
| 894 |
+
"step": 1000
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.79,
|
| 898 |
+
"eval_accuracy": 0.7377358490566037,
|
| 899 |
+
"eval_f1_macro": 0.6049285124615932,
|
| 900 |
+
"eval_f1_micro": 0.7377358490566037,
|
| 901 |
+
"eval_loss": 0.047125279903411865,
|
| 902 |
+
"eval_precision_macro": 0.6181852032037266,
|
| 903 |
+
"eval_precision_micro": 0.7377358490566037,
|
| 904 |
+
"eval_recall_macro": 0.6300074429793591,
|
| 905 |
+
"eval_recall_micro": 0.7377358490566037,
|
| 906 |
+
"eval_runtime": 66.8035,
|
| 907 |
+
"eval_samples_per_second": 15.867,
|
| 908 |
+
"eval_steps_per_second": 3.967,
|
| 909 |
+
"step": 1000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.8,
|
| 913 |
+
"learning_rate": 3e-05,
|
| 914 |
+
"loss": 0.0482,
|
| 915 |
+
"step": 1010
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.81,
|
| 919 |
+
"learning_rate": 3e-05,
|
| 920 |
+
"loss": 0.0379,
|
| 921 |
+
"step": 1020
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.82,
|
| 925 |
+
"learning_rate": 3e-05,
|
| 926 |
+
"loss": 0.0403,
|
| 927 |
+
"step": 1030
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.83,
|
| 931 |
+
"learning_rate": 3e-05,
|
| 932 |
+
"loss": 0.0471,
|
| 933 |
+
"step": 1040
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.83,
|
| 937 |
+
"learning_rate": 3e-05,
|
| 938 |
+
"loss": 0.0367,
|
| 939 |
+
"step": 1050
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.83,
|
| 943 |
+
"eval_accuracy": 0.7981132075471699,
|
| 944 |
+
"eval_f1_macro": 0.6800660818700823,
|
| 945 |
+
"eval_f1_micro": 0.79811320754717,
|
| 946 |
+
"eval_loss": 0.03875497728586197,
|
| 947 |
+
"eval_precision_macro": 0.6856812225733196,
|
| 948 |
+
"eval_precision_micro": 0.7981132075471699,
|
| 949 |
+
"eval_recall_macro": 0.6992476720564776,
|
| 950 |
+
"eval_recall_micro": 0.7981132075471699,
|
| 951 |
+
"eval_runtime": 66.8444,
|
| 952 |
+
"eval_samples_per_second": 15.858,
|
| 953 |
+
"eval_steps_per_second": 3.964,
|
| 954 |
+
"step": 1050
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.84,
|
| 958 |
+
"learning_rate": 3e-05,
|
| 959 |
+
"loss": 0.0351,
|
| 960 |
+
"step": 1060
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.85,
|
| 964 |
+
"learning_rate": 3e-05,
|
| 965 |
+
"loss": 0.0479,
|
| 966 |
+
"step": 1070
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 0.86,
|
| 970 |
+
"learning_rate": 3e-05,
|
| 971 |
+
"loss": 0.0421,
|
| 972 |
+
"step": 1080
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 0.87,
|
| 976 |
+
"learning_rate": 3e-05,
|
| 977 |
+
"loss": 0.0406,
|
| 978 |
+
"step": 1090
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.87,
|
| 982 |
+
"learning_rate": 3e-05,
|
| 983 |
+
"loss": 0.0377,
|
| 984 |
+
"step": 1100
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.87,
|
| 988 |
+
"eval_accuracy": 0.8,
|
| 989 |
+
"eval_f1_macro": 0.6590911576508658,
|
| 990 |
+
"eval_f1_micro": 0.8000000000000002,
|
| 991 |
+
"eval_loss": 0.03815627098083496,
|
| 992 |
+
"eval_precision_macro": 0.6636349851737382,
|
| 993 |
+
"eval_precision_micro": 0.8,
|
| 994 |
+
"eval_recall_macro": 0.6697553358712118,
|
| 995 |
+
"eval_recall_micro": 0.8,
|
| 996 |
+
"eval_runtime": 66.9434,
|
| 997 |
+
"eval_samples_per_second": 15.834,
|
| 998 |
+
"eval_steps_per_second": 3.959,
|
| 999 |
+
"step": 1100
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.88,
|
| 1003 |
+
"learning_rate": 3e-05,
|
| 1004 |
+
"loss": 0.0365,
|
| 1005 |
