Upload 30 files
Browse files- adapter_config.json +19 -0
- adapter_model.bin +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +12 -0
- checkpoint-1000/tokenizer.model +3 -0
- checkpoint-1000/tokenizer_config.json +33 -0
- checkpoint-1000/trainer_state.json +632 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-500/optimizer.pt +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/rng_state.pth +3 -0
- checkpoint-500/scaler.pt +3 -0
- checkpoint-500/scheduler.pt +3 -0
- checkpoint-500/special_tokens_map.json +12 -0
- checkpoint-500/tokenizer.model +3 -0
- checkpoint-500/tokenizer_config.json +33 -0
- checkpoint-500/trainer_state.json +324 -0
- checkpoint-500/training_args.bin +3 -0
- finetune_args.json +27 -0
- info.json +9 -0
- runs/Jun27_17-42-45_04e3f719f875/1687887765.9930556/events.out.tfevents.1687887765.04e3f719f875.4175.1 +3 -0
- runs/Jun27_17-42-45_04e3f719f875/events.out.tfevents.1687887765.04e3f719f875.4175.0 +3 -0
- train_data_samples.json +0 -0
- train_output.json +12 -0
- trainer_args.json +115 -0
- trainer_log_history.jsonl +107 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"lora_alpha": 16,
|
| 9 |
+
"lora_dropout": 0.05,
|
| 10 |
+
"merge_weights": false,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"target_modules": [
|
| 15 |
+
"q_proj",
|
| 16 |
+
"v_proj"
|
| 17 |
+
],
|
| 18 |
+
"task_type": "CAUSAL_LM"
|
| 19 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64ff77e111d1f45fdc703693a5f15b246d40843847a42012084a0a93cfb8313b
|
| 3 |
+
size 16822989
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78e180c5106dc4637c6e06bd3f6962dd7985c947741124c93fb60e3117950214
|
| 3 |
+
size 33661637
|
checkpoint-1000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95f39502a58c7bb52c66dbd78964733626525e111f25b19157447678e4fd8489
|
| 3 |
+
size 16822989
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4d3a419e3565914fb7d23e3a197bab0d29ab2c376b64718bd8d2652b6add445
|
| 3 |
+
size 14575
|
checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:636a1ea3193a7963286c6a67f3befe6fd39638b0c707fe4288acba215be4adc9
|
| 3 |
+
size 557
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d631f2519aa4a7efbc127756b3d2412768d0d7f5c21107b521243789e389c0b2
|
| 3 |
+
size 627
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<unk>",
|
| 5 |
+
"unk_token": {
|
| 6 |
+
"content": "",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
}
|
| 12 |
+
}
|
checkpoint-1000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
+
"pad_token": null,
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,632 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.50592440366745,
|
| 3 |
+
"best_model_checkpoint": "/content/My Drive/LLaMA-LoRA Tuner/lora_models/earthshine-nondecorative-2023-06-27-17-40-07/checkpoint-1000",
|
| 4 |
+
"epoch": 2.808988764044944,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 2.3999999999999997e-05,
|
| 13 |
+
"loss": 2.0693,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 5.399999999999999e-05,
|
| 19 |
+
"loss": 1.9946,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 8.1e-05,
|
| 25 |
+
"loss": 1.8837,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 0.00011099999999999999,
|
| 31 |
+
"loss": 1.6655,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.14,
|
| 36 |
+
"learning_rate": 0.00014099999999999998,
|
| 37 |
+
"loss": 1.6095,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.17,
|
| 42 |
+
"learning_rate": 0.00017099999999999998,
|
| 43 |
+
"loss": 1.3838,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2,
|
| 48 |
+
"learning_rate": 0.000201,
|
| 49 |
+
"loss": 1.3548,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.22,
|
| 54 |
+
"learning_rate": 0.00023099999999999998,
|
| 55 |
+
"loss": 1.0789,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.25,
|
| 60 |
+
"learning_rate": 0.000261,
|
| 61 |
+
"loss": 1.0589,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.28,
|
| 66 |
+
"learning_rate": 0.00029099999999999997,
|
| 67 |
+
"loss": 1.0259,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.31,
|
| 72 |
+
"learning_rate": 0.000299393063583815,
|
| 73 |
+
"loss": 0.9936,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.34,
|
| 78 |
+
"learning_rate": 0.0002985260115606936,
|
| 79 |
+
"loss": 0.9633,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.37,
|
| 84 |
+
"learning_rate": 0.00029765895953757224,
|
| 85 |
+
"loss": 1.0018,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.39,
|
| 90 |
+
"learning_rate": 0.0002967919075144509,
|
| 91 |
+
"loss": 0.893,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.42,
|
| 96 |
+
"learning_rate": 0.00029592485549132945,
|
| 97 |
+
"loss": 0.8079,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.45,
|
| 102 |
+
"learning_rate": 0.0002950578034682081,
|
| 103 |
+
"loss": 0.8668,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.48,
|
| 108 |
+
"learning_rate": 0.00029419075144508666,
|
| 109 |
+
"loss": 0.773,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.51,
|
| 114 |
+
"learning_rate": 0.0002933236994219653,
|
| 115 |
+
"loss": 0.8139,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.53,
|
| 120 |
+
"learning_rate": 0.0002924566473988439,
|
| 121 |
+
"loss": 0.9139,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.56,
|
| 126 |
+
"learning_rate": 0.0002915895953757225,
|
| 127 |
+
"loss": 0.7371,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.59,
|
| 132 |
+
"learning_rate": 0.0002907225433526011,
|
| 133 |
+
"loss": 0.8604,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.62,
|
| 138 |
+
"learning_rate": 0.0002898554913294797,
|
| 139 |
+
