Uploading /ephemeral/hossein/output/newData-progressive-yoco-tiny-llama-CDL-18
Browse files- README.md +61 -0
- all_results.json +8 -0
- config.json +1 -0
- generation_config.json +7 -0
- runs/Nov29_09-39-22_creative-turing-2/events.out.tfevents.1732873360.creative-turing-2.2677938.0 +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- train_results.json +8 -0
- trainer_log.jsonl +51 -0
- trainer_state.json +392 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: TinyLlama/TinyLlama_v1.1
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: newData-progressive-yoco-tiny-llama-CDL-18
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# newData-progressive-yoco-tiny-llama-CDL-18
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/ephemeral/hossein/output/newData-progressive-yoco-tiny-llama-CDL-19/checkpoint-50](https://huggingface.co//ephemeral/hossein/output/newData-progressive-yoco-tiny-llama-CDL-19/checkpoint-50) on the alpaca_reformatted, the UltraInteract_sft_reformatted, the reformatted_ultrachat_200k, the reformatted_MathInstruct and the small_slim_pajama datasets.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 58
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 42
|
| 42 |
+
- distributed_type: multi-GPU
|
| 43 |
+
- num_devices: 8
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 1856
|
| 46 |
+
- total_eval_batch_size: 8
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.005
|
| 50 |
+
- training_steps: 50
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
### Framework versions
|
| 57 |
+
|
| 58 |
+
- Transformers 4.45.2
|
| 59 |
+
- Pytorch 2.5.1+cu124
|
| 60 |
+
- Datasets 3.1.0
|
| 61 |
+
- Tokenizers 0.20.3
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.05959475566150179,
|
| 3 |
+
"total_flos": 106890730143744.0,
|
| 4 |
+
"train_loss": 2.030773923397064,
|
| 5 |
+
"train_runtime": 1597.0722,
|
| 6 |
+
"train_samples_per_second": 58.106,
|
| 7 |
+
"train_steps_per_second": 0.031
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_name_or_path": "TinyLlama/TinyLlama_v1.1", "architectures": ["ProgressiveYocoLlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "crossDecoder_start_idx": 4, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "progressive_yoco_llama", "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "use_cache": false, "vocab_size": 32000}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.45.2"
|
| 7 |
+
}
|
runs/Nov29_09-39-22_creative-turing-2/events.out.tfevents.1732873360.creative-turing-2.2677938.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2264760cd5763388436a75b397ca474decb033ca3d6589a65ac38a2e8c178c85
|
| 3 |
+
size 16158
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": 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,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
|
| 33 |
+
"clean_up_tokenization_spaces": false,
|
| 34 |
+
"eos_token": "</s>",
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"padding_side": "right",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"split_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": false
|
| 44 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.05959475566150179,
|
| 3 |
+
"total_flos": 106890730143744.0,
|
| 4 |
+
"train_loss": 2.030773923397064,
|
| 5 |
+
"train_runtime": 1597.0722,
|
| 6 |
+
"train_samples_per_second": 58.106,
|
| 7 |
+
"train_steps_per_second": 0.031
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 50, "loss": 2.1431, "lr": 2e-05, "epoch": 0.0011918951132300357, "percentage": 2.0, "elapsed_time": "0:00:35", "remaining_time": "0:28:40"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 50, "loss": 2.138, "lr": 1.9979453927503366e-05, "epoch": 0.0023837902264600714, "percentage": 4.0, "elapsed_time": "0:01:06", "remaining_time": "0:26:35"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 50, "loss": 2.0438, "lr": 1.991790013823246e-05, "epoch": 0.003575685339690107, "percentage": 6.0, "elapsed_time": "0:01:38", "remaining_time": "0:25:35"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 50, "loss": 2.0838, "lr": 1.9815591569910654e-05, "epoch": 0.004767580452920143, "percentage": 