Training in progress, epoch 20, checkpoint
Browse files- checkpoint-3750/README.md +9 -0
- checkpoint-3750/adapter_config.json +25 -0
- checkpoint-3750/adapter_model.safetensors +3 -0
- checkpoint-3750/added_tokens.json +5 -0
- checkpoint-3750/merges.txt +0 -0
- checkpoint-3750/optimizer.pt +3 -0
- checkpoint-3750/rng_state_0.pth +3 -0
- checkpoint-3750/rng_state_1.pth +3 -0
- checkpoint-3750/rng_state_2.pth +3 -0
- checkpoint-3750/rng_state_3.pth +3 -0
- checkpoint-3750/scheduler.pt +3 -0
- checkpoint-3750/special_tokens_map.json +14 -0
- checkpoint-3750/tokenizer.json +0 -0
- checkpoint-3750/tokenizer_config.json +43 -0
- checkpoint-3750/trainer_state.json +472 -0
- checkpoint-3750/training_args.bin +3 -0
- checkpoint-3750/vocab.json +0 -0
checkpoint-3750/README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
checkpoint-3750/adapter_config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "Qwen/Qwen1.5-4B",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 16,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"k_proj",
|
| 19 |
+
"v_proj",
|
| 20 |
+
"down_proj",
|
| 21 |
+
"gate_proj",
|
| 22 |
+
"up_proj"
|
| 23 |
+
],
|
| 24 |
+
"task_type": "CAUSAL_LM"
|
| 25 |
+
}
|
checkpoint-3750/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:456c2123809195c78762725c20a43e10e9574cf37a17e192d465d87033359f33
|
| 3 |
+
size 112130416
|
checkpoint-3750/added_tokens.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_end|>": 151645,
|
| 4 |
+
"<|im_start|>": 151644
|
| 5 |
+
}
|
checkpoint-3750/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3750/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6b6431538b390b96dcb073ad6d95ec54fcfdd900b4b96ef94db3f007f7e4c13
|
| 3 |
+
size 224537202
|
checkpoint-3750/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb08628d64f1b1055cf34ce9d64f3438813396663580a4fdf0e0b7fa563dbc72
|
| 3 |
+
size 15024
|
checkpoint-3750/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97035ffae66df324b5664fb72f7a11a928ae4bbcea9da1e5e1ea6f7abbc4831c
|
| 3 |
+
size 15024
|
checkpoint-3750/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ee82caacef728b09f46da0bf4ae0c481917e4b69d7188db8d83355880800ae5
|
| 3 |
+
size 15024
|
checkpoint-3750/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5eab3b2e22621bdcbef4e83451cef1b4640c9ed3a60051e2111a8cd940bef84
|
| 3 |
+
size 15024
|
checkpoint-3750/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49836dcf95ab2d64e1e042fec1d1ea63cc95a913213d48809d4135530e98dc83
|
| 3 |
+
size 1064
|
checkpoint-3750/special_tokens_map.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>"
|
| 5 |
+
],
|
| 6 |
+
"eos_token": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
},
|
| 13 |
+
"pad_token": "<|endoftext|>"
|
| 14 |
+
}
|
checkpoint-3750/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3750/tokenizer_config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
}
|
| 28 |
+
},
|
| 29 |
+
"additional_special_tokens": [
|
| 30 |
+
"<|im_start|>",
|
| 31 |
+
"<|im_end|>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": null,
|
| 34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
+
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|endoftext|>",
|
| 37 |
+
"errors": "replace",
|
| 38 |
+
"model_max_length": 32768,
|
| 39 |
+
"pad_token": "<|endoftext|>",
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 42 |
+
"unk_token": null
|
| 43 |
+
}
|
checkpoint-3750/trainer_state.json
ADDED
|
@@ -0,0 +1,472 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3750,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5333333333333333,
|
| 13 |
+
"grad_norm": 0.2409825623035431,