"loss": 0.8597,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.65,
|
| 144 |
+
"learning_rate": 0.0002889884393063584,
|
| 145 |
+
"loss": 0.7954,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.67,
|
| 150 |
+
"learning_rate": 0.00028812138728323696,
|
| 151 |
+
"loss": 0.7559,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.7,
|
| 156 |
+
"learning_rate": 0.0002872543352601156,
|
| 157 |
+
"loss": 0.8488,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.73,
|
| 162 |
+
"learning_rate": 0.00028638728323699417,
|
| 163 |
+
"loss": 0.7252,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.76,
|
| 168 |
+
"learning_rate": 0.0002855202312138728,
|
| 169 |
+
"loss": 0.6751,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.79,
|
| 174 |
+
"learning_rate": 0.00028465317919075143,
|
| 175 |
+
"loss": 0.7852,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.81,
|
| 180 |
+
"learning_rate": 0.00028378612716763,
|
| 181 |
+
"loss": 0.7843,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.84,
|
| 186 |
+
"learning_rate": 0.00028291907514450864,
|
| 187 |
+
"loss": 0.7886,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.87,
|
| 192 |
+
"learning_rate": 0.00028205202312138727,
|
| 193 |
+
"loss": 0.7218,
|
| 194 |
+
"step": 310
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.9,
|
| 198 |
+
"learning_rate": 0.0002811849710982659,
|
| 199 |
+
"loss": 0.7919,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.93,
|
| 204 |
+
"learning_rate": 0.0002803179190751445,
|
| 205 |
+
"loss": 0.7248,
|
| 206 |
+
"step": 330
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.96,
|
| 210 |
+
"learning_rate": 0.0002794508670520231,
|
| 211 |
+
"loss": 0.7699,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.98,
|
| 216 |
+
"learning_rate": 0.00027858381502890174,
|
| 217 |
+
"loss": 0.6909,
|
| 218 |
+
"step": 350
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.01,
|
| 222 |
+
"learning_rate": 0.0002777167630057803,
|
| 223 |
+
"loss": 0.6992,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.04,
|
| 228 |
+
"learning_rate": 0.00027684971098265894,
|
| 229 |
+
"loss": 0.6747,
|
| 230 |
+
"step": 370
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.07,
|
| 234 |
+
"learning_rate": 0.0002759826589595375,
|
| 235 |
+
"loss": 0.672,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.1,
|
| 240 |
+
"learning_rate": 0.0002751156069364162,
|
| 241 |
+
"loss": 0.5997,
|
| 242 |
+
"step": 390
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.12,
|
| 246 |
+
"learning_rate": 0.0002742485549132948,
|
| 247 |
+
"loss": 0.747,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.15,
|
| 252 |
+
"learning_rate": 0.0002733815028901734,
|
| 253 |
+
"loss": 0.7217,
|
| 254 |
+
"step": 410
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.18,
|
| 258 |
+
"learning_rate": 0.000272514450867052,
|
| 259 |
+
"loss": 0.683,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.21,
|
| 264 |
+
"learning_rate": 0.0002716473988439306,
|
| 265 |
+
"loss": 0.63,
|
| 266 |
+
"step": 430
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.24,
|
| 270 |
+
"learning_rate": 0.00027078034682080925,
|
| 271 |
+
"loss": 0.6889,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.26,
|
| 276 |
+
"learning_rate": 0.0002699132947976878,
|
| 277 |
+
"loss": 0.6582,
|
| 278 |
+
"step": 450
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.29,
|
| 282 |
+
"learning_rate": 0.00026904624277456645,
|
| 283 |
+
"loss": 0.6366,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.32,
|
| 288 |
+
"learning_rate": 0.00026817919075144503,
|
| 289 |
+
"loss": 0.7249,
|
| 290 |
+
"step": 470
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.35,
|
| 294 |
+
"learning_rate": 0.0002673121387283237,
|
| 295 |
+
"loss": 0.53,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.38,
|
| 300 |
+
"learning_rate": 0.0002664450867052023,
|
| 301 |
+
"loss": 0.6172,
|
| 302 |
+
"step": 490
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.4,
|
| 306 |
+
"learning_rate": 0.0002655780346820809,
|
| 307 |
+
"loss": 0.6033,
|
| 308 |
+
"step": 500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.4,
|
| 312 |
+
"eval_loss": 0.5882205367088318,
|
| 313 |
+
"eval_runtime": 14.2208,
|
| 314 |
+
"eval_samples_per_second": 3.516,
|
| 315 |
+
"eval_steps_per_second": 0.492,
|
| 316 |
+
"step": 500
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.43,
|
| 320 |
+
"learning_rate": 0.0002647109826589595,
|
| 321 |
+
"loss": 0.7452,
|
| 322 |
+
"step": 510
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.46,
|
| 326 |
+
"learning_rate": 0.00026384393063583813,
|
| 327 |
+
"loss": 0.6689,
|
| 328 |
+
"step": 520
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.49,
|
| 332 |
+
"learning_rate": 0.00026297687861271676,
|
| 333 |
+
"loss": 0.6339,
|
| 334 |
+
"step": 530
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.52,
|
| 338 |
+
"learning_rate": 0.00026210982658959533,
|
| 339 |
+
"loss": 0.6538,
|
| 340 |
+
"step": 540
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.54,
|
| 344 |
+
"learning_rate": 0.00026124277456647397,
|
| 345 |
+
"loss": 0.6864,
|
| 346 |
+
"step": 550
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.57,
|
| 350 |
+
"learning_rate": 0.0002603757225433526,
|
| 351 |
+
"loss": 0.6466,
|
| 352 |
+
"step": 560
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.6,
|
| 356 |
+
"learning_rate": 0.00025950867052023117,
|
| 357 |
+
"loss": 0.6186,
|
| 358 |
+
"step": 570
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.63,
|
| 362 |
+
"learning_rate": 0.0002586416184971098,
|
| 363 |
+
"loss": 0.6872,
|
| 364 |
+
"step": 580