+
"step": 1110
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.89,
|
| 1009 |
+
"learning_rate": 3e-05,
|
| 1010 |
+
"loss": 0.0353,
|
| 1011 |
+
"step": 1120
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.9,
|
| 1015 |
+
"learning_rate": 3e-05,
|
| 1016 |
+
"loss": 0.0388,
|
| 1017 |
+
"step": 1130
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.91,
|
| 1021 |
+
"learning_rate": 3e-05,
|
| 1022 |
+
"loss": 0.0358,
|
| 1023 |
+
"step": 1140
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.91,
|
| 1027 |
+
"learning_rate": 3e-05,
|
| 1028 |
+
"loss": 0.0429,
|
| 1029 |
+
"step": 1150
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.91,
|
| 1033 |
+
"eval_accuracy": 0.7952830188679245,
|
| 1034 |
+
"eval_f1_macro": 0.6465609013784224,
|
| 1035 |
+
"eval_f1_micro": 0.7952830188679245,
|
| 1036 |
+
"eval_loss": 0.03976297378540039,
|
| 1037 |
+
"eval_precision_macro": 0.6923924758215005,
|
| 1038 |
+
"eval_precision_micro": 0.7952830188679245,
|
| 1039 |
+
"eval_recall_macro": 0.6441492192889419,
|
| 1040 |
+
"eval_recall_micro": 0.7952830188679245,
|
| 1041 |
+
"eval_runtime": 67.1705,
|
| 1042 |
+
"eval_samples_per_second": 15.781,
|
| 1043 |
+
"eval_steps_per_second": 3.945,
|
| 1044 |
+
"step": 1150
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 0.92,
|
| 1048 |
+
"learning_rate": 3e-05,
|
| 1049 |
+
"loss": 0.0461,
|
| 1050 |
+
"step": 1160
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.93,
|
| 1054 |
+
"learning_rate": 3e-05,
|
| 1055 |
+
"loss": 0.0434,
|
| 1056 |
+
"step": 1170
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 0.94,
|
| 1060 |
+
"learning_rate": 3e-05,
|
| 1061 |
+
"loss": 0.0524,
|
| 1062 |
+
"step": 1180
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.95,
|
| 1066 |
+
"learning_rate": 3e-05,
|
| 1067 |
+
"loss": 0.0362,
|
| 1068 |
+
"step": 1190
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.95,
|
| 1072 |
+
"learning_rate": 3e-05,
|
| 1073 |
+
"loss": 0.0451,
|
| 1074 |
+
"step": 1200
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.95,
|
| 1078 |
+
"eval_accuracy": 0.7943396226415095,
|
| 1079 |
+
"eval_f1_macro": 0.6535399936575059,
|
| 1080 |
+
"eval_f1_micro": 0.7943396226415095,
|
| 1081 |
+
"eval_loss": 0.037755727767944336,
|
| 1082 |
+
"eval_precision_macro": 0.6712905678869693,
|
| 1083 |
+
"eval_precision_micro": 0.7943396226415095,
|
| 1084 |
+
"eval_recall_macro": 0.6537773538776073,
|
| 1085 |
+
"eval_recall_micro": 0.7943396226415095,
|
| 1086 |
+
"eval_runtime": 66.9611,
|
| 1087 |
+
"eval_samples_per_second": 15.83,
|
| 1088 |
+
"eval_steps_per_second": 3.958,
|
| 1089 |
+
"step": 1200
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.96,
|
| 1093 |
+
"learning_rate": 3e-05,
|
| 1094 |
+
"loss": 0.0456,
|
| 1095 |
+
"step": 1210
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.97,
|
| 1099 |
+
"learning_rate": 3e-05,
|
| 1100 |
+
"loss": 0.0455,
|
| 1101 |
+
"step": 1220
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.98,
|
| 1105 |
+
"learning_rate": 3e-05,
|
| 1106 |
+
"loss": 0.0409,
|
| 1107 |
+
"step": 1230
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.99,
|
| 1111 |
+
"learning_rate": 3e-05,
|
| 1112 |
+
"loss": 0.037,
|
| 1113 |
+
"step": 1240
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.99,
|
| 1117 |
+
"learning_rate": 3e-05,
|
| 1118 |
+
"loss": 0.0347,
|
| 1119 |
+
"step": 1250
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.99,
|