|
| 14 |
+
"learning_rate": 0.0001,
|
| 15 |
+
"loss": 1.7886,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.9973333333333333,
|
| 20 |
+
"eval_accuracy": 0.6061076233183856,
|
| 21 |
+
"eval_loss": 1.6901254653930664,
|
| 22 |
+
"eval_runtime": 5.5484,
|
| 23 |
+
"eval_samples_per_second": 90.116,
|
| 24 |
+
"eval_steps_per_second": 11.355,
|
| 25 |
+
"step": 187
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.0666666666666667,
|
| 29 |
+
"grad_norm": 0.2729445993900299,
|
| 30 |
+
"learning_rate": 0.0001,
|
| 31 |
+
"loss": 1.7283,
|
| 32 |
+
"step": 200
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.6,
|
| 36 |
+
"grad_norm": 0.37678101658821106,
|
| 37 |
+
"learning_rate": 0.0001,
|
| 38 |
+
"loss": 1.6544,
|
| 39 |
+
"step": 300
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"eval_accuracy": 0.607677130044843,
|
| 44 |
+
"eval_loss": 1.6766204833984375,
|
| 45 |
+
"eval_runtime": 6.4294,
|
| 46 |
+
"eval_samples_per_second": 77.768,
|
| 47 |
+
"eval_steps_per_second": 9.799,
|
| 48 |
+
"step": 375
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.1333333333333333,
|
| 52 |
+
"grad_norm": 0.4604090750217438,
|
| 53 |
+
"learning_rate": 0.0001,
|
| 54 |
+
"loss": 1.6338,
|
| 55 |
+
"step": 400
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 2.6666666666666665,
|
| 59 |
+
"grad_norm": 0.5606330633163452,
|
| 60 |
+
"learning_rate": 0.0001,
|
| 61 |
+
"loss": 1.5273,
|
| 62 |
+
"step": 500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.997333333333333,
|
| 66 |
+
"eval_accuracy": 0.6079910313901346,
|
| 67 |
+
"eval_loss": 1.6929064989089966,
|
| 68 |
+
"eval_runtime": 5.431,
|
| 69 |
+
"eval_samples_per_second": 92.063,
|
| 70 |
+
"eval_steps_per_second": 11.6,
|
| 71 |
+
"step": 562
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.2,
|
| 75 |
+
"grad_norm": 0.6363856196403503,
|
| 76 |
+
"learning_rate": 0.0001,
|
| 77 |
+
"loss": 1.4796,
|
| 78 |
+
"step": 600
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 3.7333333333333334,
|
| 82 |
+
"grad_norm": 0.5985731482505798,
|
| 83 |
+
"learning_rate": 0.0001,
|
| 84 |
+
"loss": 1.3871,
|
| 85 |
+
"step": 700
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 4.0,
|
| 89 |
+
"eval_accuracy": 0.606896860986547,
|
| 90 |
+
"eval_loss": 1.7257370948791504,
|
| 91 |
+
"eval_runtime": 5.8318,
|
| 92 |
+
"eval_samples_per_second": 85.737,
|
| 93 |
+
"eval_steps_per_second": 10.803,
|
| 94 |
+
"step": 750
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 4.266666666666667,
|
| 98 |
+
"grad_norm": 0.7769015431404114,
|
| 99 |
+
"learning_rate": 0.0001,
|
| 100 |
+
"loss": 1.3013,
|
| 101 |
+
"step": 800
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 4.8,
|
| 105 |
+
"grad_norm": 0.708043098449707,
|
| 106 |
+
"learning_rate": 0.0001,
|
| 107 |
+
"loss": 1.23,
|
| 108 |
+
"step": 900
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 4.997333333333334,
|
| 112 |
+
"eval_accuracy": 0.6061076233183856,
|
| 113 |
+
"eval_loss": 1.7812739610671997,
|
| 114 |
+
"eval_runtime": 5.9335,
|
| 115 |
+
"eval_samples_per_second": 84.267,
|
| 116 |
+
"eval_steps_per_second": 10.618,
|
| 117 |
+
"step": 937
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 5.333333333333333,
|
| 121 |
+
"grad_norm": 0.8580867648124695,
|
| 122 |
+
"learning_rate": 0.0001,
|
| 123 |
+
"loss": 1.1011,
|
| 124 |
+
"step": 1000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 5.866666666666667,
|
| 128 |
+
"grad_norm": 0.9232878684997559,
|
| 129 |
+
"learning_rate": 0.0001,
|
| 130 |
+
"loss": 1.0749,
|
| 131 |
+
"step": 1100
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 6.0,