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.66,
|
| 368 |
+
"learning_rate": 0.00025777456647398843,
|
| 369 |
+
"loss": 0.7206,
|
| 370 |
+
"step": 590
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.69,
|
| 374 |
+
"learning_rate": 0.000256907514450867,
|
| 375 |
+
"loss": 0.5848,
|
| 376 |
+
"step": 600
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.71,
|
| 380 |
+
"learning_rate": 0.00025604046242774564,
|
| 381 |
+
"loss": 0.711,
|
| 382 |
+
"step": 610
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.74,
|
| 386 |
+
"learning_rate": 0.00025517341040462427,
|
| 387 |
+
"loss": 0.628,
|
| 388 |
+
"step": 620
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.77,
|
| 392 |
+
"learning_rate": 0.00025430635838150285,
|
| 393 |
+
"loss": 0.7035,
|
| 394 |
+
"step": 630
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.8,
|
| 398 |
+
"learning_rate": 0.0002534393063583815,
|
| 399 |
+
"loss": 0.5965,
|
| 400 |
+
"step": 640
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.83,
|
| 404 |
+
"learning_rate": 0.0002525722543352601,
|
| 405 |
+
"loss": 0.6486,
|
| 406 |
+
"step": 650
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.85,
|
| 410 |
+
"learning_rate": 0.0002517052023121387,
|
| 411 |
+
"loss": 0.6264,
|
| 412 |
+
"step": 660
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.88,
|
| 416 |
+
"learning_rate": 0.0002508381502890173,
|
| 417 |
+
"loss": 0.6469,
|
| 418 |
+
"step": 670
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.91,
|
| 422 |
+
"learning_rate": 0.00024997109826589595,
|
| 423 |
+
"loss": 0.61,
|
| 424 |
+
"step": 680
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.94,
|
| 428 |
+
"learning_rate": 0.0002491040462427746,
|
| 429 |
+
"loss": 0.6664,
|
| 430 |
+
"step": 690
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.97,
|
| 434 |
+
"learning_rate": 0.00024823699421965315,
|
| 435 |
+
"loss": 0.5312,
|
| 436 |
+
"step": 700
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.99,
|
| 440 |
+
"learning_rate": 0.0002473699421965318,
|
| 441 |
+
"loss": 0.4703,
|
| 442 |
+
"step": 710
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 2.02,
|
| 446 |
+
"learning_rate": 0.00024650289017341036,
|
| 447 |
+
"loss": 0.535,
|
| 448 |
+
"step": 720
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 2.05,
|
| 452 |
+
"learning_rate": 0.000245635838150289,
|
| 453 |
+
"loss": 0.6568,
|
| 454 |
+
"step": 730
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 2.08,
|
| 458 |
+
"learning_rate": 0.0002447687861271676,
|
| 459 |
+
"loss": 0.6303,
|
| 460 |
+
"step": 740
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 2.11,
|
| 464 |
+
"learning_rate": 0.00024390173410404622,
|
| 465 |
+
"loss": 0.4911,
|
| 466 |
+
"step": 750
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.13,
|
| 470 |
+
"learning_rate": 0.00024303468208092483,
|
| 471 |
+
"loss": 0.5043,
|
| 472 |
+
"step": 760
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 2.16,
|
| 476 |
+
"learning_rate": 0.00024216763005780346,
|
| 477 |
+
"loss": 0.5248,
|
| 478 |
+
"step": 770
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.19,
|
| 482 |
+
"learning_rate": 0.00024130057803468206,
|
| 483 |
+
"loss": 0.6274,
|
| 484 |
+
"step": 780
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 2.22,
|
| 488 |
+
"learning_rate": 0.00024043352601156066,
|
| 489 |
+
"loss": 0.5617,
|
| 490 |
+
"step": 790
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 2.25,
|
| 494 |
+
"learning_rate": 0.00023956647398843927,
|
| 495 |
+
"loss": 0.5978,
|
| 496 |
+
"step": 800
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 2.28,
|
| 500 |
+
"learning_rate": 0.00023869942196531787,
|
| 501 |
+
"loss": 0.6027,
|
| 502 |
+
"step": 810
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 2.3,
|
| 506 |
+
"learning_rate": 0.00023783236994219653,
|
| 507 |
+
"loss": 0.5925,
|
| 508 |
+
"step": 820
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.33,
|
| 512 |
+
"learning_rate": 0.00023696531791907513,
|
| 513 |
+
"loss": 0.593,
|
| 514 |
+
"step": 830
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 2.36,
|
| 518 |
+
"learning_rate": 0.00023609826589595373,
|
| 519 |
+
"loss": 0.6181,
|
| 520 |
+
"step": 840
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.39,
|
| 524 |
+
"learning_rate": 0.00023523121387283234,
|
| 525 |
+
"loss": 0.4752,
|
| 526 |
+
"step": 850
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 2.42,
|
| 530 |
+
"learning_rate": 0.00023436416184971097,
|
| 531 |
+
"loss": 0.655,
|
| 532 |
+
"step": 860
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 2.44,
|
| 536 |
+
"learning_rate": 0.00023349710982658957,
|
| 537 |
+
"loss": 0.5577,
|
| 538 |
+
"step": 870
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 2.47,
|
| 542 |
+
"learning_rate": 0.00023263005780346818,
|
| 543 |
+
"loss": 0.6132,
|
| 544 |
+
"step": 880
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 2.5,
|
| 548 |
+
"learning_rate": 0.00023176300578034678,
|
| 549 |
+
"loss": 0.5003,
|
| 550 |
+
"step": 890
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.53,
|
| 554 |
+
"learning_rate": 0.00023089595375722544,
|
| 555 |
+
"loss": 0.5323,
|
| 556 |
+
"step": 900
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 2.56,
|
| 560 |
+
"learning_rate": 0.00023002890173410404,
|
| 561 |
+
"loss": 0.5908,
|
| 562 |
+
"step": 910
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 2.58,
|
| 566 |
+
"learning_rate": 0.00022916184971098264,
|
| 567 |
+
"loss": 0.5911,
|
| 568 |
+
"step": 920
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 2.61,
|
| 572 |
+
"learning_rate": 0.00022829479768786125,
|
| 573 |
