Upload folder using huggingface_hub
Browse files- 11_128_e3_3e-5/README.md +63 -0
- 11_128_e3_3e-5/adapter_config.json +39 -0
- 11_128_e3_3e-5/adapter_model.safetensors +3 -0
- 11_128_e3_3e-5/all_results.json +9 -0
- 11_128_e3_3e-5/config.json +32 -0
- 11_128_e3_3e-5/merges.txt +0 -0
- 11_128_e3_3e-5/special_tokens_map.json +45 -0
- 11_128_e3_3e-5/tokenizer.json +0 -0
- 11_128_e3_3e-5/tokenizer_config.json +188 -0
- 11_128_e3_3e-5/train_results.json +9 -0
- 11_128_e3_3e-5/trainer_state.json +1618 -0
- 11_128_e3_3e-5/training_args.bin +3 -0
- 11_128_e3_3e-5/vocab.json +0 -0
11_128_e3_3e-5/README.md
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: ibm-granite/granite-3.3-8b-base
|
| 5 |
+
tags:
|
| 6 |
+
- alignment-handbook
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- data/knowledge_lora_training_data_2000
|
| 10 |
+
model-index:
|
| 11 |
+
- name: 11_128_e3_3e-5
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# 11_128_e3_3e-5
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [ibm-granite/granite-3.3-8b-base](https://huggingface.co/ibm-granite/granite-3.3-8b-base) on the data/knowledge_lora_training_data_2000 dataset.
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
+
- train_batch_size: 2
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 8
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 32
|
| 47 |
+
- total_eval_batch_size: 64
|
| 48 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 51 |
+
- num_epochs: 3.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
### Framework versions
|
| 58 |
+
|
| 59 |
+
- PEFT 0.15.2
|
| 60 |
+
- Transformers 4.52.4
|
| 61 |
+
- Pytorch 2.7.0+cu126
|
| 62 |
+
- Datasets 3.6.0
|
| 63 |
+
- Tokenizers 0.21.2
|
11_128_e3_3e-5/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 256,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 128,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"down_proj",
|
| 28 |
+
"q_proj",
|
| 29 |
+
"gate_proj",
|
| 30 |
+
"o_proj",
|
| 31 |
+
"up_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"v_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
11_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a3dc70c45d4cf86b8b63395ef00871c0be26bc17f9a412a369d080f25e8a2ee
|
| 3 |
+
size 791751704
|
11_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.6050721755748106e+18,
|
| 4 |
+
"train_loss": 0.5690460730658637,
|
| 5 |
+
"train_runtime": 738.6249,
|
| 6 |
+
"train_samples": 11979,
|
| 7 |
+
"train_samples_per_second": 48.654,
|
| 8 |
+
"train_steps_per_second": 1.523
|
| 9 |
+
}
|
11_128_e3_3e-5/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"GraniteForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0,
|
| 7 |
+
"attention_multiplier": 0.0078125,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"embedding_multiplier": 12.0,
|
| 10 |
+
"eos_token_id": 0,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 12800,
|
| 15 |
+
"logits_scaling": 16.0,
|
| 16 |
+
"max_position_embeddings": 131072,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "granite",
|
| 19 |
+
"num_attention_heads": 32,
|
| 20 |
+
"num_hidden_layers": 40,
|
| 21 |
+
"num_key_value_heads": 8,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"residual_multiplier": 0.22,
|
| 24 |
+
"rms_norm_eps": 1e-05,
|
| 25 |
+
"rope_scaling": null,
|
| 26 |
+
"rope_theta": 10000000.0,
|
| 27 |
+
"tie_word_embeddings": true,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.52.4",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49152
|
| 32 |
+
}
|
11_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
11_128_e3_3e-5/special_tokens_map.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"pad_token": "<reponame>",
|
| 38 |
+
"unk_token": {
|
| 39 |
+
"content": "<|endoftext|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
}
|
| 45 |
+
}
|
11_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
11_128_e3_3e-5/tokenizer_config.json
ADDED
|
@@ -0,0 +1,188 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<filename>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<gh_stars>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<empty_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<commit_before>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<commit_msg>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<commit_after>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<reponame>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
}
|
| 156 |
+
},
|
| 157 |
+
"additional_special_tokens": [
|
| 158 |
+
"<|endoftext|>",
|
| 159 |
+
"<fim_prefix>",
|
| 160 |
+
"<fim_middle>",
|
| 161 |
+
"<fim_suffix>",
|
| 162 |
+
"<fim_pad>",
|
| 163 |
+
"<filename>",
|
| 164 |
+
"<gh_stars>",
|
| 165 |
+
"<issue_start>",
|
| 166 |
+
"<issue_comment>",
|
| 167 |
+
"<issue_closed>",
|
| 168 |
+
"<jupyter_start>",
|
| 169 |
+
"<jupyter_text>",
|
| 170 |
+
"<jupyter_code>",
|
| 171 |
+
"<jupyter_output>",
|
| 172 |
+
"<empty_output>",
|
| 173 |
+
"<commit_before>",
|
| 174 |
+
"<commit_msg>",
|
| 175 |
+
"<commit_after>",
|
| 176 |
+
"<reponame>"
|
| 177 |
+
],
|
| 178 |
+
"bos_token": "<|endoftext|>",
|
| 179 |
+
"clean_up_tokenization_spaces": true,
|
| 180 |
+
"eos_token": "<|endoftext|>",
|
| 181 |
+
"extra_special_tokens": {},
|
| 182 |
+
"model_max_length": 8192,
|
| 183 |
+
"pad_token": "<reponame>",
|
| 184 |
+
"padding_side": "left",
|
| 185 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 186 |
+
"unk_token": "<|endoftext|>",
|
| 187 |
+
"vocab_size": 49152
|
| 188 |
+
}
|
11_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.6050721755748106e+18,
|
| 4 |
+
"train_loss": 0.5690460730658637,
|
| 5 |
+
"train_runtime": 738.6249,
|
| 6 |
+
"train_samples": 11979,
|
| 7 |
+
"train_samples_per_second": 48.654,
|
| 8 |
+
"train_steps_per_second": 1.523
|
| 9 |
+
}
|
11_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1618 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1125,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01335113484646195,