|
| 135 |
+
"eval_accuracy": 0.6018026905829597,
|
| 136 |
+
"eval_loss": 1.877648949623108,
|
| 137 |
+
"eval_runtime": 6.474,
|
| 138 |
+
"eval_samples_per_second": 77.231,
|
| 139 |
+
"eval_steps_per_second": 9.731,
|
| 140 |
+
"step": 1125
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.4,
|
| 144 |
+
"grad_norm": 1.0364516973495483,
|
| 145 |
+
"learning_rate": 0.0001,
|
| 146 |
+
"loss": 0.9164,
|
| 147 |
+
"step": 1200
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 6.933333333333334,
|
| 151 |
+
"grad_norm": 1.0082701444625854,
|
| 152 |
+
"learning_rate": 0.0001,
|
| 153 |
+
"loss": 0.8957,
|
| 154 |
+
"step": 1300
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 6.997333333333334,
|
| 158 |
+
"eval_accuracy": 0.5997937219730942,
|
| 159 |
+
"eval_loss": 1.978247046470642,
|
| 160 |
+
"eval_runtime": 5.9491,
|
| 161 |
+
"eval_samples_per_second": 84.047,
|
| 162 |
+
"eval_steps_per_second": 10.59,
|
| 163 |
+
"step": 1312
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 7.466666666666667,
|
| 167 |
+
"grad_norm": 1.0375924110412598,
|
| 168 |
+
"learning_rate": 0.0001,
|
| 169 |
+
"loss": 0.7382,
|
| 170 |
+
"step": 1400
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 8.0,
|
| 174 |
+
"grad_norm": 1.115308403968811,
|
| 175 |
+
"learning_rate": 0.0001,
|
| 176 |
+
"loss": 0.729,
|
| 177 |
+
"step": 1500
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 8.0,
|
| 181 |
+
"eval_accuracy": 0.5965919282511211,
|
| 182 |
+
"eval_loss": 2.097362756729126,
|
| 183 |
+
"eval_runtime": 6.5905,
|
| 184 |
+
"eval_samples_per_second": 75.867,
|
| 185 |
+
"eval_steps_per_second": 9.559,
|
| 186 |
+
"step": 1500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 8.533333333333333,
|
| 190 |
+
"grad_norm": 1.3251475095748901,
|
| 191 |
+
"learning_rate": 0.0001,
|
| 192 |
+
"loss": 0.5643,
|
| 193 |
+
"step": 1600
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 8.997333333333334,
|
| 197 |
+
"eval_accuracy": 0.5931300448430493,
|
| 198 |
+
"eval_loss": 2.2553179264068604,
|
| 199 |
+
"eval_runtime": 6.1864,
|
| 200 |
+
"eval_samples_per_second": 80.823,
|
| 201 |
+
"eval_steps_per_second": 10.184,
|
| 202 |
+
"step": 1687
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 9.066666666666666,
|
| 206 |
+
"grad_norm": 1.0753710269927979,
|
| 207 |
+
"learning_rate": 0.0001,
|
| 208 |
+
"loss": 0.5706,
|
| 209 |
+
"step": 1700
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 9.6,
|
| 213 |
+
"grad_norm": 1.5658849477767944,
|
| 214 |
+
"learning_rate": 0.0001,
|
| 215 |
+
"loss": 0.4538,
|
| 216 |
+
"step": 1800
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 10.0,
|
| 220 |
+
"eval_accuracy": 0.5900627802690583,
|
| 221 |
+
"eval_loss": 2.408897876739502,
|
| 222 |
+
"eval_runtime": 6.4582,
|
| 223 |
+
"eval_samples_per_second": 77.422,
|
| 224 |
+
"eval_steps_per_second": 9.755,
|
| 225 |
+
"step": 1875
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 10.133333333333333,
|
| 229 |
+
"grad_norm": 1.6254231929779053,
|
| 230 |
+
"learning_rate": 0.0001,
|
| 231 |
+
"loss": 0.4286,
|
| 232 |
+
"step": 1900
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 10.666666666666666,
|
| 236 |
+
"grad_norm": 1.187232255935669,
|
| 237 |
+
"learning_rate": 0.0001,
|
| 238 |
+
"loss": 0.3563,
|
| 239 |
+
"step": 2000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 10.997333333333334,
|
| 243 |
+
"eval_accuracy": 0.588914798206278,
|
| 244 |
+
"eval_loss": 2.529802083969116,
|
| 245 |
+
"eval_runtime": 5.9806,
|
| 246 |
+
"eval_samples_per_second": 83.604,
|
| 247 |
+
"eval_steps_per_second": 10.534,