+
"loss": 0.565,
|
| 574 |
+
"step": 930
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 2.64,
|
| 578 |
+
"learning_rate": 0.00022742774566473988,
|
| 579 |
+
"loss": 0.5789,
|
| 580 |
+
"step": 940
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 2.67,
|
| 584 |
+
"learning_rate": 0.00022656069364161848,
|
| 585 |
+
"loss": 0.5242,
|
| 586 |
+
"step": 950
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.7,
|
| 590 |
+
"learning_rate": 0.00022569364161849708,
|
| 591 |
+
"loss": 0.5082,
|
| 592 |
+
"step": 960
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.72,
|
| 596 |
+
"learning_rate": 0.0002248265895953757,
|
| 597 |
+
"loss": 0.5184,
|
| 598 |
+
"step": 970
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 2.75,
|
| 602 |
+
"learning_rate": 0.0002239595375722543,
|
| 603 |
+
"loss": 0.6131,
|
| 604 |
+
"step": 980
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 2.78,
|
| 608 |
+
"learning_rate": 0.00022309248554913295,
|
| 609 |
+
"loss": 0.5129,
|
| 610 |
+
"step": 990
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 2.81,
|
| 614 |
+
"learning_rate": 0.00022222543352601155,
|
| 615 |
+
"loss": 0.6016,
|
| 616 |
+
"step": 1000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 2.81,
|
| 620 |
+
"eval_loss": 0.50592440366745,
|
| 621 |
+
"eval_runtime": 14.2225,
|
| 622 |
+
"eval_samples_per_second": 3.516,
|
| 623 |
+
"eval_steps_per_second": 0.492,
|
| 624 |
+
"step": 1000
|
| 625 |
+
}
|
| 626 |
+
],
|
| 627 |
+
"max_steps": 3560,
|
| 628 |
+
"num_train_epochs": 10,
|
| 629 |
+
"total_flos": 2.1070675154141184e+17,
|
| 630 |
+
"trial_name": null,
|
| 631 |
+
"trial_params": null
|
| 632 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:192bb8c013ae662fb0d4863dbc3254df0fbc2d1dc1eda37c4f9a2ac04b123a99
|
| 3 |
+
size 3771
|
checkpoint-500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa46925987f162d4d15ec6a1a7894299219eeb165ab66207453775a0e251a2ea
|
| 3 |
+
size 33661637
|
checkpoint-500/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:661bba0eef7d213a66caca9ed4d6c3a10d5ac4f849ec6fd0d298602f4fc52a71
|
| 3 |
+
size 16822989
|
checkpoint-500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80374c523339cbada5653606c3f391bc8649fd8866d5fea9a3587097101c165c
|
| 3 |
+
size 14575
|
checkpoint-500/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0d73e960e0c59a3ccac82210aaa3abcd9e00f7d9ab5c7ba39ef8751e5c0ee4b
|
| 3 |
+
size 557
|
checkpoint-500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5c26271f5f8a5d30d9a855ee399a8c85768b7490a42865ed931b650844878c5
|
| 3 |
+
size 627
|
checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "<unk>",
|
| 5 |
+
"unk_token": {
|
| 6 |
+
"content": "",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
}
|
| 12 |
+
}
|
checkpoint-500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
+
"pad_token": null,
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.5882205367088318,
|
| 3 |
+
"best_model_checkpoint": "/content/My Drive/LLaMA-LoRA Tuner/lora_models/earthshine-nondecorative-2023-06-27-17-40-07/checkpoint-500",
|
| 4 |
+
"epoch": 1.404494382022472,
|
| 5 |
+
"global_step": 500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 2.3999999999999997e-05,
|
| 13 |
+
"loss": 2.0693,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 5.399999999999999e-05,
|
| 19 |
+
"loss": 1.9946,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 8.1e-05,
|
| 25 |
+
"loss": 1.8837,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 0.00011099999999999999,
|
| 31 |
+
"loss": 1.6655,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.14,
|
| 36 |
+
"learning_rate": 0.00014099999999999998,
|
| 37 |
+
"loss": 1.6095,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.17,
|
| 42 |
+
"learning_rate": 0.00017099999999999998,
|
| 43 |
+
"loss": 1.3838,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.2,
|
| 48 |
+
"learning_rate": 0.000201,
|
| 49 |
+
"loss": 1.3548,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.22,
|
| 54 |
+
"learning_rate": 0.00023099999999999998,
|
| 55 |
+
"loss": 1.0789,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.25,
|
| 60 |
+
"learning_rate": 0.000261,
|
| 61 |
+
"loss": 1.0589,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.28,
|
| 66 |
+
"learning_rate": 0.00029099999999999997,
|
| 67 |
+
"loss": 1.0259,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.31,
|
| 72 |
+
"learning_rate": 0.000299393063583815,
|
| 73 |
+
"loss": 0.9936,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.34,
|
| 78 |
+
"learning_rate": 0.0002985260115606936,
|
| 79 |
+
"loss": 0.9633,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.37,
|
| 84 |
+
"learning_rate": 0.00029765895953757224,
|
| 85 |
+
"loss": 1.0018,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.39,
|
| 90 |
+
"learning_rate": 0.0002967919075144509,
|
| 91 |
+
"loss": 0.893,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.42,
|
| 96 |
+
"learning_rate": 0.00029592485549132945,
|
| 97 |
+
"loss": 0.8079,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.45,
|
| 102 |
+
"learning_rate": 0.0002950578034682081,
|
| 103 |
+
"loss": 0.8668,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.48,
|
| 108 |
+
"learning_rate": 0.00029419075144508666,
|
| 109 |
+
"loss": 0.773,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.51,
|
| 114 |
+
"learning_rate": 0.0002933236994219653,
|
| 115 |
+
"loss": 0.8139,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.53,
|
| 120 |
+
"learning_rate": 0.0002924566473988439,
|
| 121 |
+
"loss": 0.9139,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.56,
|
| 126 |
+
"learning_rate": 0.0002915895953757225,