|
| 14 |
+
"grad_norm": 1.0486401319503784,
|
| 15 |
+
"learning_rate": 2.1052631578947366e-06,
|
| 16 |
+
"loss": 1.303,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0267022696929239,
|
| 21 |
+
"grad_norm": 0.7367771863937378,
|
| 22 |
+
"learning_rate": 4.736842105263158e-06,
|
| 23 |
+
"loss": 1.2698,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04005340453938585,
|
| 28 |
+
"grad_norm": 0.63253253698349,
|
| 29 |
+
"learning_rate": 7.3684210526315784e-06,
|
| 30 |
+
"loss": 1.3144,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0534045393858478,
|
| 35 |
+
"grad_norm": 0.5439664125442505,
|
| 36 |
+
"learning_rate": 9.999999999999999e-06,
|
| 37 |
+
"loss": 1.3013,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.06675567423230974,
|
| 42 |
+
"grad_norm": 0.7603079080581665,
|
| 43 |
+
"learning_rate": 1.263157894736842e-05,
|
| 44 |
+
"loss": 1.2448,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.0801068090787717,
|
| 49 |
+
"grad_norm": 0.48528000712394714,
|
| 50 |
+
"learning_rate": 1.5263157894736842e-05,
|
| 51 |
+
"loss": 1.1948,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09345794392523364,
|
| 56 |
+
"grad_norm": 0.466791570186615,
|
| 57 |
+
"learning_rate": 1.7894736842105264e-05,
|
| 58 |
+
"loss": 1.2206,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1068090787716956,
|
| 63 |
+
"grad_norm": 0.7093009352684021,
|
| 64 |
+
"learning_rate": 2.0526315789473685e-05,
|
| 65 |
+
"loss": 1.1996,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12016021361815754,
|
| 70 |
+
"grad_norm": 0.4372748136520386,
|
| 71 |
+
"learning_rate": 2.3157894736842103e-05,
|
| 72 |
+
"loss": 1.1616,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.13351134846461948,
|
| 77 |
+
"grad_norm": 1.0817705392837524,
|
| 78 |
+
"learning_rate": 2.578947368421053e-05,
|
| 79 |
+
"loss": 1.1628,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.14686248331108145,
|
| 84 |
+
"grad_norm": 0.5496600866317749,
|
| 85 |
+
"learning_rate": 2.8421052631578946e-05,
|
| 86 |
+
"loss": 1.1774,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.1602136181575434,
|
| 91 |
+
"grad_norm": 0.41005897521972656,
|
| 92 |
+
"learning_rate": 2.9999740416405374e-05,
|
| 93 |
+
"loss": 1.1697,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.17356475300400534,
|
| 98 |
+
"grad_norm": 0.4476589560508728,
|
| 99 |
+
"learning_rate": 2.9996820204146065e-05,
|
| 100 |
+
"loss": 1.1776,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.18691588785046728,
|
| 105 |
+
"grad_norm": 0.454683780670166,
|
| 106 |
+
"learning_rate": 2.9990655933929675e-05,
|
| 107 |
+
"loss": 1.1209,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.20026702269692923,
|
| 112 |
+
"grad_norm": 0.5272197127342224,
|
| 113 |
+
"learning_rate": 2.998124893918886e-05,
|
| 114 |
+
"loss": 1.1374,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.2136181575433912,
|
| 119 |
+
"grad_norm": 0.4725058078765869,
|
| 120 |
+
"learning_rate": 2.9968601254810732e-05,
|
| 121 |
+
"loss": 1.1118,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.22696929238985314,
|
| 126 |
+
"grad_norm": 0.4944089651107788,
|
| 127 |
+
"learning_rate": 2.995271561669667e-05,
|
| 128 |
+
"loss": 1.0628,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.24032042723631508,
|
| 133 |
+
"grad_norm": 0.5687285661697388,
|
| 134 |
+
"learning_rate": 2.993359546117052e-05,
|
| 135 |
+
"loss": 1.1098,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.253671562082777,
|
| 140 |
+
"grad_norm": 0.4798280894756317,
|
| 141 |
+
"learning_rate": 2.9911244924235226e-05,
|
| 142 |
+
"loss": 1.128,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.26702269692923897,
|
| 147 |
+
"grad_norm": 0.4693334996700287,
|
| 148 |
+
"learning_rate": 2.9885668840678184e-05,
|
| 149 |
+
"loss": 1.095,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2803738317757009,
|
| 154 |
+
"grad_norm": 0.5227109789848328,
|
| 155 |
+
"learning_rate": 2.985687274302537e-05,
|
| 156 |
+
"loss": 1.091,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.2937249666221629,
|
| 161 |
+
"grad_norm": 0.5313762426376343,
|
| 162 |
+
"learning_rate": 2.982486286034458e-05,
|
| 163 |
+
"loss": 1.0718,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.30707610146862485,
|
| 168 |
+
"grad_norm": 0.6038285493850708,
|
| 169 |
+
"learning_rate": 2.9789646116897966e-05,
|
| 170 |
+
"loss": 1.0642,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.3204272363150868,
|
| 175 |
+
"grad_norm": 0.4769440293312073,
|
| 176 |
+
"learning_rate": 2.9751230130644217e-05,
|
| 177 |
+
"loss": 1.0004,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.33377837116154874,
|
| 182 |
+
"grad_norm": 0.6203076839447021,
|
| 183 |
+
"learning_rate": 2.9709623211590674e-05,
|
| 184 |
+
"loss": 1.0546,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.3471295060080107,
|
| 189 |
+
"grad_norm": 0.600827693939209,
|
| 190 |
+
"learning_rate": 2.966483435999572e-05,
|
| 191 |
+
"loss": 1.0104,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.3604806408544726,
|
| 196 |
+
"grad_norm": 0.5806782841682434,
|
| 197 |
+
"learning_rate": 2.9616873264421887e-05,
|
| 198 |
+
"loss": 0.994,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.37383177570093457,
|
| 203 |
+
"grad_norm": 0.6229504346847534,
|
| 204 |
+
"learning_rate": 2.9565750299640078e-05,
|
| 205 |
+
"loss": 1.01,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.3871829105473965,
|
| 210 |
+
"grad_norm": 0.6058214902877808,
|
| 211 |
+
"learning_rate": 2.95114765243853e-05,
|
| 212 |
+
"loss": 0.9863,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.40053404539385845,
|
| 217 |
+
"grad_norm": 0.7894612550735474,
|
| 218 |
+
"learning_rate": 2.9454063678964502e-05,
|
| 219 |
+
"loss": 1.0063,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.41388518024032045,
|
| 224 |
+
"grad_norm": 0.6172760128974915,
