Commit
•
7e4e7a7
1
Parent(s):
dba646e
Model save
Browse files- README.md +5 -6
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- all_results.json +10 -10
- eval_results.json +5 -5
- mm_projector.bin +1 -1
- special_tokens_map.json +7 -1
- train_results.json +5 -5
- trainer_state.json +1091 -29
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -2,11 +2,10 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
-
- alignment-handbook
|
| 6 |
- generated_from_trainer
|
| 7 |
base_model: mistralai/Mistral-7B-v0.1
|
| 8 |
datasets:
|
| 9 |
-
-
|
| 10 |
model-index:
|
| 11 |
- name: Test_with_new_script
|
| 12 |
results: []
|
|
@@ -17,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# Test_with_new_script
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss:
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -38,7 +37,7 @@ More information needed
|
|
| 38 |
### Training hyperparameters
|
| 39 |
|
| 40 |
The following hyperparameters were used during training:
|
| 41 |
-
- learning_rate:
|
| 42 |
- train_batch_size: 32
|
| 43 |
- eval_batch_size: 8
|
| 44 |
- seed: 42
|
|
@@ -55,7 +54,7 @@ The following hyperparameters were used during training:
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 58 |
-
| 1.
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
base_model: mistralai/Mistral-7B-v0.1
|
| 7 |
datasets:
|
| 8 |
+
- generator
|
| 9 |
model-index:
|
| 10 |
- name: Test_with_new_script
|
| 11 |
results: []
|
|
|
|
| 16 |
|
| 17 |
# Test_with_new_script
|
| 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 generator dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.0115
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 2e-05
|
| 41 |
- train_batch_size: 32
|
| 42 |
- eval_batch_size: 8
|
| 43 |
- seed: 42
|
|
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 1.0177 | 1.0 | 907 | 1.0115 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
adapter_config.json
CHANGED
|
@@ -19,13 +19,13 @@
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
| 22 |
-
"k_proj",
|
| 23 |
-
"gate_proj",
|
| 24 |
"up_proj",
|
| 25 |
-
"v_proj",
|
| 26 |
"o_proj",
|
|
|
|
| 27 |
"down_proj",
|
| 28 |
-
"
|
|
|
|
|
|
|
| 29 |
],
|
| 30 |
"task_type": "CAUSAL_LM"
|
| 31 |
}
|
|
|
|
| 19 |
"rank_pattern": {},
|
| 20 |
"revision": null,
|
| 21 |
"target_modules": [
|
|
|
|
|
|
|
| 22 |
"up_proj",
|
|
|
|
| 23 |
"o_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
"down_proj",
|
| 26 |
+
"k_proj",
|
| 27 |
+
"q_proj",
|
| 28 |
+
"gate_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 83946192
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0c299d01fa630656aebfc0d6de602c24c3caa6afd9172d390e9b045b60b04a6
|
| 3 |
size 83946192
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"train_loss": 1.
|
| 9 |
-
"train_runtime":
|
| 10 |
-
"train_samples":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.0114790201187134,
|
| 4 |
+
"eval_runtime": 504.2941,
|
| 5 |
+
"eval_samples": 6440,
|
| 6 |
+
"eval_samples_per_second": 12.77,
|
| 7 |
+
"eval_steps_per_second": 0.799,
|
| 8 |
+
"train_loss": 1.0047753110873003,
|
| 9 |
+
"train_runtime": 15080.3332,
|
| 10 |
+
"train_samples": 58034,
|
| 11 |
+
"train_samples_per_second": 3.848,
|
| 12 |
+
"train_steps_per_second": 0.06
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.0114790201187134,
|
| 4 |
+
"eval_runtime": 504.2941,
|
| 5 |
+
"eval_samples": 6440,
|
| 6 |
+
"eval_samples_per_second": 12.77,
|
| 7 |
+
"eval_steps_per_second": 0.799
|
| 8 |
}
|
mm_projector.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16795126
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9d8b981cd27c35e3aa60f7b7fe28ee2ccb418a77b291607c9f298f781ebffce
|
| 3 |
size 16795126
|
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<unk>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"unk_token": {
|
| 24 |
"content": "<unk>",
|
| 25 |
"lstrip": false,
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 1.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.0047753110873003,
|
| 4 |
+
"train_runtime": 15080.3332,
|
| 5 |
+
"train_samples": 58034,
|
| 6 |
+
"train_samples_per_second": 3.848,
|
| 7 |
+
"train_steps_per_second": 0.06
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -3,65 +3,1127 @@
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 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": 0.
|
| 13 |
-
"learning_rate":
|
| 14 |
-
"loss": 1.