|
| 127 |
+
"loss": 0.7371,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.59,
|
| 132 |
+
"learning_rate": 0.0002907225433526011,
|
| 133 |
+
"loss": 0.8604,
|
| 134 |
+
"step": 210
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.62,
|
| 138 |
+
"learning_rate": 0.0002898554913294797,
|
| 139 |
+
"loss": 0.8597,
|
| 140 |
+
"step": 220
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.65,
|
| 144 |
+
"learning_rate": 0.0002889884393063584,
|
| 145 |
+
"loss": 0.7954,
|
| 146 |
+
"step": 230
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.67,
|
| 150 |
+
"learning_rate": 0.00028812138728323696,
|
| 151 |
+
"loss": 0.7559,
|
| 152 |
+
"step": 240
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.7,
|
| 156 |
+
"learning_rate": 0.0002872543352601156,
|
| 157 |
+
"loss": 0.8488,
|
| 158 |
+
"step": 250
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.73,
|
| 162 |
+
"learning_rate": 0.00028638728323699417,
|
| 163 |
+
"loss": 0.7252,
|
| 164 |
+
"step": 260
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.76,
|
| 168 |
+
"learning_rate": 0.0002855202312138728,
|
| 169 |
+
"loss": 0.6751,
|
| 170 |
+
"step": 270
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.79,
|
| 174 |
+
"learning_rate": 0.00028465317919075143,
|
| 175 |
+
"loss": 0.7852,
|
| 176 |
+
"step": 280
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.81,
|
| 180 |
+
"learning_rate": 0.00028378612716763,
|
| 181 |
+
"loss": 0.7843,
|
| 182 |
+
"step": 290
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.84,
|
| 186 |
+
"learning_rate": 0.00028291907514450864,
|
| 187 |
+
"loss": 0.7886,
|
| 188 |
+
"step": 300
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.87,
|
| 192 |
+
"learning_rate": 0.00028205202312138727,
|
| 193 |
+
"loss": 0.7218,
|
| 194 |
+
"step": 310
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.9,
|
| 198 |
+
"learning_rate": 0.0002811849710982659,
|
| 199 |
+
"loss": 0.7919,
|
| 200 |
+
"step": 320
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.93,
|
| 204 |
+
"learning_rate": 0.0002803179190751445,
|
| 205 |
+
"loss": 0.7248,
|
| 206 |
+
"step": 330
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.96,
|
| 210 |
+
"learning_rate": 0.0002794508670520231,
|
| 211 |
+
"loss": 0.7699,
|
| 212 |
+
"step": 340
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.98,
|
| 216 |
+
"learning_rate": 0.00027858381502890174,
|
| 217 |
+
"loss": 0.6909,
|
| 218 |
+
"step": 350
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.01,
|
| 222 |
+
"learning_rate": 0.0002777167630057803,
|
| 223 |
+
"loss": 0.6992,
|
| 224 |
+
"step": 360
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.04,
|
| 228 |
+
"learning_rate": 0.00027684971098265894,
|
| 229 |
+
"loss": 0.6747,
|
| 230 |
+
"step": 370
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.07,
|
| 234 |
+
"learning_rate": 0.0002759826589595375,
|
| 235 |
+
"loss": 0.672,
|
| 236 |
+
"step": 380
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.1,
|
| 240 |
+
"learning_rate": 0.0002751156069364162,
|
| 241 |
+
"loss": 0.5997,
|
| 242 |
+
"step": 390
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.12,
|
| 246 |
+
"learning_rate": 0.0002742485549132948,
|
| 247 |
+
"loss": 0.747,
|
| 248 |
+
"step": 400
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.15,
|
| 252 |
+
"learning_rate": 0.0002733815028901734,
|
| 253 |
+
"loss": 0.7217,
|
| 254 |
+
"step": 410
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.18,
|
| 258 |
+
"learning_rate": 0.000272514450867052,
|
| 259 |
+
"loss": 0.683,
|
| 260 |
+
"step": 420
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.21,
|
| 264 |
+
"learning_rate": 0.0002716473988439306,
|
| 265 |
+
"loss": 0.63,
|
| 266 |
+
"step": 430
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.24,
|
| 270 |
+
"learning_rate": 0.00027078034682080925,
|
| 271 |
+
"loss": 0.6889,
|
| 272 |
+
"step": 440
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.26,
|
| 276 |
+
"learning_rate": 0.0002699132947976878,
|
| 277 |
+
"loss": 0.6582,
|
| 278 |
+
"step": 450
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.29,
|
| 282 |
+
"learning_rate": 0.00026904624277456645,
|
| 283 |
+
"loss": 0.6366,
|
| 284 |
+
"step": 460
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.32,
|
| 288 |
+
"learning_rate": 0.00026817919075144503,
|
| 289 |
+
"loss": 0.7249,
|
| 290 |
+
"step": 470
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.35,
|
| 294 |
+
"learning_rate": 0.0002673121387283237,
|
| 295 |
+
"loss": 0.53,
|
| 296 |
+
"step": 480
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.38,
|
| 300 |
+
"learning_rate": 0.0002664450867052023,
|
| 301 |
+
"loss": 0.6172,
|
| 302 |
+
"step": 490
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.4,
|
| 306 |
+
"learning_rate": 0.0002655780346820809,
|
| 307 |
+
"loss": 0.6033,
|
| 308 |
+
"step": 500
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.4,
|
| 312 |
+
"eval_loss": 0.5882205367088318,
|
| 313 |
+
"eval_runtime": 14.2208,
|
| 314 |
+
"eval_samples_per_second": 3.516,
|
| 315 |
+
"eval_steps_per_second": 0.492,
|
| 316 |
+
"step": 500
|
| 317 |
+
}
|
| 318 |
+
],
|
| 319 |
+
"max_steps": 3560,
|
| 320 |
+
"num_train_epochs": 10,
|
| 321 |
+
"total_flos": 1.0535163032469504e+17,
|
| 322 |
+
"trial_name": null,
|
| 323 |
+
"trial_params": null
|
| 324 |
+
}
|
checkpoint-500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:192bb8c013ae662fb0d4863dbc3254df0fbc2d1dc1eda37c4f9a2ac04b123a99
|
| 3 |
+
size 3771
|
finetune_args.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"micro_batch_size": 4,
|
| 3 |
+
"gradient_accumulation_steps": 1,
|
| 4 |