| 1123 |
+
"eval_accuracy": 0.7839622641509434,
|
| 1124 |
+
"eval_f1_macro": 0.6330944207402169,
|
| 1125 |
+
"eval_f1_micro": 0.7839622641509434,
|
| 1126 |
+
"eval_loss": 0.041340529918670654,
|
| 1127 |
+
"eval_precision_macro": 0.6735372413807635,
|
| 1128 |
+
"eval_precision_micro": 0.7839622641509434,
|
| 1129 |
+
"eval_recall_macro": 0.6450299050285588,
|
| 1130 |
+
"eval_recall_micro": 0.7839622641509434,
|
| 1131 |
+
"eval_runtime": 66.9053,
|
| 1132 |
+
"eval_samples_per_second": 15.843,
|
| 1133 |
+
"eval_steps_per_second": 3.961,
|
| 1134 |
+
"step": 1250
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 1.0,
|
| 1138 |
+
"learning_rate": 3e-05,
|
| 1139 |
+
"loss": 0.0421,
|
| 1140 |
+
"step": 1260
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.01,
|
| 1144 |
+
"learning_rate": 3e-05,
|
| 1145 |
+
"loss": 0.041,
|
| 1146 |
+
"step": 1270
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 1.02,
|
| 1150 |
+
"learning_rate": 3e-05,
|
| 1151 |
+
"loss": 0.033,
|
| 1152 |
+
"step": 1280
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 1.03,
|
| 1156 |
+
"learning_rate": 3e-05,
|
| 1157 |
+
"loss": 0.036,
|
| 1158 |
+
"step": 1290
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.03,
|
| 1162 |
+
"learning_rate": 3e-05,
|
| 1163 |
+
"loss": 0.0378,
|
| 1164 |
+
"step": 1300
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.03,
|
| 1168 |
+
"eval_accuracy": 0.8047169811320755,
|
| 1169 |
+
"eval_f1_macro": 0.6488791804614907,
|
| 1170 |
+
"eval_f1_micro": 0.8047169811320755,
|
| 1171 |
+
"eval_loss": 0.037683386355638504,
|
| 1172 |
+
"eval_precision_macro": 0.7109359814450084,
|
| 1173 |
+
"eval_precision_micro": 0.8047169811320755,
|
| 1174 |
+
"eval_recall_macro": 0.6387082579227776,
|
| 1175 |
+
"eval_recall_micro": 0.8047169811320755,
|
| 1176 |
+
"eval_runtime": 67.3206,
|
| 1177 |
+
"eval_samples_per_second": 15.746,
|
| 1178 |
+
"eval_steps_per_second": 3.936,
|
| 1179 |
+
"step": 1300
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.04,
|
| 1183 |
+
"learning_rate": 3e-05,
|
| 1184 |
+
"loss": 0.0343,
|
| 1185 |
+
"step": 1310
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.05,
|
| 1189 |
+
"learning_rate": 3e-05,
|
| 1190 |
+
"loss": 0.0321,
|
| 1191 |
+
"step": 1320
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 1.06,
|
| 1195 |
+
"learning_rate": 3e-05,
|
| 1196 |
+
"loss": 0.031,
|
| 1197 |
+
"step": 1330
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.06,
|
| 1201 |
+
"learning_rate": 3e-05,
|
| 1202 |
+
"loss": 0.039,
|
| 1203 |
+
"step": 1340
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.07,
|
| 1207 |
+
"learning_rate": 3e-05,
|
| 1208 |
+
"loss": 0.0357,
|
| 1209 |
+
"step": 1350
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 1.07,
|
| 1213 |
+
"eval_accuracy": 0.8028301886792453,
|
| 1214 |
+
"eval_f1_macro": 0.6648963473667772,
|
| 1215 |
+
"eval_f1_micro": 0.8028301886792453,
|
| 1216 |
+
"eval_loss": 0.03860827535390854,
|
| 1217 |
+
"eval_precision_macro": 0.6898539099210392,
|
| 1218 |
+
"eval_precision_micro": 0.8028301886792453,
|
| 1219 |
+
"eval_recall_macro": 0.6558796396655843,
|
| 1220 |
+
"eval_recall_micro": 0.8028301886792453,
|
| 1221 |
+
"eval_runtime": 67.0656,
|
| 1222 |
+
"eval_samples_per_second": 15.805,
|
| 1223 |
+
"eval_steps_per_second": 3.951,
|
| 1224 |
+
"step": 1350
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.08,
|
| 1228 |
+
"learning_rate": 3e-05,
|