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
-
"epoch": 0.
|
| 19 |
-
"learning_rate":
|
| 20 |
-
"loss": 1.
|
| 21 |
"step": 5
|
| 22 |
},
|
| 23 |
{
|
| 24 |
-
"epoch": 0.
|
| 25 |
-
"learning_rate":
|
| 26 |
-
"loss":
|
| 27 |
"step": 10
|
| 28 |
},
|
| 29 |
{
|
| 30 |
-
"epoch": 0.
|
| 31 |
-
"learning_rate":
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
-
"epoch": 0.
|
| 37 |
-
"learning_rate":
|
| 38 |
-
"loss": 1.
|
| 39 |
"step": 20
|
| 40 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
{
|
| 42 |
"epoch": 1.0,
|
| 43 |
-
"eval_loss":
|
| 44 |
-
"eval_runtime":
|
| 45 |
-
"eval_samples_per_second":
|
| 46 |
-
"eval_steps_per_second": 0.
|
| 47 |
-
"step":
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"epoch": 1.0,
|
| 51 |
-
"step":
|
| 52 |
-
"total_flos":
|
| 53 |
-
"train_loss": 1.
|
| 54 |
-
"train_runtime":
|
| 55 |
-
"train_samples_per_second":
|
| 56 |
-
"train_steps_per_second": 0.
|
| 57 |
}
|
| 58 |
],
|
| 59 |
"logging_steps": 5,
|
| 60 |
-
"max_steps":
|
| 61 |
"num_input_tokens_seen": 0,
|
| 62 |
"num_train_epochs": 1,
|
| 63 |
"save_steps": 100,
|
| 64 |
-
"total_flos":
|
| 65 |
"train_batch_size": 32,
|
| 66 |
"trial_name": null,
|
| 67 |
"trial_params": null
|
|
|
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
"epoch": 1.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 907,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 2.197802197802198e-07,
|
| 14 |
+
"loss": 1.0052,
|
| 15 |
"step": 1
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 1.098901098901099e-06,
|
| 20 |
+
"loss": 1.0232,
|
| 21 |
"step": 5
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 2.197802197802198e-06,
|
| 26 |
+
"loss": 0.9955,
|
| 27 |
"step": 10
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 3.2967032967032968e-06,
|
| 32 |
+
"loss": 1.0264,
|
| 33 |
"step": 15
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 4.395604395604396e-06,
|
| 38 |
+
"loss": 1.0161,
|
| 39 |
"step": 20
|
| 40 |
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 5.494505494505495e-06,
|
| 44 |
+
"loss": 1.0177,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 6.5934065934065935e-06,
|
| 50 |
+
"loss": 1.0196,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 7.692307692307694e-06,
|
| 56 |
+
"loss": 1.0003,
|
| 57 |
+
"step": 35
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 8.791208791208792e-06,
|
| 62 |
+
"loss": 1.0079,
|
| 63 |
+
"step": 40
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 9.890109890109892e-06,
|
| 68 |
+
"loss": 1.0233,
|
| 69 |
+
"step": 45
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"learning_rate": 1.098901098901099e-05,
|
| 74 |
+
"loss": 1.032,
|
| 75 |
+
"step": 50
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 1.2087912087912089e-05,
|
| 80 |
+
"loss": 1.0061,
|
| 81 |
+
"step": 55
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.07,
|
| 85 |
+
"learning_rate": 1.3186813186813187e-05,
|
| 86 |
+
"loss": 1.0288,
|
| 87 |
+
"step": 60
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07,
|
| 91 |
+
"learning_rate": 1.4285714285714287e-05,
|
| 92 |
+
"loss": 1.027,
|
| 93 |
+
"step": 65
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08,
|
| 97 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 98 |
+
"loss": 1.0183,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 1.6483516483516486e-05,
|
| 104 |
+
"loss": 1.0042,
|
| 105 |
+
"step": 75
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.09,
|
| 109 |
+
"learning_rate": 1.7582417582417584e-05,
|
| 110 |
+
"loss": 1.0099,
|
| 111 |
+
"step": 80
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.09,
|
| 115 |
+
"learning_rate": 1.8681318681318682e-05,
|
| 116 |
+
"loss": 0.9873,
|
| 117 |
+
"step": 85
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.1,
|
| 121 |
+
"learning_rate": 1.9780219780219784e-05,
|
| 122 |
+
"loss": 1.017,
|
| 123 |
+
"step": 90
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.1,
|
| 127 |
+
"learning_rate": 1.999881422898077e-05,
|
| 128 |
+
"loss": 1.0021,
|
| 129 |
+
"step": 95
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.11,
|
| 133 |
+
"learning_rate": 1.999399751616869e-05,
|
| 134 |
+
"loss": 1.0193,
|
| 135 |
+
"step": 100
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12,
|
| 139 |
+
"learning_rate": 1.9985477534331582e-05,
|
| 140 |
+
"loss": 1.0003,
|
| 141 |
+
"step": 105
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.12,
|
| 145 |
+
"learning_rate": 1.9973257440542974e-05,