+
"num_train_epochs": 10,
|
| 5 |
+
"learning_rate": 0.0003,
|
| 6 |
+
"cutoff_len": 2048,
|
| 7 |
+
"val_set_size": 50,
|
| 8 |
+
"lora_r": 8,
|
| 9 |
+
"lora_alpha": 16,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"lora_target_modules": [
|
| 12 |
+
"q_proj",
|
| 13 |
+
"v_proj"
|
| 14 |
+
],
|
| 15 |
+
"lora_modules_to_save": [],
|
| 16 |
+
"train_on_inputs": true,
|
| 17 |
+
"group_by_length": false,
|
| 18 |
+
"load_in_8bit": true,
|
| 19 |
+
"fp16": true,
|
| 20 |
+
"bf16": false,
|
| 21 |
+
"gradient_checkpointing": false,
|
| 22 |
+
"save_steps": 500,
|
| 23 |
+
"save_total_limit": 5,
|
| 24 |
+
"logging_steps": 10,
|
| 25 |
+
"additional_training_arguments": null,
|
| 26 |
+
"additional_lora_config": null
|
| 27 |
+
}
|
info.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"prompt_template": "alpaca",
|
| 4 |
+
"dataset_name": "N/A (from text input)",
|
| 5 |
+
"dataset_rows": 1473,
|
| 6 |
+
"trained_on_machine": "04e3f719f875",
|
| 7 |
+
"timestamp": 1687887738.143719,
|
| 8 |
+
"tuner_version": "f4254216"
|
| 9 |
+
}
|
runs/Jun27_17-42-45_04e3f719f875/1687887765.9930556/events.out.tfevents.1687887765.04e3f719f875.4175.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59cd0c7b15630c24e21d8875a07f94feb3f09a7c7a2dce48987feb914d9c2def
|
| 3 |
+
size 6109
|
runs/Jun27_17-42-45_04e3f719f875/events.out.tfevents.1687887765.04e3f719f875.4175.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8cfa583b47c9b31f7c856b7919355df0e4cab0434410bbec2a99ea8d839cd53
|
| 3 |
+
size 21356
|
train_data_samples.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
train_output.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
1041,
|
| 3 |
+
0.7449809693580173,
|
| 4 |
+
{
|
| 5 |
+
"train_runtime": 3194.7197,
|
| 6 |
+
"train_samples_per_second": 4.454,
|
| 7 |
+
"train_steps_per_second": 1.114,
|
| 8 |
+
"total_flos": 2.2017658953498624e+17,
|
| 9 |
+
"train_loss": 0.7449809693580173,
|
| 10 |
+
"epoch": 2.92
|
| 11 |
+
}
|
| 12 |
+
]
|
trainer_args.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/content/My Drive/LLaMA-LoRA Tuner/lora_models/earthshine-nondecorative-2023-06-27-17-40-07",
|
| 3 |
+
"overwrite_output_dir": false,
|
| 4 |
+
"do_train": false,
|
| 5 |
+
"do_eval": true,
|
| 6 |
+
"do_predict": false,
|
| 7 |
+
"evaluation_strategy": "steps",
|
| 8 |
+
"prediction_loss_only": false,
|
| 9 |
+
"per_device_train_batch_size": 4,
|
| 10 |
+
"per_device_eval_batch_size": 8,
|
| 11 |
+
"per_gpu_train_batch_size": null,
|
| 12 |
+
"per_gpu_eval_batch_size": null,
|
| 13 |
+
"gradient_accumulation_steps": 1,
|
| 14 |
+
"eval_accumulation_steps": null,
|
| 15 |
+
"eval_delay": 0,
|
| 16 |
+
"learning_rate": 0.0003,
|
| 17 |
+
"weight_decay": 0.0,
|
| 18 |
+
"adam_beta1": 0.9,
|
| 19 |
+
"adam_beta2": 0.999,
|
| 20 |
+
"adam_epsilon": 1e-08,
|
| 21 |
+
"max_grad_norm": 1.0,
|
| 22 |
+
"num_train_epochs": 10,
|
| 23 |
+
"max_steps": -1,
|
| 24 |
+
"lr_scheduler_type": "linear",
|
| 25 |
+
"warmup_ratio": 0.0,
|
| 26 |
+
"warmup_steps": 100,
|
| 27 |
+
"log_level": "passive",
|
| 28 |
+
"log_level_replica": "warning",
|
| 29 |
+
"log_on_each_node": true,
|
| 30 |
+
"logging_dir": "/content/My Drive/LLaMA-LoRA Tuner/lora_models/earthshine-nondecorative-2023-06-27-17-40-07/runs/Jun27_17-42-45_04e3f719f875",
|
| 31 |
+
"logging_strategy": "steps",
|
| 32 |
+
"logging_first_step": false,
|
| 33 |
+
"logging_steps": 10,
|
| 34 |
+
"logging_nan_inf_filter": true,
|
| 35 |
+
"save_strategy": "steps",
|
| 36 |
+
"save_steps": 500,
|
| 37 |
+
"save_total_limit": 5,
|
| 38 |
+
"save_safetensors": false,
|
| 39 |
+
"save_on_each_node": false,
|
| 40 |
+
"no_cuda": false,
|
| 41 |
+
"use_mps_device": false,
|
| 42 |
+
"seed": 42,
|
| 43 |
+
"data_seed": null,
|
| 44 |
+
"jit_mode_eval": false,
|
| 45 |
+
"use_ipex": false,
|
| 46 |
+
"bf16": false,
|
| 47 |
+
"fp16": true,
|
| 48 |
+
"fp16_opt_level": "O1",
|
| 49 |
+
"half_precision_backend": "cuda_amp",
|
| 50 |
+
"bf16_full_eval": false,
|
| 51 |
+
"fp16_full_eval": false,
|
| 52 |
+
"tf32": null,
|
| 53 |
+
"local_rank": -1,
|
| 54 |
+
"xpu_backend": null,
|
| 55 |
+
"tpu_num_cores": null,
|
| 56 |
+
"tpu_metrics_debug": false,
|
| 57 |
+
"debug": [],
|
| 58 |
+
"dataloader_drop_last": false,
|
| 59 |
+
"eval_steps": 500,
|
| 60 |
+
"dataloader_num_workers": 0,
|
| 61 |
+
"past_index": -1,
|
| 62 |
+
"run_name": "/content/My Drive/LLaMA-LoRA Tuner/lora_models/earthshine-nondecorative-2023-06-27-17-40-07",
|
| 63 |
+
"disable_tqdm": false,
|
| 64 |
+
"remove_unused_columns": true,
|
| 65 |
+
"label_names": null,
|
| 66 |
+
"load_best_model_at_end": true,
|
| 67 |
+
"metric_for_best_model": "loss",
|
| 68 |
+
"greater_is_better": false,
|
| 69 |
+
"ignore_data_skip": false,
|
| 70 |
+
"sharded_ddp": [],
|
| 71 |
+
"fsdp": [],
|
| 72 |
+
"fsdp_min_num_params": 0,
|
| 73 |
+
"fsdp_config": {
|
| 74 |
+
"fsdp_min_num_params": 0,
|
| 75 |
+
"xla": false,
|
| 76 |
+
"xla_fsdp_grad_ckpt": false
|
| 77 |
+
},
|
| 78 |
+
"fsdp_transformer_layer_cls_to_wrap": null,
|
| 79 |
+
"deepspeed": null,
|
| 80 |
+
"label_smoothing_factor": 0.0,
|
| 81 |
+
"optim": "adamw_torch",
|
| 82 |
+
"optim_args": null,
|
| 83 |
+
"adafactor": false,
|
| 84 |
+
"group_by_length": false,
|
| 85 |
+
"length_column_name": "length",
|
| 86 |
+
"report_to": [
|
| 87 |
+
"tensorboard"
|
| 88 |
+
],
|
| 89 |
+
"ddp_find_unused_parameters": null,
|
| 90 |
+
"ddp_bucket_cap_mb": null,
|
| 91 |
+
"dataloader_pin_memory": true,
|
| 92 |
+
"skip_memory_metrics": true,
|
| 93 |
+
"use_legacy_prediction_loop": false,
|
| 94 |
+
"push_to_hub": false,
|
| 95 |
+
"resume_from_checkpoint": null,
|
| 96 |
+
"hub_model_id": null,
|
| 97 |
+