|
| 225 |
+
"learning_rate": 2.9393524182716958e-05,
|
| 226 |
+
"loss": 0.9752,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.4272363150867824,
|
| 231 |
+
"grad_norm": 0.6282286643981934,
|
| 232 |
+
"learning_rate": 2.9329871131327735e-05,
|
| 233 |
+
"loss": 0.9667,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.44058744993324434,
|
| 238 |
+
"grad_norm": 0.6341790556907654,
|
| 239 |
+
"learning_rate": 2.9263118293994908e-05,
|
| 240 |
+
"loss": 0.9255,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.4539385847797063,
|
| 245 |
+
"grad_norm": 0.8160889148712158,
|
| 246 |
+
"learning_rate": 2.9193280110451042e-05,
|
| 247 |
+
"loss": 0.9062,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4672897196261682,
|
| 252 |
+
"grad_norm": 0.6840095520019531,
|
| 253 |
+
"learning_rate": 2.9120371687839658e-05,
|
| 254 |
+
"loss": 0.9824,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.48064085447263016,
|
| 259 |
+
"grad_norm": 0.7107115387916565,
|
| 260 |
+
"learning_rate": 2.9044408797447277e-05,
|
| 261 |
+
"loss": 0.905,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.4939919893190921,
|
| 266 |
+
"grad_norm": 0.6693159937858582,
|
| 267 |
+
"learning_rate": 2.896540787129187e-05,
|
| 268 |
+
"loss": 0.9536,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.507343124165554,
|
| 273 |
+
"grad_norm": 0.9424569606781006,
|
| 274 |
+
"learning_rate": 2.8883385998568318e-05,
|
| 275 |
+
"loss": 0.9017,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.520694259012016,
|
| 280 |
+
"grad_norm": 0.7033911943435669,
|
| 281 |
+
"learning_rate": 2.879836092195175e-05,
|
| 282 |
+
"loss": 0.88,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5340453938584779,
|
| 287 |
+
"grad_norm": 0.7161537408828735,
|
| 288 |
+
"learning_rate": 2.871035103375952e-05,
|
| 289 |
+
"loss": 0.8537,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5473965287049399,
|
| 294 |
+
"grad_norm": 0.8812773823738098,
|
| 295 |
+
"learning_rate": 2.8619375371972615e-05,
|
| 296 |
+
"loss": 0.8983,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5607476635514018,
|
| 301 |
+
"grad_norm": 0.7930803298950195,
|
| 302 |
+
"learning_rate": 2.852545361611747e-05,
|
| 303 |
+
"loss": 0.8832,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.5740987983978638,
|
| 308 |
+
"grad_norm": 0.8224268555641174,
|
| 309 |
+
"learning_rate": 2.8428606083008928e-05,
|
| 310 |
+
"loss": 0.876,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.5874499332443258,
|
| 315 |
+
"grad_norm": 0.715986430644989,
|
| 316 |
+
"learning_rate": 2.8328853722355404e-05,
|
| 317 |
+
"loss": 0.8838,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6008010680907877,
|
| 322 |
+
"grad_norm": 0.8471271991729736,
|
| 323 |
+
"learning_rate": 2.8226218112227115e-05,
|
| 324 |
+
"loss": 0.8124,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.6141522029372497,
|
| 329 |
+
"grad_norm": 0.8807353973388672,
|
| 330 |
+
"learning_rate": 2.8120721454388376e-05,
|
| 331 |
+
"loss": 0.8633,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.6275033377837116,
|
| 336 |
+
"grad_norm": 1.0916754007339478,
|
| 337 |
+
"learning_rate": 2.8012386569495007e-05,
|
| 338 |
+
"loss": 0.8131,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.6408544726301736,
|
| 343 |
+
"grad_norm": 0.8828428387641907,
|
| 344 |
+
"learning_rate": 2.7901236892157863e-05,
|
| 345 |
+
"loss": 0.8006,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6542056074766355,
|
| 350 |
+
"grad_norm": 0.8380167484283447,
|
| 351 |
+
"learning_rate": 2.77872964658735e-05,
|
| 352 |
+
"loss": 0.8485,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.6675567423230975,
|
| 357 |
+
"grad_norm": 0.7838460803031921,
|
| 358 |
+
"learning_rate": 2.767058993782323e-05,
|
| 359 |
+
"loss": 0.8458,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.6809078771695594,
|
| 364 |
+
"grad_norm": 1.0507323741912842,
|
| 365 |
+
"learning_rate": 2.7551142553541496e-05,
|
| 366 |
+
"loss": 0.8023,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.6942590120160214,
|
| 371 |
+
"grad_norm": 0.8333808183670044,
|
| 372 |
+
"learning_rate": 2.742898015145485e-05,
|
| 373 |
+
"loss": 0.8079,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.7076101468624834,
|
| 378 |
+
"grad_norm": 0.917258620262146,
|
| 379 |
+
"learning_rate": 2.7304129157292688e-05,
|
| 380 |
+
"loss": 0.7976,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.7209612817089452,
|
| 385 |
+
"grad_norm": 0.8479587435722351,
|
| 386 |
+
"learning_rate": 2.717661657837094e-05,
|
| 387 |
+
"loss": 0.8222,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.7343124165554072,
|
| 392 |
+
"grad_norm": 0.915801465511322,
|
| 393 |
+
"learning_rate": 2.7046469997749912e-05,
|
| 394 |
+
"loss": 0.7974,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.7476635514018691,
|
| 399 |
+
"grad_norm": 0.8482130765914917,
|
| 400 |
+
"learning_rate": 2.6913717568267665e-05,
|
| 401 |
+
"loss": 0.7986,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7610146862483311,
|
| 406 |
+
"grad_norm": 1.0102380514144897,
|
| 407 |
+
"learning_rate": 2.677838800645005e-05,
|
| 408 |
+
"loss": 0.7897,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.774365821094793,
|
| 413 |
+
"grad_norm": 0.9215638637542725,
|
| 414 |
+
"learning_rate": 2.664051058629888e-05,
|
| 415 |
+
"loss": 0.7266,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.787716955941255,
|
| 420 |
+
"grad_norm": 1.023741364479065,
|
| 421 |
+
"learning_rate": 2.6500115132959478e-05,
|
| 422 |
+
"loss": 0.7288,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.8010680907877169,
|
| 427 |
+
"grad_norm": 1.0353931188583374,
|
| 428 |
+
"learning_rate": 2.6357232016269006e-05,
|
| 429 |
+
"loss": 0.7595,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.8144192256341789,
|
| 434 |
+
"grad_norm": 0.924623429775238,
|
| 435 |
+
"learning_rate": 2.621189214418697e-05,
|
| 436 |