|
| 146 |
+
"loss": 0.9745,
|
| 147 |
+
"step": 110
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.13,
|
| 151 |
+
"learning_rate": 1.9957341762950346e-05,
|
| 152 |
+
"loss": 1.0004,
|
| 153 |
+
"step": 115
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.13,
|
| 157 |
+
"learning_rate": 1.9937736399097282e-05,
|
| 158 |
+
"loss": 1.0368,
|
| 159 |
+
"step": 120
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.14,
|
| 163 |
+
"learning_rate": 1.9914448613738107e-05,
|
| 164 |
+
"loss": 0.9986,
|
| 165 |
+
"step": 125
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.14,
|
| 169 |
+
"learning_rate": 1.9887487036145942e-05,
|
| 170 |
+
"loss": 0.9896,
|
| 171 |
+
"step": 130
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.15,
|
| 175 |
+
"learning_rate": 1.985686165691514e-05,
|
| 176 |
+
"loss": 1.0119,
|
| 177 |
+
"step": 135
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.15,
|
| 181 |
+
"learning_rate": 1.9822583824259283e-05,
|
| 182 |
+
"loss": 1.0197,
|
| 183 |
+
"step": 140
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.16,
|
| 187 |
+
"learning_rate": 1.978466623980609e-05,
|
| 188 |
+
"loss": 0.9946,
|
| 189 |
+
"step": 145
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.17,
|
| 193 |
+
"learning_rate": 1.9743122953890857e-05,
|
| 194 |
+
"loss": 1.0102,
|
| 195 |
+
"step": 150
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.17,
|
| 199 |
+
"learning_rate": 1.9697969360350098e-05,
|
| 200 |
+
"loss": 0.985,
|
| 201 |
+
"step": 155
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.18,
|
| 205 |
+
"learning_rate": 1.9649222190817382e-05,
|
| 206 |
+
"loss": 1.0325,
|
| 207 |
+
"step": 160
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.18,
|
| 211 |
+
"learning_rate": 1.9596899508523432e-05,
|
| 212 |
+
"loss": 1.0178,
|
| 213 |
+
"step": 165
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.19,
|
| 217 |
+
"learning_rate": 1.9541020701602814e-05,
|
| 218 |
+
"loss": 0.9963,
|
| 219 |
+
"step": 170
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.19,
|
| 223 |
+
"learning_rate": 1.948160647590966e-05,
|
| 224 |
+
"loss": 1.0048,
|
| 225 |
+
"step": 175
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.2,
|
| 229 |
+
"learning_rate": 1.941867884734515e-05,
|
| 230 |
+
"loss": 0.9911,
|
| 231 |
+
"step": 180
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.2,
|
| 235 |
+
"learning_rate": 1.9352261133699513e-05,
|
| 236 |
+
"loss": 1.0168,
|
| 237 |
+
"step": 185
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.21,
|
| 241 |
+
"learning_rate": 1.928237794601165e-05,
|
| 242 |
+
"loss": 1.0117,
|
| 243 |
+
"step": 190
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.21,
|
| 247 |
+
"learning_rate": 1.920905517944954e-05,
|
| 248 |
+
"loss": 1.0043,
|
| 249 |
+
"step": 195
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.22,
|
| 253 |
+
"learning_rate": 1.9132320003714756e-05,
|
| 254 |
+
"loss": 1.0325,
|
| 255 |
+
"step": 200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.23,
|
| 259 |
+
"learning_rate": 1.905220085297482e-05,
|
| 260 |
+
"loss": 1.0101,
|
| 261 |
+
"step": 205
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.23,
|
| 265 |
+
"learning_rate": 1.8968727415326885e-05,
|
| 266 |
+
"loss": 0.9974,
|
| 267 |
+
"step": 210
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.24,
|
| 271 |
+
"learning_rate": 1.888193062179685e-05,
|
| 272 |
+
"loss": 1.0047,
|
| 273 |
+
"step": 215
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.24,
|
| 277 |
+
"learning_rate": 1.87918426348779e-05,
|
| 278 |
+
"loss": 1.0254,
|
| 279 |
+
"step": 220
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.25,
|
| 283 |
+
"learning_rate": 1.8698496836612693e-05,
|
| 284 |
+
"loss": 1.0169,
|
| 285 |
+
"step": 225
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.25,
|
| 289 |
+
"learning_rate": 1.86019278162237e-05,
|
| 290 |
+
"loss": 0.9984,
|
| 291 |
+
"step": 230
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.26,
|
| 295 |
+
"learning_rate": 1.8502171357296144e-05,
|
| 296 |
+
"loss": 1.0126,
|
| 297 |
+
"step": 235
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.26,
|
| 301 |
+
"learning_rate": 1.8399264424518466e-05,
|
| 302 |
+
"loss": 0.9978,
|
| 303 |
+
"step": 240
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.27,
|
| 307 |
+
"learning_rate": 1.8293245149985055e-05,
|
| 308 |
+
"loss": 0.9965,
|
| 309 |
+
"step": 245
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.28,