"hub_strategy": "every_save",
|
| 98 |
+
"hub_token": "<HUB_TOKEN>",
|
| 99 |
+
"hub_private_repo": false,
|
| 100 |
+
"gradient_checkpointing": false,
|
| 101 |
+
"include_inputs_for_metrics": false,
|
| 102 |
+
"fp16_backend": "auto",
|
| 103 |
+
"push_to_hub_model_id": null,
|
| 104 |
+
"push_to_hub_organization": null,
|
| 105 |
+
"push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
|
| 106 |
+
"mp_parameters": "",
|
| 107 |
+
"auto_find_batch_size": false,
|
| 108 |
+
"full_determinism": false,
|
| 109 |
+
"torchdynamo": null,
|
| 110 |
+
"ray_scope": "last",
|
| 111 |
+
"ddp_timeout": 1800,
|
| 112 |
+
"torch_compile": false,
|
| 113 |
+
"torch_compile_backend": null,
|
| 114 |
+
"torch_compile_mode": null
|
| 115 |
+
}
|
trainer_log_history.jsonl
ADDED
|
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"loss": 2.0693, "learning_rate": 2.3999999999999997e-05, "epoch": 0.03, "step": 10}
|
| 2 |
+
{"loss": 1.9946, "learning_rate": 5.399999999999999e-05, "epoch": 0.06, "step": 20}
|
| 3 |
+
{"loss": 1.8837, "learning_rate": 8.1e-05, "epoch": 0.08, "step": 30}
|
| 4 |
+
{"loss": 1.6655, "learning_rate": 0.00011099999999999999, "epoch": 0.11, "step": 40}
|
| 5 |
+
{"loss": 1.6095, "learning_rate": 0.00014099999999999998, "epoch": 0.14, "step": 50}
|
| 6 |
+
{"loss": 1.3838, "learning_rate": 0.00017099999999999998, "epoch": 0.17, "step": 60}
|
| 7 |
+
{"loss": 1.3548, "learning_rate": 0.000201, "epoch": 0.2, "step": 70}
|
| 8 |
+
{"loss": 1.0789, "learning_rate": 0.00023099999999999998, "epoch": 0.22, "step": 80}
|
| 9 |
+
{"loss": 1.0589, "learning_rate": 0.000261, "epoch": 0.25, "step": 90}
|
| 10 |
+
{"loss": 1.0259, "learning_rate": 0.00029099999999999997, "epoch": 0.28, "step": 100}
|
| 11 |
+
{"loss": 0.9936, "learning_rate": 0.000299393063583815, "epoch": 0.31, "step": 110}
|
| 12 |
+
{"loss": 0.9633, "learning_rate": 0.0002985260115606936, "epoch": 0.34, "step": 120}
|
| 13 |
+
{"loss": 1.0018, "learning_rate": 0.00029765895953757224, "epoch": 0.37, "step": 130}
|
| 14 |
+
{"loss": 0.893, "learning_rate": 0.0002967919075144509, "epoch": 0.39, "step": 140}
|
| 15 |
+
{"loss": 0.8079, "learning_rate": 0.00029592485549132945, "epoch": 0.42, "step": 150}
|
| 16 |
+
{"loss": 0.8668, "learning_rate": 0.0002950578034682081, "epoch": 0.45, "step": 160}
|
| 17 |
+
{"loss": 0.773, "learning_rate": 0.00029419075144508666, "epoch": 0.48, "step": 170}
|
| 18 |
+
{"loss": 0.8139, "learning_rate": 0.0002933236994219653, "epoch": 0.51, "step": 180}
|
| 19 |
+
{"loss": 0.9139, "learning_rate": 0.0002924566473988439, "epoch": 0.53, "step": 190}
|
| 20 |
+
{"loss": 0.7371, "learning_rate": 0.0002915895953757225, "epoch": 0.56, "step": 200}
|
| 21 |
+
{"loss": 0.8604, "learning_rate": 0.0002907225433526011, "epoch": 0.59, "step": 210}
|
| 22 |
+
{"loss": 0.8597, "learning_rate": 0.0002898554913294797, "epoch": 0.62, "step": 220}
|
| 23 |
+
{"loss": 0.7954, "learning_rate": 0.0002889884393063584, "epoch": 0.65, "step": 230}
|
| 24 |
+
{"loss": 0.7559, "learning_rate": 0.00028812138728323696, "epoch": 0.67, "step": 240}
|
| 25 |
+
{"loss": 0.8488, "learning_rate": 0.0002872543352601156, "epoch": 0.7, "step": 250}
|
| 26 |
+
{"loss": 0.7252, "learning_rate": 0.00028638728323699417, "epoch": 0.73, "step": 260}
|
| 27 |
+
{"loss": 0.6751, "learning_rate": 0.0002855202312138728, "epoch": 0.76, "step": 270}
|
| 28 |
+
{"loss": 0.7852, "learning_rate": 0.00028465317919075143, "epoch": 0.79, "step": 280}
|
| 29 |
+
{"loss": 0.7843, "learning_rate": 0.00028378612716763, "epoch": 0.81, "step": 290}
|
| 30 |
+
{"loss": 0.7886, "learning_rate": 0.00028291907514450864, "epoch": 0.84, "step": 300}
|
| 31 |
+
{"loss": 0.7218, "learning_rate": 0.00028205202312138727, "epoch": 0.87, "step": 310}
|
| 32 |
+
{"loss": 0.7919, "learning_rate": 0.0002811849710982659, "epoch": 0.9, "step": 320}
|
| 33 |
+
{"loss": 0.7248, "learning_rate": 0.0002803179190751445, "epoch": 0.93, "step": 330}
|
| 34 |
+
{"loss": 0.7699, "learning_rate": 0.0002794508670520231, "epoch": 0.96, "step": 340}
|
| 35 |
+
{"loss": 0.6909, "learning_rate": 0.00027858381502890174, "epoch": 0.98, "step": 350}
|
| 36 |
+
{"loss": 0.6992, "learning_rate": 0.0002777167630057803, "epoch": 1.01, "step": 360}
|
| 37 |
+
{"loss": 0.6747, "learning_rate": 0.00027684971098265894, "epoch": 1.04, "step": 370}
|
| 38 |
+
{"loss": 0.672, "learning_rate": 0.0002759826589595375, "epoch": 1.07, "step": 380}
|
| 39 |
+
{"loss": 0.5997, "learning_rate": 0.0002751156069364162, "epoch": 1.1, "step": 390}
|
| 40 |
+
{"loss": 0.747, "learning_rate": 0.0002742485549132948, "epoch": 1.12, "step": 400}
|
| 41 |
+
{"loss": 0.7217, "learning_rate": 0.0002733815028901734, "epoch": 1.15, "step": 410}
|
| 42 |
+
{"loss": 0.683, "learning_rate": 0.000272514450867052, "epoch": 1.18, "step": 420}
|
| 43 |
+
{"loss": 0.63, "learning_rate": 0.0002716473988439306, "epoch": 1.21, "step": 430}
|
| 44 |
+
{"loss": 0.6889, "learning_rate": 0.00027078034682080925, "epoch": 1.24, "step": 440}
|
| 45 |
+
{"loss": 0.6582, "learning_rate": 0.0002699132947976878, "epoch": 1.26, "step": 450}
|
| 46 |
+
{"loss": 0.6366, "learning_rate": 0.00026904624277456645, "epoch": 1.29, "step": 460}
|
| 47 |
+
{"loss": 0.7249, "learning_rate": 0.00026817919075144503, "epoch": 1.32, "step": 470}
|
| 48 |
+
{"loss": 0.53, "learning_rate": 0.0002673121387283237, "epoch": 1.35, "step": 480}
|
| 49 |
+
{"loss": 0.6172, "learning_rate": 0.0002664450867052023, "epoch": 1.38, "step": 490}
|
| 50 |
+
{"loss": 0.6033, "learning_rate": 0.0002655780346820809, "epoch": 1.4, "step": 500}
|
| 51 |
+
{"eval_loss": 0.5882205367088318, "eval_runtime": 14.2208, "eval_samples_per_second": 3.516, "eval_steps_per_second": 0.492, "epoch": 1.4, "step": 500}