|
| 248 |
+
"step": 2062
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 11.2,
|
| 252 |
+
"grad_norm": 1.3838512897491455,
|
| 253 |
+
"learning_rate": 0.0001,
|
| 254 |
+
"loss": 0.3256,
|
| 255 |
+
"step": 2100
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 11.733333333333333,
|
| 259 |
+
"grad_norm": 1.249315619468689,
|
| 260 |
+
"learning_rate": 0.0001,
|
| 261 |
+
"loss": 0.2787,
|
| 262 |
+
"step": 2200
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 12.0,
|
| 266 |
+
"eval_accuracy": 0.5870582959641255,
|
| 267 |
+
"eval_loss": 2.684791088104248,
|
| 268 |
+
"eval_runtime": 5.7871,
|
| 269 |
+
"eval_samples_per_second": 86.399,
|
| 270 |
+
"eval_steps_per_second": 10.886,
|
| 271 |
+
"step": 2250
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 12.266666666666667,
|
| 275 |
+
"grad_norm": 1.163707971572876,
|
| 276 |
+
"learning_rate": 0.0001,
|
| 277 |
+
"loss": 0.2558,
|
| 278 |
+
"step": 2300
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 12.8,
|
| 282 |
+
"grad_norm": 1.092466950416565,
|
| 283 |
+
"learning_rate": 0.0001,
|
| 284 |
+
"loss": 0.2314,
|
| 285 |
+
"step": 2400
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 12.997333333333334,
|
| 289 |
+
"eval_accuracy": 0.5863408071748879,
|
| 290 |
+
"eval_loss": 2.7943203449249268,
|
| 291 |
+
"eval_runtime": 6.5027,
|
| 292 |
+
"eval_samples_per_second": 76.891,
|
| 293 |
+
"eval_steps_per_second": 9.688,
|
| 294 |
+
"step": 2437
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 13.333333333333334,
|
| 298 |
+
"grad_norm": 1.1065410375595093,
|
| 299 |
+
"learning_rate": 0.0001,
|
| 300 |
+
"loss": 0.2029,
|
| 301 |
+
"step": 2500
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 13.866666666666667,
|
| 305 |
+
"grad_norm": 1.1960605382919312,
|
| 306 |
+
"learning_rate": 0.0001,
|
| 307 |
+
"loss": 0.1923,
|
| 308 |
+
"step": 2600
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 14.0,
|
| 312 |
+
"eval_accuracy": 0.5856502242152466,
|
| 313 |
+
"eval_loss": 2.8624069690704346,
|
| 314 |
+
"eval_runtime": 5.5405,
|
| 315 |
+
"eval_samples_per_second": 90.244,
|
| 316 |
+
"eval_steps_per_second": 11.371,
|
| 317 |
+
"step": 2625
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 14.4,
|
| 321 |
+
"grad_norm": 1.014957070350647,
|
| 322 |
+
"learning_rate": 0.0001,
|
| 323 |
+
"loss": 0.1661,
|
| 324 |
+
"step": 2700
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 14.933333333333334,
|
| 328 |
+
"grad_norm": 1.2782268524169922,
|
| 329 |
+
"learning_rate": 0.0001,
|
| 330 |
+
"loss": 0.1687,
|
| 331 |
+
"step": 2800
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 14.997333333333334,
|
| 335 |
+
"eval_accuracy": 0.5847533632286995,
|
| 336 |
+
"eval_loss": 2.978261947631836,
|
| 337 |
+
"eval_runtime": 6.5241,
|
| 338 |
+
"eval_samples_per_second": 76.639,
|
| 339 |
+
"eval_steps_per_second": 9.656,
|
| 340 |
+
"step": 2812
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 15.466666666666667,
|
| 344 |
+
"grad_norm": 1.0024491548538208,
|
| 345 |
+
"learning_rate": 0.0001,
|
| 346 |
+
"loss": 0.1464,
|
| 347 |
+
"step": 2900
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 16.0,
|
| 351 |
+
"grad_norm": 0.9853018522262573,
|
| 352 |
+
"learning_rate": 0.0001,
|
| 353 |
+
"loss": 0.1514,
|
| 354 |
+
"step": 3000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 16.0,
|
| 358 |
+
"eval_accuracy": 0.5849865470852018,
|
| 359 |
+
"eval_loss": 3.0238428115844727,
|
| 360 |
+
"eval_runtime": 5.8457,
|
| 361 |
+
"eval_samples_per_second": 85.533,
|
| 362 |
+
"eval_steps_per_second": 10.777,
|
| 363 |
+
"step": 3000