|
| 313 |
+
"learning_rate": 1.8184152819066437e-05,
|
| 314 |
+
"loss": 0.9948,
|
| 315 |
+
"step": 250
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.28,
|
| 319 |
+
"learning_rate": 1.8072027855852098e-05,
|
| 320 |
+
"loss": 1.0217,
|
| 321 |
+
"step": 255
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.29,
|
| 325 |
+
"learning_rate": 1.7956911808171375e-05,
|
| 326 |
+
"loss": 0.9937,
|
| 327 |
+
"step": 260
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.29,
|
| 331 |
+
"learning_rate": 1.783884733219794e-05,
|
| 332 |
+
"loss": 1.0244,
|
| 333 |
+
"step": 265
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.3,
|
| 337 |
+
"learning_rate": 1.7717878176643563e-05,
|
| 338 |
+
"loss": 0.9868,
|
| 339 |
+
"step": 270
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3,
|
| 343 |
+
"learning_rate": 1.7594049166547073e-05,
|
| 344 |
+
"loss": 1.0318,
|
| 345 |
+
"step": 275
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.31,
|
| 349 |
+
"learning_rate": 1.7467406186664474e-05,
|
| 350 |
+
"loss": 1.0055,
|
| 351 |
+
"step": 280
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.31,
|
| 355 |
+
"learning_rate": 1.7337996164466373e-05,
|
| 356 |
+
"loss": 1.0186,
|
| 357 |
+
"step": 285
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.32,
|
| 361 |
+
"learning_rate": 1.7205867052749025e-05,
|
| 362 |
+
"loss": 0.9931,
|
| 363 |
+
"step": 290
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.33,
|
| 367 |
+
"learning_rate": 1.7071067811865477e-05,
|
| 368 |
+
"loss": 0.9745,
|
| 369 |
+
"step": 295
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.33,
|
| 373 |
+
"learning_rate": 1.693364839158333e-05,
|
| 374 |
+
"loss": 0.9722,
|
| 375 |
+
"step": 300
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.34,
|
| 379 |
+
"learning_rate": 1.67936597125759e-05,
|
| 380 |
+
"loss": 0.9903,
|
| 381 |
+
"step": 305
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.34,
|
| 385 |
+
"learning_rate": 1.665115364755357e-05,
|
| 386 |
+
"loss": 1.0161,
|
| 387 |
+
"step": 310
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.35,
|
| 391 |
+
"learning_rate": 1.650618300204242e-05,
|
| 392 |
+
"loss": 1.024,
|
| 393 |
+
"step": 315
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.35,
|
| 397 |
+
"learning_rate": 1.6358801494817172e-05,
|
| 398 |
+
"loss": 1.0145,
|
| 399 |
+
"step": 320
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.36,
|
| 403 |
+
"learning_rate": 1.6209063737995716e-05,
|
| 404 |
+
"loss": 1.0042,
|
| 405 |
+
"step": 325
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.36,
|
| 409 |
+
"learning_rate": 1.605702521680263e-05,
|
| 410 |
+
"loss": 0.9978,
|
| 411 |
+
"step": 330
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.37,
|
| 415 |
+
"learning_rate": 1.5902742269009198e-05,
|
| 416 |
+
"loss": 1.0053,
|
| 417 |
+
"step": 335
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.37,
|
| 421 |
+
"learning_rate": 1.5746272064057438e-05,
|
| 422 |
+
"loss": 1.0039,
|
| 423 |
+
"step": 340
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.38,
|
| 427 |
+
"learning_rate": 1.5587672581876053e-05,
|
| 428 |
+
"loss": 0.9971,
|
| 429 |
+
"step": 345
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.39,
|
| 433 |
+
"learning_rate": 1.5427002591395966e-05,
|
| 434 |
+
"loss": 1.0039,
|
| 435 |
+
"step": 350
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.39,
|
| 439 |
+
"learning_rate": 1.526432162877356e-05,
|
| 440 |
+
"loss": 1.027,
|
| 441 |
+
"step": 355
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.4,
|
| 445 |
+
"learning_rate": 1.5099689975329584e-05,
|
| 446 |
+
"loss": 1.0024,
|
| 447 |
+
"step": 360
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.4,
|
| 451 |
+
"learning_rate": 1.4933168635211956e-05,
|
| 452 |
+
"loss": 0.9885,
|
| 453 |
+
"step": 365
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.41,
|
| 457 |
+
"learning_rate": 1.4764819312790706e-05,
|
| 458 |
+
"loss": 1.0057,
|
| 459 |
+
"step": 370
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.41,
|
| 463 |
+
"learning_rate": 1.4594704389793477e-05,
|
| 464 |
+
"loss": 1.004,
|
| 465 |
+
"step": 375
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.42,
|
| 469 |
+
"learning_rate": 1.4422886902190014e-05,
|
| 470 |
+
"loss": 0.9862,
|
| 471 |
+
"step": 380
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.42,
|
| 475 |
+
"learning_rate": 1.4249430516834222e-05,
|
| 476 |
+
"loss": 1.0274,
|
| 477 |
+
"step": 385