8.0, "elapsed_time": "0:02:09", "remaining_time": "0:24:51"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 50, "loss": 2.0696, "lr": 1.9672948630390296e-05, "epoch": 0.0059594755661501785, "percentage": 10.0, "elapsed_time": "0:02:41", "remaining_time": "0:24:12"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 50, "loss": 2.0977, "lr": 1.949055747010669e-05, "epoch": 0.007151370679380214, "percentage": 12.0, "elapsed_time": "0:03:13", "remaining_time": "0:23:36"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 50, "loss": 2.0518, "lr": 1.926916757346022e-05, "epoch": 0.00834326579261025, "percentage": 14.0, "elapsed_time": "0:03:44", "remaining_time": "0:23:01"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 50, "loss": 2.0096, "lr": 1.900968867902419e-05, "epoch": 0.009535160905840286, "percentage": 16.0, "elapsed_time": "0:04:16", "remaining_time": "0:22:27"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 50, "loss": 2.0271, "lr": 1.8713187041233896e-05, "epoch": 0.010727056019070322, "percentage": 18.0, "elapsed_time": "0:04:48", "remaining_time": "0:21:53"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 50, "loss": 2.0058, "lr": 1.8380881048918406e-05, "epoch": 0.011918951132300357, "percentage": 20.0, "elapsed_time": "0:05:20", "remaining_time": "0:21:20"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 50, "loss": 2.01, "lr": 1.8014136218679566e-05, "epoch": 0.013110846245530394, "percentage": 22.0, "elapsed_time": "0:05:51", "remaining_time": "0:20:47"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 50, "loss": 2.0019, "lr": 1.7614459583691346e-05, "epoch": 0.014302741358760428, "percentage": 24.0, "elapsed_time": "0:06:23", "remaining_time": "0:20:14"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 50, "loss": 1.9932, "lr": 1.7183493500977277e-05, "epoch": 0.015494636471990465, "percentage": 26.0, "elapsed_time": "0:06:55", "remaining_time": "0:19:41"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 50, "loss": 1.9988, "lr": 1.672300890261317e-05, "epoch": 0.0166865315852205, "percentage": 28.0, "elapsed_time": "0:07:27", "remaining_time": "0:19:09"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 50, "loss": 2.0101, "lr": 1.6234898018587336e-05, "epoch": 0.017878426698450536, "percentage": 30.0, "elapsed_time": "0:07:58", "remaining_time": "0:18:37"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 50, "loss": 1.9911, "lr": 1.5721166601221697e-05, "epoch": 0.01907032181168057, "percentage": 32.0, "elapsed_time": "0:08:30", "remaining_time": "0:18:04"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 50, "loss": 2.0116, "lr": 1.5183925683105254e-05, "epoch": 0.02026221692491061, "percentage": 34.0, "elapsed_time": "0:09:02", "remaining_time": "0:17:32"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 50, "loss": 2.0073, "lr": 1.4625382902408356e-05, "epoch": 0.021454112038140644, "percentage": 36.0, "elapsed_time": "0:09:34", "remaining_time": "0:17:00"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 50, "loss": 2.0208, "lr": 1.4047833431223938e-05, "epoch": 0.02264600715137068, "percentage": 38.0, "elapsed_time": "0:10:05", "remaining_time": "0:16:28"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 50, "loss": 2.031, "lr": 1.3453650544213078e-05, "epoch": 0.023837902264600714, "percentage": 40.0, "elapsed_time": "0:10:37", "remaining_time": "0:15:56"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 50, "loss": 1.9957, "lr": 1.2845275866310325e-05, "epoch": 0.025029797377830752, "percentage": 42.0, "elapsed_time": "0:11:09", "remaining_time": "0:15:24"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 50, "loss": 2.0049, "lr": 1.2225209339563144e-05, "epoch": 0.026221692491060787, "percentage": 44.0, "elapsed_time": "0:11:41", "remaining_time": "0:14:52"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 50, "loss": 2.02, "lr": 1.1595998950333794e-05, "epoch": 0.027413587604290822, "percentage": 46.0, "elapsed_time": "0:12:12", "remaining_time": "0:14:20"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 50, "loss": 2.0122, "lr": 1.0960230259076819e-05, "epoch": 0.028605482717520857, "percentage": 