|
| 52 |
+
{"loss": 0.7452, "learning_rate": 0.0002647109826589595, "epoch": 1.43, "step": 510}
|
| 53 |
+
{"loss": 0.6689, "learning_rate": 0.00026384393063583813, "epoch": 1.46, "step": 520}
|
| 54 |
+
{"loss": 0.6339, "learning_rate": 0.00026297687861271676, "epoch": 1.49, "step": 530}
|
| 55 |
+
{"loss": 0.6538, "learning_rate": 0.00026210982658959533, "epoch": 1.52, "step": 540}
|
| 56 |
+
{"loss": 0.6864, "learning_rate": 0.00026124277456647397, "epoch": 1.54, "step": 550}
|
| 57 |
+
{"loss": 0.6466, "learning_rate": 0.0002603757225433526, "epoch": 1.57, "step": 560}
|
| 58 |
+
{"loss": 0.6186, "learning_rate": 0.00025950867052023117, "epoch": 1.6, "step": 570}
|
| 59 |
+
{"loss": 0.6872, "learning_rate": 0.0002586416184971098, "epoch": 1.63, "step": 580}
|
| 60 |
+
{"loss": 0.7206, "learning_rate": 0.00025777456647398843, "epoch": 1.66, "step": 590}
|
| 61 |
+
{"loss": 0.5848, "learning_rate": 0.000256907514450867, "epoch": 1.69, "step": 600}
|
| 62 |
+
{"loss": 0.711, "learning_rate": 0.00025604046242774564, "epoch": 1.71, "step": 610}
|
| 63 |
+
{"loss": 0.628, "learning_rate": 0.00025517341040462427, "epoch": 1.74, "step": 620}
|
| 64 |
+
{"loss": 0.7035, "learning_rate": 0.00025430635838150285, "epoch": 1.77, "step": 630}
|
| 65 |
+
{"loss": 0.5965, "learning_rate": 0.0002534393063583815, "epoch": 1.8, "step": 640}
|
| 66 |
+
{"loss": 0.6486, "learning_rate": 0.0002525722543352601, "epoch": 1.83, "step": 650}
|
| 67 |
+
{"loss": 0.6264, "learning_rate": 0.0002517052023121387, "epoch": 1.85, "step": 660}
|
| 68 |
+
{"loss": 0.6469, "learning_rate": 0.0002508381502890173, "epoch": 1.88, "step": 670}
|
| 69 |
+
{"loss": 0.61, "learning_rate": 0.00024997109826589595, "epoch": 1.91, "step": 680}
|
| 70 |
+
{"loss": 0.6664, "learning_rate": 0.0002491040462427746, "epoch": 1.94, "step": 690}
|
| 71 |
+
{"loss": 0.5312, "learning_rate": 0.00024823699421965315, "epoch": 1.97, "step": 700}
|
| 72 |
+
{"loss": 0.4703, "learning_rate": 0.0002473699421965318, "epoch": 1.99, "step": 710}
|
| 73 |
+
{"loss": 0.535, "learning_rate": 0.00024650289017341036, "epoch": 2.02, "step": 720}
|
| 74 |
+
{"loss": 0.6568, "learning_rate": 0.000245635838150289, "epoch": 2.05, "step": 730}
|
| 75 |
+
{"loss": 0.6303, "learning_rate": 0.0002447687861271676, "epoch": 2.08, "step": 740}
|
| 76 |
+
{"loss": 0.4911, "learning_rate": 0.00024390173410404622, "epoch": 2.11, "step": 750}
|
| 77 |
+
{"loss": 0.5043, "learning_rate": 0.00024303468208092483, "epoch": 2.13, "step": 760}
|
| 78 |
+
{"loss": 0.5248, "learning_rate": 0.00024216763005780346, "epoch": 2.16, "step": 770}
|
| 79 |
+
{"loss": 0.6274, "learning_rate": 0.00024130057803468206, "epoch": 2.19, "step": 780}
|
| 80 |
+
{"loss": 0.5617, "learning_rate": 0.00024043352601156066, "epoch": 2.22, "step": 790}
|
| 81 |
+
{"loss": 0.5978, "learning_rate": 0.00023956647398843927, "epoch": 2.25, "step": 800}
|
| 82 |
+
{"loss": 0.6027, "learning_rate": 0.00023869942196531787, "epoch": 2.28, "step": 810}
|
| 83 |
+
{"loss": 0.5925, "learning_rate": 0.00023783236994219653, "epoch": 2.3, "step": 820}
|
| 84 |
+
{"loss": 0.593, "learning_rate": 0.00023696531791907513, "epoch": 2.33, "step": 830}
|
| 85 |
+
{"loss": 0.6181, "learning_rate": 0.00023609826589595373, "epoch": 2.36, "step": 840}
|
| 86 |
+
{"loss": 0.4752, "learning_rate": 0.00023523121387283234, "epoch": 2.39, "step": 850}
|
| 87 |
+
{"loss": 0.655, "learning_rate": 0.00023436416184971097, "epoch": 2.42, "step": 860}
|
| 88 |
+
{"loss": 0.5577, "learning_rate": 0.00023349710982658957, "epoch": 2.44, "step": 870}
|
| 89 |
+
{"loss": 0.6132, "learning_rate": 0.00023263005780346818, "epoch": 2.47, "step": 880}
|
| 90 |
+
{"loss": 0.5003, "learning_rate": 0.00023176300578034678, "epoch": 2.5, "step": 890}
|
| 91 |
+
{"loss": 0.5323, "learning_rate": 0.00023089595375722544, "epoch": 2.53, "step": 900}
|
| 92 |
+
{"loss": 0.5908, "learning_rate": 0.00023002890173410404, "epoch": 2.56, "step": 910}
|
| 93 |
+
{"loss": 0.5911, "learning_rate": 0.00022916184971098264, "epoch": 2.58, "step": 920}
|
| 94 |
+
{"loss": 0.565, "learning_rate": 0.00022829479768786125, "epoch": 2.61, "step": 930}
|
| 95 |
+
{"loss": 0.5789, "learning_rate": 0.00022742774566473988, "epoch": 2.64, "step": 940}
|
| 96 |
+
{"loss": 0.5242, "learning_rate": 0.00022656069364161848, "epoch": 2.67, "step": 950}
|
| 97 |
+
{"loss": 0.5082, "learning_rate": 0.00022569364161849708, "epoch": 2.7, "step": 960}
|
| 98 |
+
{"loss": 0.5184, "learning_rate": 0.0002248265895953757, "epoch": 2.72, "step": 970}
|
| 99 |
+
{"loss": 0.6131, "learning_rate": 0.0002239595375722543, "epoch": 2.75, "step": 980}
|
| 100 |
+
{"loss": 0.5129, "learning_rate": 0.00022309248554913295, "epoch": 2.78, "step": 990}
|
| 101 |
+
{"loss": 0.6016, "learning_rate": 0.00022222543352601155, "epoch": 2.81, "step": 1000}
|
| 102 |
+
{"eval_loss": 0.50592440366745, "eval_runtime": 14.2225, "eval_samples_per_second": 3.516, "eval_steps_per_second": 0.492, "epoch": 2.81, "step": 1000}
|
| 103 |
+
{"loss": 0.5728, "learning_rate": 0.00022135838150289016, "epoch": 2.84, "step": 1010}
|
| 104 |
+
{"loss": 0.5155, "learning_rate": 0.00022049132947976876, "epoch": 2.87, "step": 1020}
|
| 105 |
+
{"loss": 0.5522, "learning_rate": 0.0002196242774566474, "epoch": 2.89, "step": 1030}
|
| 106 |
+
{"loss": 0.5176, "learning_rate": 0.000218757225433526, "epoch": 2.92, "step": 1040}
|
| 107 |
+
{"train_runtime": 3194.7197, "train_samples_per_second": 4.454, "train_steps_per_second": 1.114, "total_flos": 2.2017658953498624e+17, "train_loss": 0.7449809693580173, "epoch": 2.92, "step": 1041}
|