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.43,
|
| 481 |
+
"learning_rate": 1.4074399507872455e-05,
|
| 482 |
+
"loss": 1.0215,
|
| 483 |
+
"step": 390
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.44,
|
| 487 |
+
"learning_rate": 1.3897858732926794e-05,
|
| 488 |
+
"loss": 0.9889,
|
| 489 |
+
"step": 395
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.44,
|
| 493 |
+
"learning_rate": 1.3719873609062078e-05,
|
| 494 |
+
"loss": 0.9888,
|
| 495 |
+
"step": 400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.45,
|
| 499 |
+
"learning_rate": 1.3540510088545652e-05,
|
| 500 |
+
"loss": 1.0109,
|
| 501 |
+
"step": 405
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.45,
|
| 505 |
+
"learning_rate": 1.3359834634408828e-05,
|
| 506 |
+
"loss": 0.9834,
|
| 507 |
+
"step": 410
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.46,
|
| 511 |
+
"learning_rate": 1.3177914195819018e-05,
|
| 512 |
+
"loss": 1.0123,
|
| 513 |
+
"step": 415
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.46,
|
| 517 |
+
"learning_rate": 1.2994816183271787e-05,
|
| 518 |
+
"loss": 1.0013,
|
| 519 |
+
"step": 420
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.47,
|
| 523 |
+
"learning_rate": 1.2810608443611943e-05,
|
| 524 |
+
"loss": 1.0126,
|
| 525 |
+
"step": 425
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.47,
|
| 529 |
+
"learning_rate": 1.2625359234892906e-05,
|
| 530 |
+
"loss": 1.009,
|
| 531 |
+
"step": 430
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.48,
|
| 535 |
+
"learning_rate": 1.2439137201083772e-05,
|
| 536 |
+
"loss": 1.0251,
|
| 537 |
+
"step": 435
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.49,
|
| 541 |
+
"learning_rate": 1.2252011346633306e-05,
|
| 542 |
+
"loss": 0.9926,
|
| 543 |
+
"step": 440
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.49,
|
| 547 |
+
"learning_rate": 1.2064051010900397e-05,
|
| 548 |
+
"loss": 1.0018,
|
| 549 |
+
"step": 445
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.5,
|
| 553 |
+
"learning_rate": 1.1875325842460424e-05,
|
| 554 |
+
"loss": 0.9847,
|
| 555 |
+
"step": 450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.5,
|
| 559 |
+
"learning_rate": 1.1685905773296992e-05,
|
| 560 |
+
"loss": 0.9991,
|
| 561 |
+
"step": 455
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.51,
|
| 565 |
+
"learning_rate": 1.1495860992888712e-05,
|
| 566 |
+
"loss": 1.0106,
|
| 567 |
+
"step": 460
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.51,
|
| 571 |
+
"learning_rate": 1.130526192220052e-05,
|
| 572 |
+
"loss": 1.0096,
|
| 573 |
+
"step": 465
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.52,
|
| 577 |
+
"learning_rate": 1.1114179187589233e-05,
|
| 578 |
+
"loss": 1.02,
|
| 579 |
+
"step": 470
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.52,
|
| 583 |
+
"learning_rate": 1.092268359463302e-05,
|
| 584 |
+
"loss": 0.9931,
|
| 585 |
+
"step": 475
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.53,
|
| 589 |
+
"learning_rate": 1.0730846101894428e-05,
|
| 590 |
+
"loss": 1.0,
|
| 591 |
+
"step": 480
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.53,
|
| 595 |
+
"learning_rate": 1.0538737794626735e-05,
|
| 596 |
+
"loss": 1.0172,
|
| 597 |
+
"step": 485
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.54,
|
| 601 |
+
"learning_rate": 1.0346429858433354e-05,
|
| 602 |
+
"loss": 1.0125,
|
| 603 |
+
"step": 490
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.55,
|
| 607 |
+
"learning_rate": 1.0153993552890069e-05,
|
| 608 |
+
"loss": 1.0016,
|
| 609 |
+
"step": 495
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.55,
|
| 613 |
+
"learning_rate": 9.961500185139843e-06,
|
| 614 |
+
"loss": 1.0004,
|
| 615 |
+
"step": 500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.56,
|
| 619 |
+
"learning_rate": 9.769021083469991e-06,
|
| 620 |
+
"loss": 0.9909,
|
| 621 |
+
"step": 505
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.56,
|
| 625 |
+
"learning_rate": 9.576627570881551e-06,
|
| 626 |
+
"loss": 0.9905,
|
| 627 |
+
"step": 510
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.57,
|
| 631 |
+
"learning_rate": 9.384390938660572e-06,
|
| 632 |
+
"loss": 1.0142,
|
| 633 |
+
"step": 515
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.57,
|
| 637 |
+
"learning_rate": 9.192382419961208e-06,
|
| 638 |
+
"loss": 1.0016,
|
| 639 |
+
"step": 520
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.58,
|
| 643 |
+
"learning_rate": 9.000673163410287e-06,
|