| 1229 |
+
"loss": 0.0445,
|
| 1230 |
+
"step": 1360
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 1.09,
|
| 1234 |
+
"learning_rate": 3e-05,
|
| 1235 |
+
"loss": 0.0375,
|
| 1236 |
+
"step": 1370
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 1.1,
|
| 1240 |
+
"learning_rate": 3e-05,
|
| 1241 |
+
"loss": 0.0375,
|
| 1242 |
+
"step": 1380
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.1,
|
| 1246 |
+
"learning_rate": 3e-05,
|
| 1247 |
+
"loss": 0.0333,
|
| 1248 |
+
"step": 1390
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.11,
|
| 1252 |
+
"learning_rate": 3e-05,
|
| 1253 |
+
"loss": 0.0418,
|
| 1254 |
+
"step": 1400
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 1.11,
|
| 1258 |
+
"eval_accuracy": 0.7962264150943397,
|
| 1259 |
+
"eval_f1_macro": 0.6910242491250081,
|
| 1260 |
+
"eval_f1_micro": 0.7962264150943396,
|
| 1261 |
+
"eval_loss": 0.0368194542825222,
|
| 1262 |
+
"eval_precision_macro": 0.7114033533579757,
|
| 1263 |
+
"eval_precision_micro": 0.7962264150943397,
|
| 1264 |
+
"eval_recall_macro": 0.6942176996685531,
|
| 1265 |
+
"eval_recall_micro": 0.7962264150943397,
|
| 1266 |
+
"eval_runtime": 66.8832,
|
| 1267 |
+
"eval_samples_per_second": 15.849,
|
| 1268 |
+
"eval_steps_per_second": 3.962,
|
| 1269 |
+
"step": 1400
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.12,
|
| 1273 |
+
"learning_rate": 3e-05,
|
| 1274 |
+
"loss": 0.0414,
|
| 1275 |
+
"step": 1410
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.13,
|
| 1279 |
+
"learning_rate": 3e-05,
|
| 1280 |
+
"loss": 0.0357,
|
| 1281 |
+
"step": 1420
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.14,
|
| 1285 |
+
"learning_rate": 3e-05,
|
| 1286 |
+
"loss": 0.0272,
|
| 1287 |
+
"step": 1430
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.14,
|
| 1291 |
+
"learning_rate": 3e-05,
|
| 1292 |
+
"loss": 0.0323,
|
| 1293 |
+
"step": 1440
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 1.15,
|
| 1297 |
+
"learning_rate": 3e-05,
|
| 1298 |
+
"loss": 0.0293,
|
| 1299 |
+
"step": 1450
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 1.15,
|
| 1303 |
+
"eval_accuracy": 0.8141509433962264,
|
| 1304 |
+
"eval_f1_macro": 0.7097996478763092,
|
| 1305 |
+
"eval_f1_micro": 0.8141509433962264,
|
| 1306 |
+
"eval_loss": 0.035770244896411896,
|
| 1307 |
+
"eval_precision_macro": 0.7222302630120379,
|
| 1308 |
+
"eval_precision_micro": 0.8141509433962264,
|
| 1309 |
+
"eval_recall_macro": 0.7125706602249756,
|
| 1310 |
+
"eval_recall_micro": 0.8141509433962264,
|
| 1311 |
+
"eval_runtime": 67.0694,
|
| 1312 |
+
"eval_samples_per_second": 15.805,
|
| 1313 |
+
"eval_steps_per_second": 3.951,
|
| 1314 |
+
"step": 1450
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 1.15,
|
| 1318 |
+
"step": 1450,
|
| 1319 |
+
"total_flos": 3.612646182806976e+17,
|
| 1320 |
+
"train_loss": 0.07879953698865298,
|
| 1321 |
+
"train_runtime": 5948.326,
|
| 1322 |
+
"train_samples_per_second": 3.9,
|
| 1323 |
+
"train_steps_per_second": 0.244
|
| 1324 |
}
|
| 1325 |
],
|
| 1326 |
"logging_steps": 10,
|
| 1327 |
+
"max_steps": 1450,
|
| 1328 |
"num_input_tokens_seen": 0,
|
| 1329 |
"num_train_epochs": 2,
|
| 1330 |
+
"save_steps": 250,
|
| 1331 |
+
"total_flos": 3.612646182806976e+17,
|
| 1332 |
"train_batch_size": 4,
|
| 1333 |
"trial_name": null,
|
| 1334 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:add2669eaaf689daa0607cb945e0a514be11a77fcad05794f011caf4efc79995
|
| 3 |
size 6648
|