48.0, "elapsed_time": "0:12:44", "remaining_time": "0:13:48"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 50, "loss": 2.0194, "lr": 1.0320515775716556e-05, "epoch": 0.029797377830750895, "percentage": 50.0, "elapsed_time": "0:13:16", "remaining_time": "0:13:16"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 50, "loss": 2.0244, "lr": 9.67948422428345e-06, "epoch": 0.03098927294398093, "percentage": 52.0, "elapsed_time": "0:13:48", "remaining_time": "0:12:44"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 50, "loss": 2.0301, "lr": 9.039769740923183e-06, "epoch": 0.03218116805721097, "percentage": 54.0, "elapsed_time": "0:14:19", "remaining_time": "0:12:12"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 50, "loss": 2.039, "lr": 8.404001049666211e-06, "epoch": 0.033373063170441, "percentage": 56.0, "elapsed_time": "0:14:51", "remaining_time": "0:11:40"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 50, "loss": 2.0065, "lr": 7.774790660436857e-06, "epoch": 0.03456495828367104, "percentage": 58.0, "elapsed_time": "0:15:23", "remaining_time": "0:11:08"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 50, "loss": 1.9824, "lr": 7.154724133689677e-06, "epoch": 0.03575685339690107, "percentage": 60.0, "elapsed_time": "0:15:55", "remaining_time": "0:10:36"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 50, "loss": 2.0211, "lr": 6.546349455786926e-06, "epoch": 0.03694874851013111, "percentage": 62.0, "elapsed_time": "0:16:26", "remaining_time": "0:10:04"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 50, "loss": 2.0364, "lr": 5.952166568776062e-06, "epoch": 0.03814064362336114, "percentage": 64.0, "elapsed_time": "0:16:58", "remaining_time": "0:09:32"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 50, "loss": 2.0124, "lr": 5.37461709759165e-06, "epoch": 0.03933253873659118, "percentage": 66.0, "elapsed_time": "0:17:30", "remaining_time": "0:09:01"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 50, "loss": 2.0512, "lr": 4.81607431689475e-06, "epoch": 0.04052443384982122, "percentage": 68.0, "elapsed_time": "0:18:02", "remaining_time": "0:08:29"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 50, "loss": 2.0375, "lr": 4.278833398778306e-06, "epoch": 0.041716328963051254, "percentage": 70.0, "elapsed_time": "0:18:33", "remaining_time": "0:07:57"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 50, "loss": 2.0665, "lr": 3.7651019814126656e-06, "epoch": 0.04290822407628129, "percentage": 72.0, "elapsed_time": "0:19:05", "remaining_time": "0:07:25"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 50, "loss": 2.0289, "lr": 3.2769910973868314e-06, "epoch": 0.04410011918951132, "percentage": 74.0, "elapsed_time": "0:19:37", "remaining_time": "0:06:53"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 50, "loss": 2.0451, "lr": 2.8165064990227255e-06, "epoch": 0.04529201430274136, "percentage": 76.0, "elapsed_time": "0:20:09", "remaining_time": "0:06:21"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 50, "loss": 2.0445, "lr": 2.3855404163086558e-06, "epoch": 0.04648390941597139, "percentage": 78.0, "elapsed_time": "0:20:40", "remaining_time": "0:05:49"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 50, "loss": 2.0017, "lr": 1.9858637813204352e-06, "epoch": 0.04767580452920143, "percentage": 80.0, "elapsed_time": "0:21:12", "remaining_time": "0:05:18"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 50, "loss": 2.0239, "lr": 1.6191189510815942e-06, "epoch": 0.04886769964243146, "percentage": 82.0, "elapsed_time": "0:21:44", "remaining_time": "0:04:46"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 50, "loss": 1.9878, "lr": 1.286812958766106e-06, "epoch": 0.050059594755661505, "percentage": 84.0, "elapsed_time": "0:22:15", "remaining_time": "0:04:14"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 50, "loss": 2.0205, "lr": 9.903113209758098e-07, "epoch": 0.05125148986889154, "percentage": 86.0, "elapsed_time": "0:22:47", "remaining_time": "0:03:42"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 50, "loss": 2.0377, "lr": 7.308324265397837e-07, "epoch": 0.052443384982121574, "percentage": 88.0, "elapsed_time": "0:23:19", "remaining_time": "0:03:10"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 