| 644 |
+
"loss": 0.9803,
|
| 645 |
+
"step": 525
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.58,
|
| 649 |
+
"learning_rate": 8.809334206743251e-06,
|
| 650 |
+
"loss": 0.996,
|
| 651 |
+
"step": 530
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.59,
|
| 655 |
+
"learning_rate": 8.618436450481182e-06,
|
| 656 |
+
"loss": 0.9945,
|
| 657 |
+
"step": 535
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.6,
|
| 661 |
+
"learning_rate": 8.428050631658628e-06,
|
| 662 |
+
"loss": 1.004,
|
| 663 |
+
"step": 540
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.6,
|
| 667 |
+
"learning_rate": 8.238247297612092e-06,
|
| 668 |
+
"loss": 0.9999,
|
| 669 |
+
"step": 545
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.61,
|
| 673 |
+
"learning_rate": 8.04909677983872e-06,
|
| 674 |
+
"loss": 0.9738,
|
| 675 |
+
"step": 550
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.61,
|
| 679 |
+
"learning_rate": 7.860669167935028e-06,
|
| 680 |
+
"loss": 0.9883,
|
| 681 |
+
"step": 555
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.62,
|
| 685 |
+
"learning_rate": 7.673034283625258e-06,
|
| 686 |
+
"loss": 0.9888,
|
| 687 |
+
"step": 560
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.62,
|
| 691 |
+
"learning_rate": 7.486261654888974e-06,
|
| 692 |
+
"loss": 1.0127,
|
| 693 |
+
"step": 565
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.63,
|
| 697 |
+
"learning_rate": 7.300420490197524e-06,
|
| 698 |
+
"loss": 1.0114,
|
| 699 |
+
"step": 570
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.63,
|
| 703 |
+
"learning_rate": 7.115579652868878e-06,
|
| 704 |
+
"loss": 1.0012,
|
| 705 |
+
"step": 575
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.64,
|
| 709 |
+
"learning_rate": 6.9318076355503835e-06,
|
| 710 |
+
"loss": 1.0039,
|
| 711 |
+
"step": 580
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.64,
|
| 715 |
+
"learning_rate": 6.749172534838849e-06,
|
| 716 |
+
"loss": 0.9927,
|
| 717 |
+
"step": 585
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.65,
|
| 721 |
+
"learning_rate": 6.5677420260474055e-06,
|
| 722 |
+
"loss": 0.9996,
|
| 723 |
+
"step": 590
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.66,
|
| 727 |
+
"learning_rate": 6.387583338128471e-06,
|
| 728 |
+
"loss": 0.993,
|
| 729 |
+
"step": 595
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.66,
|
| 733 |
+
"learning_rate": 6.208763228762082e-06,
|
| 734 |
+
"loss": 1.023,
|
| 735 |
+
"step": 600
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.67,
|
| 739 |
+
"learning_rate": 6.031347959618914e-06,
|
| 740 |
+
"loss": 0.9678,
|
| 741 |
+
"step": 605
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.67,
|
| 745 |
+
"learning_rate": 5.855403271807033e-06,
|
| 746 |
+
"loss": 0.9956,
|
| 747 |
+
"step": 610
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.68,
|
| 751 |
+
"learning_rate": 5.6809943615115915e-06,
|
| 752 |
+
"loss": 1.0131,
|
| 753 |
+
"step": 615
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.68,
|
| 757 |
+
"learning_rate": 5.508185855836426e-06,
|
| 758 |
+
"loss": 1.0111,
|
| 759 |
+
"step": 620
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.69,
|
| 763 |
+
"learning_rate": 5.337041788856518e-06,
|
| 764 |
+
"loss": 1.0068,
|
| 765 |
+
"step": 625
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.69,
|
| 769 |
+
"learning_rate": 5.1676255778902225e-06,
|
| 770 |
+
"loss": 1.0215,
|
| 771 |
+
"step": 630
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.7,
|
| 775 |
+
"learning_rate": 5.000000000000003e-06,
|
| 776 |
+
"loss": 1.0114,
|
| 777 |
+
"step": 635
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.71,
|
| 781 |
+
"learning_rate": 4.834227168730451e-06,
|
| 782 |
+
"loss": 1.0366,
|
| 783 |
+
"step": 640
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.71,
|
| 787 |
+
"learning_rate": 4.670368511092166e-06,
|
| 788 |
+
"loss": 1.0133,
|
| 789 |
+
"step": 645
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.72,
|
| 793 |
+
"learning_rate": 4.508484744799979e-06,
|
| 794 |
+
"loss": 1.0043,
|
| 795 |
+
"step": 650
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.72,
|
| 799 |
+
"learning_rate": 4.348635855774082e-06,
|
| 800 |
+
"loss": 0.9932,
|
| 801 |
+
"step": 655
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.73,
|
| 805 |
+
"learning_rate": 4.190881075912269e-06,
|
| 806 |
+
"loss": 0.996,
|
| 807 |
+
"step": 660
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.73,
|
| 811 |
+