+
"loss": 0.8017,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.8277703604806409,
|
| 441 |
+
"grad_norm": 0.9015868902206421,
|
| 442 |
+
"learning_rate": 2.606412695610933e-05,
|
| 443 |
+
"loss": 0.7682,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.8411214953271028,
|
| 448 |
+
"grad_norm": 1.0143524408340454,
|
| 449 |
+
"learning_rate": 2.5913968416067644e-05,
|
| 450 |
+
"loss": 0.7319,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.8544726301735648,
|
| 455 |
+
"grad_norm": 0.9672964215278625,
|
| 456 |
+
"learning_rate": 2.57614490058147e-05,
|
| 457 |
+
"loss": 0.6988,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.8678237650200267,
|
| 462 |
+
"grad_norm": 0.9396893382072449,
|
| 463 |
+
"learning_rate": 2.5606601717798212e-05,
|
| 464 |
+
"loss": 0.7167,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.8811748998664887,
|
| 469 |
+
"grad_norm": 0.9486520886421204,
|
| 470 |
+
"learning_rate": 2.5449460048024005e-05,
|
| 471 |
+
"loss": 0.7362,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.8945260347129506,
|
| 476 |
+
"grad_norm": 0.9320957660675049,
|
| 477 |
+
"learning_rate": 2.5290057988810267e-05,
|
| 478 |
+
"loss": 0.7195,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.9078771695594126,
|
| 483 |
+
"grad_norm": 1.0414938926696777,
|
| 484 |
+
"learning_rate": 2.512843002143446e-05,
|
| 485 |
+
"loss": 0.7003,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.9212283044058746,
|
| 490 |
+
"grad_norm": 1.0145341157913208,
|
| 491 |
+
"learning_rate": 2.4964611108674464e-05,
|
| 492 |
+
"loss": 0.7248,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.9345794392523364,
|
| 497 |
+
"grad_norm": 1.0088192224502563,
|
| 498 |
+
"learning_rate": 2.479863668724554e-05,
|
| 499 |
+
"loss": 0.698,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.9479305740987984,
|
| 504 |
+
"grad_norm": 1.2435886859893799,
|
| 505 |
+
"learning_rate": 2.4630542660134808e-05,
|
| 506 |
+
"loss": 0.6839,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.9612817089452603,
|
| 511 |
+
"grad_norm": 1.001948595046997,
|
| 512 |
+
"learning_rate": 2.4460365388834816e-05,
|
| 513 |
+
"loss": 0.6943,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.9746328437917223,
|
| 518 |
+
"grad_norm": 0.931431770324707,
|
| 519 |
+
"learning_rate": 2.428814168547798e-05,
|
| 520 |
+
"loss": 0.6714,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.9879839786381842,
|
| 525 |
+
"grad_norm": 0.9906545281410217,
|
| 526 |
+
"learning_rate": 2.4113908804873486e-05,
|
| 527 |
+
"loss": 0.678,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.0,
|
| 532 |
+
"grad_norm": 1.43329656124115,
|
| 533 |
+
"learning_rate": 2.3937704436448502e-05,
|
| 534 |
+
"loss": 0.6953,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.0133511348464619,
|
| 539 |
+
"grad_norm": 1.1846697330474854,
|
| 540 |
+
"learning_rate": 2.3759566696095304e-05,
|
| 541 |
+
"loss": 0.6101,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.026702269692924,
|
| 546 |
+
"grad_norm": 1.0284260511398315,
|
| 547 |
+
"learning_rate": 2.3579534117926214e-05,
|
| 548 |
+
"loss": 0.5942,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.0400534045393859,
|
| 553 |
+
"grad_norm": 0.9567074179649353,
|
| 554 |
+
"learning_rate": 2.3397645645938002e-05,
|
| 555 |
+
"loss": 0.6035,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0534045393858478,
|
| 560 |
+
"grad_norm": 1.0356601476669312,
|
| 561 |
+
"learning_rate": 2.321394062558769e-05,
|
| 562 |
+
"loss": 0.5844,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.0667556742323097,
|
| 567 |
+
"grad_norm": 1.047681450843811,
|
| 568 |
+
"learning_rate": 2.3028458795281487e-05,
|
| 569 |
+
"loss": 0.6087,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0801068090787718,
|
| 574 |
+
"grad_norm": 1.0633341073989868,
|
| 575 |
+
"learning_rate": 2.284124027777871e-05,
|
| 576 |
+
"loss": 0.5566,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0934579439252337,
|
| 581 |
+
"grad_norm": 1.0654174089431763,
|
| 582 |
+
"learning_rate": 2.2652325571512562e-05,
|
| 583 |
+
"loss": 0.5367,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.1068090787716955,
|
| 588 |
+
"grad_norm": 1.0637167692184448,
|
| 589 |
+
"learning_rate": 2.246175554182968e-05,
|
| 590 |
+
"loss": 0.5451,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.1201602136181577,
|
| 595 |
+
"grad_norm": 1.0810866355895996,
|
| 596 |
+
"learning_rate": 2.2269571412150283e-05,
|
| 597 |
+
"loss": 0.5288,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.1335113484646195,
|
| 602 |
+
"grad_norm": 1.1243711709976196,
|
| 603 |
+
"learning_rate": 2.207581475505086e-05,
|
| 604 |
+
"loss": 0.5435,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.1468624833110814,
|
| 609 |
+
"grad_norm": 1.1037837266921997,
|
| 610 |
+
"learning_rate": 2.1880527483271357e-05,
|
| 611 |
+
"loss": 0.5351,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.1602136181575433,
|
| 616 |
+
"grad_norm": 1.0308574438095093,
|
| 617 |
+
"learning_rate": 2.168375184064876e-05,
|
| 618 |
+
"loss": 0.5558,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.1735647530040054,
|
| 623 |
+
"grad_norm": 1.06681489944458,
|
| 624 |
+
"learning_rate": 2.1485530392979047e-05,
|
| 625 |
+
"loss": 0.4981,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1869158878504673,
|
| 630 |
+
"grad_norm": 1.184482455253601,
|
| 631 |
+
"learning_rate": 2.1285906018809524e-05,
|
| 632 |
+
"loss": 0.5584,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.2002670226969292,
|
| 637 |
+
"grad_norm": 1.1062068939208984,
|
| 638 |
+
"learning_rate": 2.1084921900163495e-05,
|
| 639 |
+
"loss": 0.5757,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.213618157543391,
|
| 644 |
+
"grad_norm": 1.1051130294799805,
|
| 645 |
+
"learning_rate": 2.0882621513199265e-05,
|
| 646 |
+
"loss": 0.5721,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.2269692923898532,