50, "loss": 2.034, "lr": 5.094425298933136e-07, "epoch": 0.05363528009535161, "percentage": 90.0, "elapsed_time": "0:23:51", "remaining_time": "0:02:39"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 50, "loss": 2.0496, "lr": 3.2705136960970554e-07, "epoch": 0.054827175208581644, "percentage": 92.0, "elapsed_time": "0:24:22", "remaining_time": "0:02:07"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 50, "loss": 2.0299, "lr": 1.844084300893456e-07, "epoch": 0.05601907032181168, "percentage": 94.0, "elapsed_time": "0:24:54", "remaining_time": "0:01:35"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 50, "loss": 2.0317, "lr": 8.209986176753947e-08, "epoch": 0.057210965435041714, "percentage": 96.0, "elapsed_time": "0:25:26", "remaining_time": "0:01:03"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 50, "loss": 2.0296, "lr": 2.054607249663665e-08, "epoch": 0.058402860548271755, "percentage": 98.0, "elapsed_time": "0:25:58", "remaining_time": "0:00:31"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 50, "loss": 2.068, "lr": 0.0, "epoch": 0.05959475566150179, "percentage": 100.0, "elapsed_time": "0:26:29", "remaining_time": "0:00:00"}
|
| 51 |
+
{"current_steps": 50, "total_steps": 50, "epoch": 0.05959475566150179, "percentage": 100.0, "elapsed_time": "0:26:37", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,392 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.05959475566150179,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 50,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0011918951132300357,
|
| 13 |
+
"grad_norm": 3.1771470700380333,
|
| 14 |
+
"learning_rate": 2e-05,
|
| 15 |
+
"loss": 2.1431,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0023837902264600714,
|
| 20 |
+
"grad_norm": 3.1161312627163005,
|
| 21 |
+
"learning_rate": 1.9979453927503366e-05,
|
| 22 |
+
"loss": 2.138,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.003575685339690107,
|
| 27 |
+
"grad_norm": 1.264785017261071,
|
| 28 |
+
"learning_rate": 1.991790013823246e-05,
|
| 29 |
+
"loss": 2.0438,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.004767580452920143,
|
| 34 |
+
"grad_norm": 3.409228751017024,
|
| 35 |
+
"learning_rate": 1.9815591569910654e-05,
|
| 36 |
+
"loss": 2.0838,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0059594755661501785,
|
| 41 |
+
"grad_norm": 2.7305256748776907,
|
| 42 |
+
"learning_rate": 1.9672948630390296e-05,
|
| 43 |
+
"loss": 2.0696,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.007151370679380214,
|
| 48 |
+
"grad_norm": 1.8763103868114503,
|
| 49 |
+
"learning_rate": 1.949055747010669e-05,
|
| 50 |
+
"loss": 2.0977,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.00834326579261025,
|
| 55 |
+
"grad_norm": 1.5468453869545318,
|
| 56 |
+
"learning_rate": 1.926916757346022e-05,
|
| 57 |
+
"loss": 2.0518,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.009535160905840286,
|
| 62 |
+
"grad_norm": 1.0642293866767805,
|
| 63 |
+
"learning_rate": 1.900968867902419e-05,
|
| 64 |
+
"loss": 2.0096,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.010727056019070322,
|
| 69 |
+
"grad_norm": 0.780500699075983,
|
| 70 |
+
"learning_rate": 1.8713187041233896e-05,
|
| 71 |
+
"loss": 2.0271,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.011918951132300357,
|
| 76 |
+
"grad_norm": 0.764005329228154,
|
| 77 |
+
"learning_rate": 1.8380881048918406e-05,
|
| 78 |
+
"loss": 2.0058,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.013110846245530394,
|
| 83 |
+
"grad_norm": 0.6241582333904159,
|
| 84 |
+
"learning_rate": 1.8014136218679566e-05,
|
| 85 |
+
"loss": 2.01,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.014302741358760428,
|
| 90 |
+
"grad_norm": 0.5902053742685855,
|
| 91 |
+
"learning_rate": 1.7614459583691346e-05,
|
| 92 |
+
"loss": 2.0019,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.015494636471990465,
|
| 97 |
+
"grad_norm": 0.6425310694189268,
|
| 98 |
+
"learning_rate": 1.7183493500977277e-05,
|
| 99 |
+
"loss": 1.9932,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.0166865315852205,
|
| 104 |
+
"grad_norm": 0.5309446367223852,
|
| 105 |
+