"learning_rate": 4.035278861141588e-06,
|
| 812 |
+
"loss": 1.0058,
|
| 813 |
+
"step": 665
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.74,
|
| 817 |
+
"learning_rate": 3.881886869757565e-06,
|
| 818 |
+
"loss": 1.0133,
|
| 819 |
+
"step": 670
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.74,
|
| 823 |
+
"learning_rate": 3.730761941058938e-06,
|
| 824 |
+
"loss": 0.9999,
|
| 825 |
+
"step": 675
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.75,
|
| 829 |
+
"learning_rate": 3.581960074285885e-06,
|
| 830 |
+
"loss": 0.9914,
|
| 831 |
+
"step": 680
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.76,
|
| 835 |
+
"learning_rate": 3.435536407869575e-06,
|
| 836 |
+
"loss": 0.9907,
|
| 837 |
+
"step": 685
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.76,
|
| 841 |
+
"learning_rate": 3.2915451990006365e-06,
|
| 842 |
+
"loss": 1.003,
|
| 843 |
+
"step": 690
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.77,
|
| 847 |
+
"learning_rate": 3.150039803524194e-06,
|
| 848 |
+
"loss": 0.9881,
|
| 849 |
+
"step": 695
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.77,
|
| 853 |
+
"learning_rate": 3.011072656168906e-06,
|
| 854 |
+
"loss": 1.0037,
|
| 855 |
+
"step": 700
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.78,
|
| 859 |
+
"learning_rate": 2.874695251117303e-06,
|
| 860 |
+
"loss": 0.9977,
|
| 861 |
+
"step": 705
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.78,
|
| 865 |
+
"learning_rate": 2.7409581229246496e-06,
|
| 866 |
+
"loss": 0.99,
|
| 867 |
+
"step": 710
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.79,
|
| 871 |
+
"learning_rate": 2.6099108277934105e-06,
|
| 872 |
+
"loss": 1.0215,
|
| 873 |
+
"step": 715
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.79,
|
| 877 |
+
"learning_rate": 2.4816019252102274e-06,
|
| 878 |
+
"loss": 1.004,
|
| 879 |
+
"step": 720
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.8,
|
| 883 |
+
"learning_rate": 2.3560789599522325e-06,
|
| 884 |
+
"loss": 0.9984,
|
| 885 |
+
"step": 725
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.8,
|
| 889 |
+
"learning_rate": 2.2333884444693656e-06,
|
| 890 |
+
"loss": 0.9938,
|
| 891 |
+
"step": 730
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.81,
|
| 895 |
+
"learning_rate": 2.1135758416492168e-06,
|
| 896 |
+
"loss": 0.989,
|
| 897 |
+
"step": 735
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.82,
|
| 901 |
+
"learning_rate": 1.996685547970787e-06,
|
| 902 |
+
"loss": 0.9997,
|
| 903 |
+
"step": 740
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.82,
|
| 907 |
+
"learning_rate": 1.882760877053388e-06,
|
| 908 |
+
"loss": 0.9884,
|
| 909 |
+
"step": 745
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.83,
|
| 913 |
+
"learning_rate": 1.7718440436068385e-06,
|
| 914 |
+
"loss": 1.0203,
|
| 915 |
+
"step": 750
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.83,
|
| 919 |
+
"learning_rate": 1.663976147788806e-06,
|
| 920 |
+
"loss": 0.9981,
|
| 921 |
+
"step": 755
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.84,
|
| 925 |
+
"learning_rate": 1.55919715997518e-06,
|
| 926 |
+
"loss": 1.0208,
|
| 927 |
+
"step": 760
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.84,
|
| 931 |
+
"learning_rate": 1.4575459059490771e-06,
|
| 932 |
+
"loss": 1.0058,
|
| 933 |
+
"step": 765
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.85,
|
| 937 |
+
"learning_rate": 1.3590600525139764e-06,
|
| 938 |
+
"loss": 1.0002,
|
| 939 |
+
"step": 770
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.85,
|
| 943 |
+
"learning_rate": 1.2637760935363053e-06,
|
| 944 |
+
"loss": 1.0193,
|
| 945 |
+
"step": 775
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.86,
|
| 949 |
+
"learning_rate": 1.1717293364226612e-06,
|
| 950 |
+
"loss": 1.015,
|
| 951 |
+
"step": 780
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.87,
|
| 955 |
+
"learning_rate": 1.0829538890366864e-06,
|
| 956 |
+
"loss": 1.0105,
|
| 957 |
+
"step": 785
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.87,
|
| 961 |
+
"learning_rate": 9.97482647060405e-07,
|
| 962 |
+
"loss": 0.982,
|
| 963 |
+
"step": 790
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.88,
|
| 967 |
+
"learning_rate": 9.153472818047627e-07,
|
| 968 |
+
"loss": 1.0159,
|
| 969 |
+
"step": 795
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.88,
|
| 973 |
+
"learning_rate": 8.365782284738488e-07,
|
| 974 |
+
"loss": 0.9884,
|
| 975 |
+
"step": 800
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.89,