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 16.533333333333335,
|
| 367 |
+
"grad_norm": 1.2373902797698975,
|
| 368 |
+
"learning_rate": 0.0001,
|
| 369 |
+
"loss": 0.1282,
|
| 370 |
+
"step": 3100
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 16.997333333333334,
|
| 374 |
+
"eval_accuracy": 0.5841614349775784,
|
| 375 |
+
"eval_loss": 3.091371774673462,
|
| 376 |
+
"eval_runtime": 5.5018,
|
| 377 |
+
"eval_samples_per_second": 90.879,
|
| 378 |
+
"eval_steps_per_second": 11.451,
|
| 379 |
+
"step": 3187
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 17.066666666666666,
|
| 383 |
+
"grad_norm": 0.9496106505393982,
|
| 384 |
+
"learning_rate": 0.0001,
|
| 385 |
+
"loss": 0.1358,
|
| 386 |
+
"step": 3200
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 17.6,
|
| 390 |
+
"grad_norm": 1.0109747648239136,
|
| 391 |
+
"learning_rate": 0.0001,
|
| 392 |
+
"loss": 0.121,
|
| 393 |
+
"step": 3300
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 18.0,
|
| 397 |
+
"eval_accuracy": 0.5847982062780269,
|
| 398 |
+
"eval_loss": 3.143228530883789,
|
| 399 |
+
"eval_runtime": 5.4395,
|
| 400 |
+
"eval_samples_per_second": 91.919,
|
| 401 |
+
"eval_steps_per_second": 11.582,
|
| 402 |
+
"step": 3375
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 18.133333333333333,
|
| 406 |
+
"grad_norm": 0.9266707301139832,
|
| 407 |
+
"learning_rate": 0.0001,
|
| 408 |
+
"loss": 0.1262,
|
| 409 |
+
"step": 3400
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 18.666666666666668,
|
| 413 |
+
"grad_norm": 1.026375651359558,
|
| 414 |
+
"learning_rate": 0.0001,
|
| 415 |
+
"loss": 0.1164,
|
| 416 |
+
"step": 3500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 18.997333333333334,
|
| 420 |
+
"eval_accuracy": 0.5847533632286995,
|
| 421 |
+
"eval_loss": 3.231442451477051,
|
| 422 |
+
"eval_runtime": 6.4528,
|
| 423 |
+
"eval_samples_per_second": 77.486,
|
| 424 |
+
"eval_steps_per_second": 9.763,
|
| 425 |
+
"step": 3562
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 19.2,
|
| 429 |
+
"grad_norm": 0.9512910842895508,
|
| 430 |
+
"learning_rate": 0.0001,
|
| 431 |
+
"loss": 0.1153,
|
| 432 |
+
"step": 3600
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 19.733333333333334,
|
| 436 |
+
"grad_norm": 1.1021068096160889,
|
| 437 |
+
"learning_rate": 0.0001,
|
| 438 |
+
"loss": 0.1103,
|
| 439 |
+
"step": 3700
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 20.0,
|
| 443 |
+
"eval_accuracy": 0.5843946188340807,
|
| 444 |
+
"eval_loss": 3.278094530105591,
|
| 445 |
+
"eval_runtime": 6.151,
|
| 446 |
+
"eval_samples_per_second": 81.288,
|
| 447 |
+
"eval_steps_per_second": 10.242,
|
| 448 |
+
"step": 3750
|
| 449 |
+
}
|
| 450 |
+
],
|
| 451 |
+
"logging_steps": 100,
|
| 452 |
+
"max_steps": 9350,
|
| 453 |
+
"num_input_tokens_seen": 0,
|
| 454 |
+
"num_train_epochs": 50,
|
| 455 |
+
"save_steps": 500,
|
| 456 |
+
"stateful_callbacks": {
|
| 457 |
+
"TrainerControl": {
|
| 458 |
+
"args": {
|
| 459 |
+
"should_epoch_stop": false,
|
| 460 |
+
"should_evaluate": false,
|
| 461 |
+
"should_log": false,
|
| 462 |
+
"should_save": true,
|
| 463 |
+
"should_training_stop": false
|
| 464 |
+
},
|
| 465 |
+
"attributes": {}
|
| 466 |
+
}
|
| 467 |
+
},
|
| 468 |
+
"total_flos": 3.777309101470515e+17,
|
| 469 |
+
"train_batch_size": 1,
|
| 470 |
+
"trial_name": null,
|
| 471 |
+
"trial_params": null
|
| 472 |
+
}
|
checkpoint-3750/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a48e2910c0614efc83f1cdab0e18284ec3fdf02b7a0946bdd13c56e7e15f701
|
| 3 |
+
size 5304
|
checkpoint-3750/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|