|
| 651 |
+
"grad_norm": 1.2227230072021484,
|
| 652 |
+
"learning_rate": 2.0679048618805552e-05,
|
| 653 |
+
"loss": 0.5688,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.240320427236315,
|
| 658 |
+
"grad_norm": 1.0711619853973389,
|
| 659 |
+
"learning_rate": 2.0474247253135284e-05,
|
| 660 |
+
"loss": 0.5223,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.253671562082777,
|
| 665 |
+
"grad_norm": 1.0962611436843872,
|
| 666 |
+
"learning_rate": 2.0268261718079842e-05,
|
| 667 |
+
"loss": 0.5279,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.267022696929239,
|
| 672 |
+
"grad_norm": 1.0452942848205566,
|
| 673 |
+
"learning_rate": 2.0061136571685875e-05,
|
| 674 |
+
"loss": 0.5396,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.280373831775701,
|
| 679 |
+
"grad_norm": 1.0427463054656982,
|
| 680 |
+
"learning_rate": 1.9852916618516622e-05,
|
| 681 |
+
"loss": 0.4792,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2937249666221629,
|
| 686 |
+
"grad_norm": 1.1034791469573975,
|
| 687 |
+
"learning_rate": 1.9643646899959972e-05,
|
| 688 |
+
"loss": 0.4827,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.307076101468625,
|
| 693 |
+
"grad_norm": 1.1174825429916382,
|
| 694 |
+
"learning_rate": 1.9433372684485264e-05,
|
| 695 |
+
"loss": 0.4907,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.3204272363150868,
|
| 700 |
+
"grad_norm": 1.192457914352417,
|
| 701 |
+
"learning_rate": 1.922213945785098e-05,
|
| 702 |
+
"loss": 0.4998,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.3337783711615487,
|
| 707 |
+
"grad_norm": 1.1392796039581299,
|
| 708 |
+
"learning_rate": 1.9009992913265453e-05,
|
| 709 |
+
"loss": 0.5285,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.3471295060080106,
|
| 714 |
+
"grad_norm": 1.0850481986999512,
|
| 715 |
+
"learning_rate": 1.8796978941502626e-05,
|
| 716 |
+
"loss": 0.4779,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.3604806408544725,
|
| 721 |
+
"grad_norm": 1.0928312540054321,
|
| 722 |
+
"learning_rate": 1.8583143620975167e-05,
|
| 723 |
+
"loss": 0.5244,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.3738317757009346,
|
| 728 |
+
"grad_norm": 1.0619415044784546,
|
| 729 |
+
"learning_rate": 1.8368533207766945e-05,
|
| 730 |
+
"loss": 0.4926,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.3871829105473965,
|
| 735 |
+
"grad_norm": 1.1855837106704712,
|
| 736 |
+
"learning_rate": 1.815319412562707e-05,
|
| 737 |
+
"loss": 0.4974,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.4005340453938584,
|
| 742 |
+
"grad_norm": 1.095412015914917,
|
| 743 |
+
"learning_rate": 1.7937172955927677e-05,
|
| 744 |
+
"loss": 0.4981,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.4138851802403205,
|
| 749 |
+
"grad_norm": 1.0880358219146729,
|
| 750 |
+
"learning_rate": 1.7720516427587637e-05,
|
| 751 |
+
"loss": 0.5336,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.4272363150867824,
|
| 756 |
+
"grad_norm": 1.2341724634170532,
|
| 757 |
+
"learning_rate": 1.750327140696429e-05,
|
| 758 |
+
"loss": 0.49,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.4405874499332443,
|
| 763 |
+
"grad_norm": 1.3782603740692139,
|
| 764 |
+
"learning_rate": 1.7285484887715505e-05,
|
| 765 |
+
"loss": 0.4883,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.4539385847797064,
|
| 770 |
+
"grad_norm": 1.278130054473877,
|
| 771 |
+
"learning_rate": 1.7067203980634176e-05,
|
| 772 |
+
"loss": 0.4332,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.4672897196261683,
|
| 777 |
+
"grad_norm": 1.0901286602020264,
|
| 778 |
+
"learning_rate": 1.6848475903457378e-05,
|
| 779 |
+
"loss": 0.4663,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.4806408544726302,
|
| 784 |
+
"grad_norm": 1.0132968425750732,
|
| 785 |
+
"learning_rate": 1.6629347970652434e-05,
|
| 786 |
+
"loss": 0.4861,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.493991989319092,
|
| 791 |
+
"grad_norm": 1.1939258575439453,
|
| 792 |
+
"learning_rate": 1.6409867583181957e-05,
|
| 793 |
+
"loss": 0.4712,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.507343124165554,
|
| 798 |
+
"grad_norm": 1.295768141746521,
|
| 799 |
+
"learning_rate": 1.6190082218250297e-05,
|
| 800 |
+
"loss": 0.4463,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.520694259012016,
|
| 805 |
+
"grad_norm": 1.1621875762939453,
|
| 806 |
+
"learning_rate": 1.5970039419033428e-05,
|
| 807 |
+
"loss": 0.4633,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.534045393858478,
|
| 812 |
+
"grad_norm": 1.2825847864151,
|
| 813 |
+
"learning_rate": 1.574978678439457e-05,
|
| 814 |
+
"loss": 0.4875,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.5473965287049398,
|
| 819 |
+
"grad_norm": 1.1304399967193604,
|
| 820 |
+
"learning_rate": 1.5529371958587788e-05,
|
| 821 |
+
"loss": 0.4707,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.560747663551402,
|
| 826 |
+
"grad_norm": 1.1779073476791382,
|
| 827 |
+
"learning_rate": 1.530884262095176e-05,
|
| 828 |
+
"loss": 0.4643,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.5740987983978638,
|
| 833 |
+
"grad_norm": 1.1478030681610107,
|
| 834 |
+
"learning_rate": 1.5088246475595933e-05,
|
| 835 |
+
"loss": 0.4282,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.5874499332443257,
|
| 840 |
+
"grad_norm": 1.197334885597229,
|
| 841 |
+
"learning_rate": 1.4867631241081384e-05,
|
| 842 |
+
"loss": 0.453,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.6008010680907878,
|
| 847 |
+
"grad_norm": 1.1974467039108276,
|
| 848 |
+
"learning_rate": 1.4647044640098456e-05,
|
| 849 |
+
"loss": 0.4605,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.6141522029372497,
|
| 854 |
+
"grad_norm": 1.12503981590271,
|
| 855 |
+
"learning_rate": 1.4426534389143615e-05,
|
| 856 |
+
"loss": 0.4609,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.6275033377837116,
|
| 861 |
+
"grad_norm": 1.2048460245132446,