|
| 979 |
+
"learning_rate": 7.612046748871327e-07,
|
| 980 |
+
"loss": 1.0274,
|
| 981 |
+
"step": 805
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.89,
|
| 985 |
+
"learning_rate": 6.892545506639559e-07,
|
| 986 |
+
"loss": 1.0192,
|
| 987 |
+
"step": 810
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.9,
|
| 991 |
+
"learning_rate": 6.207545168742212e-07,
|
| 992 |
+
"loss": 1.0136,
|
| 993 |
+
"step": 815
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.9,
|
| 997 |
+
"learning_rate": 5.557299561591478e-07,
|
| 998 |
+
"loss": 0.9856,
|
| 999 |
+
"step": 820
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.91,
|
| 1003 |
+
"learning_rate": 4.942049633257673e-07,
|
| 1004 |
+
"loss": 1.0191,
|
| 1005 |
+
"step": 825
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.92,
|
| 1009 |
+
"learning_rate": 4.3620233641858855e-07,
|
| 1010 |
+
"loss": 1.0165,
|
| 1011 |
+
"step": 830
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.92,
|
| 1015 |
+
"learning_rate": 3.817435682718096e-07,
|
| 1016 |
+
"loss": 0.9956,
|
| 1017 |
+
"step": 835
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.93,
|
| 1021 |
+
"learning_rate": 3.3084883854516136e-07,
|
| 1022 |
+
"loss": 1.0112,
|
| 1023 |
+
"step": 840
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.93,
|
| 1027 |
+
"learning_rate": 2.835370062463449e-07,
|
| 1028 |
+
"loss": 0.9854,
|
| 1029 |
+
"step": 845
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.94,
|
| 1033 |
+
"learning_rate": 2.398256027428436e-07,
|
| 1034 |
+
"loss": 1.003,
|
| 1035 |
+
"step": 850
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.94,
|
| 1039 |
+
"learning_rate": 1.9973082526568155e-07,
|
| 1040 |
+
"loss": 1.0058,
|
| 1041 |
+
"step": 855
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.95,
|
| 1045 |
+
"learning_rate": 1.6326753090755487e-07,
|
| 1046 |
+
"loss": 1.0071,
|
| 1047 |
+
"step": 860
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.95,
|
| 1051 |
+
"learning_rate": 1.3044923111754427e-07,
|
| 1052 |
+
"loss": 0.9816,
|
| 1053 |
+
"step": 865
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.96,
|
| 1057 |
+
"learning_rate": 1.0128808669445323e-07,
|
| 1058 |
+
"loss": 0.9971,
|
| 1059 |
+
"step": 870
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.96,
|
| 1063 |
+
"learning_rate": 7.579490328064265e-08,
|
| 1064 |
+
"loss": 0.9976,
|
| 1065 |
+
"step": 875
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.97,
|
| 1069 |
+
"learning_rate": 5.397912735799371e-08,
|
| 1070 |
+
"loss": 0.991,
|
| 1071 |
+
"step": 880
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.98,
|
| 1075 |
+
"learning_rate": 3.5848842747532306e-08,
|
| 1076 |
+
"loss": 0.9916,
|
| 1077 |
+
"step": 885
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.98,
|
| 1081 |
+
"learning_rate": 2.1410767613965212e-08,
|
| 1082 |
+
"loss": 1.0156,
|
| 1083 |
+
"step": 890
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.99,
|
| 1087 |
+
"learning_rate": 1.0670251976275803e-08,
|
| 1088 |
+
"loss": 1.0103,
|
| 1089 |
+
"step": 895
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.99,
|
| 1093 |
+
"learning_rate": 3.63127572527433e-09,
|
| 1094 |
+
"loss": 0.9953,
|
| 1095 |
+
"step": 900
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.0,
|
| 1099 |
+
"learning_rate": 2.964471488531295e-10,
|
| 1100 |
+
"loss": 1.0177,
|
| 1101 |
+
"step": 905
|
| 1102 |
+
},
|
| 1103 |
{
|
| 1104 |
"epoch": 1.0,
|
| 1105 |
+
"eval_loss": 1.0114790201187134,
|
| 1106 |
+
"eval_runtime": 504.0881,
|
| 1107 |
+
"eval_samples_per_second": 12.776,
|
| 1108 |
+
"eval_steps_per_second": 0.799,
|
| 1109 |
+
"step": 907
|
| 1110 |
},
|
| 1111 |
{
|
| 1112 |
"epoch": 1.0,
|
| 1113 |
+
"step": 907,
|
| 1114 |
+
"total_flos": 5.321288023160127e+18,
|
| 1115 |
+
"train_loss": 1.0047753110873003,
|
| 1116 |
+
"train_runtime": 15080.3332,
|
| 1117 |
+
"train_samples_per_second": 3.848,
|
| 1118 |
+
"train_steps_per_second": 0.06
|
| 1119 |
}
|
| 1120 |
],
|
| 1121 |
"logging_steps": 5,
|
| 1122 |
+
"max_steps": 907,
|
| 1123 |
"num_input_tokens_seen": 0,
|
| 1124 |
"num_train_epochs": 1,
|
| 1125 |
"save_steps": 100,
|
| 1126 |
+
"total_flos": 5.321288023160127e+18,
|
| 1127 |
"train_batch_size": 32,
|
| 1128 |
"trial_name": null,
|
| 1129 |
"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 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cfc4b16b16212f6de8d24861fac8e34adaef10a3b9f92ede6401c4e76eea3ff
|
| 3 |
size 4856
|