"learning_rate": 1.672300890261317e-05,
|
| 106 |
+
"loss": 1.9988,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.017878426698450536,
|
| 111 |
+
"grad_norm": 0.5138876585539982,
|
| 112 |
+
"learning_rate": 1.6234898018587336e-05,
|
| 113 |
+
"loss": 2.0101,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.01907032181168057,
|
| 118 |
+
"grad_norm": 0.5392570440013659,
|
| 119 |
+
"learning_rate": 1.5721166601221697e-05,
|
| 120 |
+
"loss": 1.9911,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.02026221692491061,
|
| 125 |
+
"grad_norm": 0.5029299842352577,
|
| 126 |
+
"learning_rate": 1.5183925683105254e-05,
|
| 127 |
+
"loss": 2.0116,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.021454112038140644,
|
| 132 |
+
"grad_norm": 0.43594035780610685,
|
| 133 |
+
"learning_rate": 1.4625382902408356e-05,
|
| 134 |
+
"loss": 2.0073,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.02264600715137068,
|
| 139 |
+
"grad_norm": 0.41696447792308583,
|
| 140 |
+
"learning_rate": 1.4047833431223938e-05,
|
| 141 |
+
"loss": 2.0208,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.023837902264600714,
|
| 146 |
+
"grad_norm": 0.3892062305227489,
|
| 147 |
+
"learning_rate": 1.3453650544213078e-05,
|
| 148 |
+
"loss": 2.031,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.025029797377830752,
|
| 153 |
+
"grad_norm": 0.3632073887411339,
|
| 154 |
+
"learning_rate": 1.2845275866310325e-05,
|
| 155 |
+
"loss": 1.9957,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.026221692491060787,
|
| 160 |
+
"grad_norm": 0.33796099940642593,
|
| 161 |
+
"learning_rate": 1.2225209339563144e-05,
|
| 162 |
+
"loss": 2.0049,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.027413587604290822,
|
| 167 |
+
"grad_norm": 0.32832752521945185,
|
| 168 |
+
"learning_rate": 1.1595998950333794e-05,
|
| 169 |
+
"loss": 2.02,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.028605482717520857,
|
| 174 |
+
"grad_norm": 0.31678859599430514,
|
| 175 |
+
"learning_rate": 1.0960230259076819e-05,
|
| 176 |
+
"loss": 2.0122,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.029797377830750895,
|
| 181 |
+
"grad_norm": 0.3054795643275271,
|
| 182 |
+
"learning_rate": 1.0320515775716556e-05,
|
| 183 |
+
"loss": 2.0194,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.03098927294398093,
|
| 188 |
+
"grad_norm": 0.30476969314662167,
|
| 189 |
+
"learning_rate": 9.67948422428345e-06,
|
| 190 |
+
"loss": 2.0244,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.03218116805721097,
|
| 195 |
+
"grad_norm": 0.3397762952406562,
|
| 196 |
+
"learning_rate": 9.039769740923183e-06,
|
| 197 |
+
"loss": 2.0301,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.033373063170441,
|
| 202 |
+
"grad_norm": 0.28294935774392,
|
| 203 |
+
"learning_rate": 8.404001049666211e-06,
|
| 204 |
+
"loss": 2.039,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.03456495828367104,
|
| 209 |
+
"grad_norm": 0.2677495861482238,
|
| 210 |
+
"learning_rate": 7.774790660436857e-06,
|
| 211 |
+
"loss": 2.0065,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.03575685339690107,
|
| 216 |
+
"grad_norm": 0.2523404664659208,
|
| 217 |
+
"learning_rate": 7.154724133689677e-06,
|
| 218 |
+
"loss": 1.9824,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.03694874851013111,
|
| 223 |
+
"grad_norm": 0.2677420506485163,
|
| 224 |
+
"learning_rate": 6.546349455786926e-06,
|
| 225 |
+
"loss": 2.0211,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.03814064362336114,
|
| 230 |
+
"grad_norm": 0.25403279083921193,
|
| 231 |
+
"learning_rate": 5.952166568776062e-06,
|
| 232 |
+
"loss": 2.0364,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.03933253873659118,
|
| 237 |
+
"grad_norm": 0.23827255140088083,
|
| 238 |
+
"learning_rate": 5.37461709759165e-06,
|
| 239 |
+
"loss": 2.0124,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.04052443384982122,
|
| 244 |
+
"grad_norm": 0.21241476817661348,
|
| 245 |
+
"learning_rate": 4.81607431689475e-06,
|
| 246 |
+
"loss": 2.0512,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.041716328963051254,
|
| 251 |
+
"grad_norm": 0.209552693603396,
|
| 252 |
+
"learning_rate": 4.278833398778306e-06,