|
| 862 |
+
"learning_rate": 1.4206148188197552e-05,
|
| 863 |
+
"loss": 0.4448,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.6408544726301737,
|
| 868 |
+
"grad_norm": 1.1521352529525757,
|
| 869 |
+
"learning_rate": 1.398593371040692e-05,
|
| 870 |
+
"loss": 0.4538,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.6542056074766354,
|
| 875 |
+
"grad_norm": 1.1560252904891968,
|
| 876 |
+
"learning_rate": 1.3765938591771832e-05,
|
| 877 |
+
"loss": 0.4882,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.6675567423230975,
|
| 882 |
+
"grad_norm": 1.1206822395324707,
|
| 883 |
+
"learning_rate": 1.354621042084141e-05,
|
| 884 |
+
"loss": 0.4542,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.6809078771695594,
|
| 889 |
+
"grad_norm": 1.1073603630065918,
|
| 890 |
+
"learning_rate": 1.3326796728419634e-05,
|
| 891 |
+
"loss": 0.4482,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.6942590120160212,
|
| 896 |
+
"grad_norm": 1.3115222454071045,
|
| 897 |
+
"learning_rate": 1.3107744977283614e-05,
|
| 898 |
+
"loss": 0.4188,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.7076101468624834,
|
| 903 |
+
"grad_norm": 1.1150600910186768,
|
| 904 |
+
"learning_rate": 1.2889102551916645e-05,
|
| 905 |
+
"loss": 0.4487,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.7209612817089452,
|
| 910 |
+
"grad_norm": 1.1357851028442383,
|
| 911 |
+
"learning_rate": 1.267091674825813e-05,
|
| 912 |
+
"loss": 0.3953,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.7343124165554071,
|
| 917 |
+
"grad_norm": 1.141181468963623,
|
| 918 |
+
"learning_rate": 1.2453234763472723e-05,
|
| 919 |
+
"loss": 0.4577,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.7476635514018692,
|
| 924 |
+
"grad_norm": 1.2599561214447021,
|
| 925 |
+
"learning_rate": 1.2236103685740808e-05,
|
| 926 |
+
"loss": 0.3862,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.7610146862483311,
|
| 931 |
+
"grad_norm": 1.2928332090377808,
|
| 932 |
+
"learning_rate": 1.2019570484072535e-05,
|
| 933 |
+
"loss": 0.4042,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.774365821094793,
|
| 938 |
+
"grad_norm": 1.0486078262329102,
|
| 939 |
+
"learning_rate": 1.1803681998147677e-05,
|
| 940 |
+
"loss": 0.3993,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.7877169559412551,
|
| 945 |
+
"grad_norm": 1.1684564352035522,
|
| 946 |
+
"learning_rate": 1.1588484928183407e-05,
|
| 947 |
+
"loss": 0.4183,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.8010680907877168,
|
| 952 |
+
"grad_norm": 1.1839678287506104,
|
| 953 |
+
"learning_rate": 1.1374025824832307e-05,
|
| 954 |
+
"loss": 0.3871,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.814419225634179,
|
| 959 |
+
"grad_norm": 1.1706185340881348,
|
| 960 |
+
"learning_rate": 1.11603510791127e-05,
|
| 961 |
+
"loss": 0.411,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.827770360480641,
|
| 966 |
+
"grad_norm": 1.1968703269958496,
|
| 967 |
+
"learning_rate": 1.094750691237347e-05,
|
| 968 |
+
"loss": 0.3979,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.8411214953271027,
|
| 973 |
+
"grad_norm": 1.3668683767318726,
|
| 974 |
+
"learning_rate": 1.0735539366295697e-05,
|
| 975 |
+
"loss": 0.3605,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.8544726301735648,
|
| 980 |
+
"grad_norm": 1.1672745943069458,
|
| 981 |
+
"learning_rate": 1.0524494292933008e-05,
|
| 982 |
+
"loss": 0.3836,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.8678237650200267,
|
| 987 |
+
"grad_norm": 1.2132056951522827,
|
| 988 |
+
"learning_rate": 1.0314417344793088e-05,
|
| 989 |
+
"loss": 0.4161,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.8811748998664886,
|
| 994 |
+
"grad_norm": 1.2260169982910156,
|
| 995 |
+
"learning_rate": 1.0105353964962273e-05,
|
| 996 |
+
"loss": 0.4115,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.8945260347129507,
|
| 1001 |
+
"grad_norm": 1.1670173406600952,
|
| 1002 |
+
"learning_rate": 9.897349377275447e-06,
|
| 1003 |
+
"loss": 0.4081,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.9078771695594126,
|
| 1008 |
+
"grad_norm": 1.2216064929962158,
|
| 1009 |
+
"learning_rate": 9.690448576533427e-06,
|
| 1010 |
+
"loss": 0.4098,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.9212283044058744,
|
| 1015 |
+
"grad_norm": 1.1378860473632812,
|
| 1016 |
+
"learning_rate": 9.484696318769813e-06,
|
| 1017 |
+
"loss": 0.4022,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.9345794392523366,
|
| 1022 |
+
"grad_norm": 1.3526135683059692,
|
| 1023 |
+
"learning_rate": 9.280137111569525e-06,
|
| 1024 |
+
"loss": 0.4077,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.9479305740987984,
|
| 1029 |
+
"grad_norm": 1.1377341747283936,
|
| 1030 |
+
"learning_rate": 9.076815204441133e-06,
|
| 1031 |
+
"loss": 0.3991,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.9612817089452603,
|
| 1036 |
+
"grad_norm": 1.1733932495117188,
|
| 1037 |
+
"learning_rate": 8.874774579244886e-06,
|
| 1038 |
+
"loss": 0.3988,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.9746328437917224,
|
| 1043 |
+
"grad_norm": 1.1890455484390259,
|
| 1044 |
+
"learning_rate": 8.674058940678784e-06,
|
| 1045 |
+
"loss": 0.388,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.987983978638184,
|
| 1050 |
+
"grad_norm": 1.2858023643493652,
|
| 1051 |
+
"learning_rate": 8.474711706824494e-06,
|
| 1052 |
+
"loss": 0.4204,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.0,
|
| 1057 |
+
"grad_norm": 1.7074345350265503,
|
| 1058 |
+
"learning_rate": 8.27677599975532e-06,
|
| 1059 |
+
"loss": 0.3581,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.013351134846462,
|
| 1064 |
+
"grad_norm": 1.3163394927978516,
|
| 1065 |
+
"learning_rate": 8.080294636208196e-06,
|
| 1066 |
+
"loss": 0.2975,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.0267022696929238,
|
| 1071 |
+
"grad_norm": 1.1061831712722778,
|
| 1072 |
+
"learning_rate": 7.885310118321713e-06,
|
| 1073 |
+
"loss": 0.3446,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.040053404539386,
|
| 1078 |
+
"grad_norm": 1.192775845527649,
|
| 1079 |
+
"learning_rate": 7.69186462444224e-06,
|
| 1080 |
+
"loss": 0.3023,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.053404539385848,
|
| 1085 |
+
"grad_norm": 1.310829997062683,
|
| 1086 |
+
"learning_rate": 7.500000000000004e-06,
|
| 1087 |
+
"loss": 0.3888,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.0667556742323097,
|
| 1092 |
+
"grad_norm": 1.1934746503829956,
|
| 1093 |
+
"learning_rate": 7.309757748457277e-06,
|
| 1094 |
+
"loss": 0.3383,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.0801068090787718,
|
| 1099 |
+
"grad_norm": 1.2559807300567627,
|
| 1100 |
+
"learning_rate": 7.12117902233051e-06,
|
| 1101 |
+
"loss": 0.314,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.0934579439252334,
|
| 1106 |
+
"grad_norm": 1.2182846069335938,
|
| 1107 |
+
"learning_rate": 6.934304614288306e-06,
|
| 1108 |
+
"loss": 0.3112,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.1068090787716955,
|
| 1113 |
+
"grad_norm": 1.079424500465393,
|
| 1114 |
+
"learning_rate": 6.74917494832738e-06,
|
| 1115 |
+
"loss": 0.2797,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.1201602136181577,
|
| 1120 |
+
"grad_norm": 1.3284610509872437,
|
| 1121 |
+
"learning_rate": 6.5658300710281226e-06,
|
| 1122 |
+
"loss": 0.3168,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.1335113484646193,
|
| 1127 |
+
"grad_norm": 1.2821263074874878,
|
| 1128 |
+
"learning_rate": 6.38430964289188e-06,
|
| 1129 |
+
"loss": 0.3013,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.1468624833110814,
|
| 1134 |
+
"grad_norm": 1.172289490699768,
|
| 1135 |
+
"learning_rate": 6.204652929761774e-06,
|
| 1136 |
+
"loss": 0.289,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.1602136181575435,
|
| 1141 |
+
"grad_norm": 1.2766392230987549,
|
| 1142 |
+
"learning_rate": 6.026898794328814e-06,
|
| 1143 |
+
"loss": 0.297,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.173564753004005,
|
| 1148 |
+
"grad_norm": 1.2614953517913818,
|
| 1149 |
+
"learning_rate": 5.8510856877252805e-06,
|
| 1150 |
+
"loss": 0.2912,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.1869158878504673,
|
| 1155 |
+
"grad_norm": 1.3711159229278564,
|
| 1156 |
+
"learning_rate": 5.6772516412071115e-06,
|
| 1157 |
+
"loss": 0.2946,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.2002670226969294,
|
| 1162 |
+
"grad_norm": 1.0605024099349976,
|
| 1163 |
+
"learning_rate": 5.505434257927118e-06,
|
| 1164 |
+
"loss": 0.3215,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.213618157543391,
|
| 1169 |
+
"grad_norm": 1.2528624534606934,
|
| 1170 |
+
"learning_rate": 5.335670704800805e-06,
|
| 1171 |
+
"loss": 0.3172,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.226969292389853,
|
| 1176 |
+
"grad_norm": 1.2434332370758057,
|
| 1177 |
+
"learning_rate": 5.167997704466564e-06,
|
| 1178 |
+
"loss": 0.2948,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.2403204272363153,
|
| 1183 |
+
"grad_norm": 1.130089282989502,
|
| 1184 |
+
"learning_rate": 5.0024515273419514e-06,
|
| 1185 |
+
"loss": 0.3066,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.253671562082777,
|
| 1190 |
+
"grad_norm": 1.3827749490737915,
|
| 1191 |
+
"learning_rate": 4.839067983777836e-06,
|
| 1192 |
+
"loss": 0.301,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.267022696929239,
|
| 1197 |
+
"grad_norm": 1.0616753101348877,
|
| 1198 |
+
"learning_rate": 4.6778824163119685e-06,
|
| 1199 |
+
"loss": 0.3311,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.2803738317757007,
|
| 1204 |
+
"grad_norm": 1.2764469385147095,
|
| 1205 |
+
"learning_rate": 4.518929692023891e-06,
|
| 1206 |
+
"loss": 0.3028,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.293724966622163,
|
| 1211 |
+
"grad_norm": 1.355482816696167,
|
| 1212 |
+
"learning_rate": 4.362244194992565e-06,
|
| 1213 |
+
"loss": 0.3014,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.307076101468625,
|
| 1218 |
+
"grad_norm": 1.067796230316162,
|
| 1219 |
+
"learning_rate": 4.2078598188585235e-06,
|
| 1220 |
+
"loss": 0.2993,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.3204272363150866,
|
| 1225 |
+
"grad_norm": 1.2589912414550781,
|
| 1226 |
+
"learning_rate": 4.055809959492176e-06,
|
| 1227 |
+
"loss": 0.3057,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.3337783711615487,
|
| 1232 |
+
"grad_norm": 1.225380778312683,
|
| 1233 |
+
"learning_rate": 3.906127507769677e-06,
|
| 1234 |
+
"loss": 0.309,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.347129506008011,
|
| 1239 |
+
"grad_norm": 1.1756408214569092,
|
| 1240 |
+
"learning_rate": 3.7588448424581247e-06,
|
| 1241 |
+
"loss": 0.3267,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.3604806408544725,
|
| 1246 |
+
"grad_norm": 1.219713807106018,
|
| 1247 |
+
"learning_rate": 3.6139938232114844e-06,
|
| 1248 |
+
"loss": 0.2918,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.3738317757009346,
|
| 1253 |
+
"grad_norm": 1.249424695968628,
|
| 1254 |
+
"learning_rate": 3.4716057836788375e-06,
|
| 1255 |
+
"loss": 0.2958,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.3871829105473967,
|
| 1260 |
+
"grad_norm": 1.3024978637695312,
|
| 1261 |
+
"learning_rate": 3.3317115247263906e-06,
|
| 1262 |
+
"loss": 0.2877,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.4005340453938584,
|
| 1267 |
+
"grad_norm": 1.3283580541610718,
|
| 1268 |
+
"learning_rate": 3.1943413077747426e-06,
|
| 1269 |
+
"loss": 0.2986,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.4138851802403205,
|
| 1274 |
+
"grad_norm": 1.218979835510254,
|
| 1275 |
+
"learning_rate": 3.059524848252858e-06,
|
| 1276 |
+
"loss": 0.2652,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.427236315086782,
|
| 1281 |
+
"grad_norm": 1.2445980310440063,
|
| 1282 |
+