|
| 253 |
+
"loss": 2.0375,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.04290822407628129,
|
| 258 |
+
"grad_norm": 0.21360560735074388,
|
| 259 |
+
"learning_rate": 3.7651019814126656e-06,
|
| 260 |
+
"loss": 2.0665,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.04410011918951132,
|
| 265 |
+
"grad_norm": 0.2182223081631352,
|
| 266 |
+
"learning_rate": 3.2769910973868314e-06,
|
| 267 |
+
"loss": 2.0289,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.04529201430274136,
|
| 272 |
+
"grad_norm": 0.21248420749052188,
|
| 273 |
+
"learning_rate": 2.8165064990227255e-06,
|
| 274 |
+
"loss": 2.0451,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.04648390941597139,
|
| 279 |
+
"grad_norm": 0.20688489883738986,
|
| 280 |
+
"learning_rate": 2.3855404163086558e-06,
|
| 281 |
+
"loss": 2.0445,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.04767580452920143,
|
| 286 |
+
"grad_norm": 0.20278373082128726,
|
| 287 |
+
"learning_rate": 1.9858637813204352e-06,
|
| 288 |
+
"loss": 2.0017,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.04886769964243146,
|
| 293 |
+
"grad_norm": 0.20097941188780546,
|
| 294 |
+
"learning_rate": 1.6191189510815942e-06,
|
| 295 |
+
"loss": 2.0239,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.050059594755661505,
|
| 300 |
+
"grad_norm": 0.19492229623743026,
|
| 301 |
+
"learning_rate": 1.286812958766106e-06,
|
| 302 |
+
"loss": 1.9878,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.05125148986889154,
|
| 307 |
+
"grad_norm": 0.19191563010483195,
|
| 308 |
+
"learning_rate": 9.903113209758098e-07,
|
| 309 |
+
"loss": 2.0205,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.052443384982121574,
|
| 314 |
+
"grad_norm": 0.18895682704532601,
|
| 315 |
+
"learning_rate": 7.308324265397837e-07,
|
| 316 |
+
"loss": 2.0377,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.05363528009535161,
|
| 321 |
+
"grad_norm": 0.2270168441556834,
|
| 322 |
+
"learning_rate": 5.094425298933136e-07,
|
| 323 |
+
"loss": 2.034,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.054827175208581644,
|
| 328 |
+
"grad_norm": 0.1944028112406021,
|
| 329 |
+
"learning_rate": 3.2705136960970554e-07,
|
| 330 |
+
"loss": 2.0496,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.05601907032181168,
|
| 335 |
+
"grad_norm": 0.18999114531888883,
|
| 336 |
+
"learning_rate": 1.844084300893456e-07,
|
| 337 |
+
"loss": 2.0299,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.057210965435041714,
|
| 342 |
+
"grad_norm": 0.19083668329491307,
|
| 343 |
+
"learning_rate": 8.209986176753947e-08,
|
| 344 |
+
"loss": 2.0317,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.058402860548271755,
|
| 349 |
+
"grad_norm": 0.19161290816553783,
|
| 350 |
+
"learning_rate": 2.054607249663665e-08,
|
| 351 |
+
"loss": 2.0296,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.05959475566150179,
|
| 356 |
+
"grad_norm": 0.19193914325325095,
|
| 357 |
+
"learning_rate": 0.0,
|
| 358 |
+
"loss": 2.068,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.05959475566150179,
|
| 363 |
+
"step": 50,
|
| 364 |
+
"total_flos": 106890730143744.0,
|
| 365 |
+
"train_loss": 2.030773923397064,
|
| 366 |
+
"train_runtime": 1597.0722,
|
| 367 |
+
"train_samples_per_second": 58.106,
|
| 368 |
+
"train_steps_per_second": 0.031
|
| 369 |
+
}
|
| 370 |
+
],
|
| 371 |
+
"logging_steps": 1,
|
| 372 |
+
"max_steps": 50,
|
| 373 |
+
"num_input_tokens_seen": 0,
|
| 374 |
+
"num_train_epochs": 1,
|
| 375 |
+
"save_steps": 50,
|
| 376 |
+
"stateful_callbacks": {
|
| 377 |
+
"TrainerControl": {
|
| 378 |
+
"args": {
|
| 379 |
+
"should_epoch_stop": false,
|
| 380 |
+
"should_evaluate": false,
|
| 381 |
+
"should_log": false,
|
| 382 |
+
"should_save": true,
|
| 383 |
+
"should_training_stop": true
|
| 384 |
+
},
|
| 385 |
+
"attributes": {}
|
| 386 |
+
}
|
| 387 |
+
},
|
| 388 |
+
"total_flos": 106890730143744.0,
|
| 389 |
+
"train_batch_size": 58,
|
| 390 |
+
"trial_name": null,
|
| 391 |
+
"trial_params": null
|
| 392 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13968be49a7e025e2cb7acb0ceca624837fd0d70af3f67bd9257fae94dc374ae
|
| 3 |
+
size 7224
|
training_loss.png
ADDED
|