"learning_rate": 2.927291309170117e-06,
|
| 1283 |
+
"loss": 0.3025,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.4405874499332443,
|
| 1288 |
+
"grad_norm": 1.0788270235061646,
|
| 1289 |
+
"learning_rate": 2.797669294807871e-06,
|
| 1290 |
+
"loss": 0.3208,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.4539385847797064,
|
| 1295 |
+
"grad_norm": 1.465824842453003,
|
| 1296 |
+
"learning_rate": 2.670686844531899e-06,
|
| 1297 |
+
"loss": 0.2803,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.467289719626168,
|
| 1302 |
+
"grad_norm": 1.2923988103866577,
|
| 1303 |
+
"learning_rate": 2.5463714267270026e-06,
|
| 1304 |
+
"loss": 0.2879,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.48064085447263,
|
| 1309 |
+
"grad_norm": 1.152324914932251,
|
| 1310 |
+
"learning_rate": 2.4247499328551646e-06,
|
| 1311 |
+
"loss": 0.2951,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.4939919893190923,
|
| 1316 |
+
"grad_norm": 1.3641313314437866,
|
| 1317 |
+
"learning_rate": 2.305848671638469e-06,
|
| 1318 |
+
"loss": 0.2604,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.507343124165554,
|
| 1323 |
+
"grad_norm": 1.2033214569091797,
|
| 1324 |
+
"learning_rate": 2.189693363368106e-06,
|
| 1325 |
+
"loss": 0.2834,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.520694259012016,
|
| 1330 |
+
"grad_norm": 1.199393630027771,
|
| 1331 |
+
"learning_rate": 2.076309134340644e-06,
|
| 1332 |
+
"loss": 0.2769,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.534045393858478,
|
| 1337 |
+
"grad_norm": 1.3125813007354736,
|
| 1338 |
+
"learning_rate": 1.9657205114228033e-06,
|
| 1339 |
+
"loss": 0.2747,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.54739652870494,
|
| 1344 |
+
"grad_norm": 1.2329076528549194,
|
| 1345 |
+
"learning_rate": 1.8579514167458989e-06,
|
| 1346 |
+
"loss": 0.2724,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.560747663551402,
|
| 1351 |
+
"grad_norm": 1.1699281930923462,
|
| 1352 |
+
"learning_rate": 1.7530251625310723e-06,
|
| 1353 |
+
"loss": 0.282,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.5740987983978636,
|
| 1358 |
+
"grad_norm": 1.2195758819580078,
|
| 1359 |
+
"learning_rate": 1.6509644460464934e-06,
|
| 1360 |
+
"loss": 0.295,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.5874499332443257,
|
| 1365 |
+
"grad_norm": 1.22368586063385,
|
| 1366 |
+
"learning_rate": 1.5517913446975745e-06,
|
| 1367 |
+
"loss": 0.2682,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.600801068090788,
|
| 1372 |
+
"grad_norm": 1.2911183834075928,
|
| 1373 |
+
"learning_rate": 1.4555273112512386e-06,
|
| 1374 |
+
"loss": 0.3225,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.61415220293725,
|
| 1379 |
+
"grad_norm": 1.1300584077835083,
|
| 1380 |
+
"learning_rate": 1.362193169195366e-06,
|
| 1381 |
+
"loss": 0.2607,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.6275033377837116,
|
| 1386 |
+
"grad_norm": 1.0462965965270996,
|
| 1387 |
+
"learning_rate": 1.2718091082343103e-06,
|
| 1388 |
+
"loss": 0.2598,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.6408544726301737,
|
| 1393 |
+
"grad_norm": 1.3598288297653198,
|
| 1394 |
+
"learning_rate": 1.1843946799215476e-06,
|
| 1395 |
+
"loss": 0.2776,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.6542056074766354,
|
| 1400 |
+
"grad_norm": 1.322589635848999,
|
| 1401 |
+
"learning_rate": 1.099968793430347e-06,
|
| 1402 |
+
"loss": 0.3107,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.6675567423230975,
|
| 1407 |
+
"grad_norm": 1.0833837985992432,
|
| 1408 |
+
"learning_rate": 1.0185497114634067e-06,
|
| 1409 |
+
"loss": 0.2696,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.6809078771695596,
|
| 1414 |
+
"grad_norm": 1.1994613409042358,
|
| 1415 |
+
"learning_rate": 9.401550463023417e-07,
|
| 1416 |
+
"loss": 0.2959,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.6942590120160212,
|
| 1421 |
+
"grad_norm": 1.2726198434829712,
|
| 1422 |
+
"learning_rate": 8.648017559978471e-07,
|
| 1423 |
+
"loss": 0.2736,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.7076101468624834,
|
| 1428 |
+
"grad_norm": 1.2189561128616333,
|
| 1429 |
+
"learning_rate": 7.925061407013967e-07,
|
| 1430 |
+
"loss": 0.2579,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.720961281708945,
|
| 1435 |
+
"grad_norm": 1.3875340223312378,
|
| 1436 |
+
"learning_rate": 7.232838391392676e-07,
|
| 1437 |
+
"loss": 0.2659,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.734312416555407,
|
| 1442 |
+
"grad_norm": 1.3861265182495117,
|
| 1443 |
+
"learning_rate": 6.571498252295971e-07,
|
| 1444 |
+
"loss": 0.3254,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.7476635514018692,
|
| 1449 |
+
"grad_norm": 1.296462059020996,
|
| 1450 |
+
"learning_rate": 5.941184048433113e-07,
|
| 1451 |
+
"loss": 0.3084,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.7610146862483314,
|
| 1456 |
+
"grad_norm": 1.4091218709945679,
|
| 1457 |
+
"learning_rate": 5.342032127095092e-07,
|
| 1458 |
+
"loss": 0.3302,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.774365821094793,
|
| 1463 |
+
"grad_norm": 1.2126643657684326,
|
| 1464 |
+
"learning_rate": 4.774172094660523e-07,
|
| 1465 |
+
"loss": 0.2845,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.787716955941255,
|
| 1470 |
+
"grad_norm": 1.0950807332992554,
|
| 1471 |
+
"learning_rate": 4.237726788559748e-07,
|
| 1472 |
+
"loss": 0.2615,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.801068090787717,
|
| 1477 |
+
"grad_norm": 1.2768464088439941,
|
| 1478 |
+
"learning_rate": 3.7328122507029994e-07,
|
| 1479 |
+
"loss": 0.3108,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.814419225634179,
|
| 1484 |
+
"grad_norm": 1.200408697128296,
|
| 1485 |
+
"learning_rate": 3.25953770237864e-07,
|
| 1486 |
+
"loss": 0.2944,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.827770360480641,
|
| 1491 |
+
"grad_norm": 1.2608294486999512,
|
| 1492 |
+
"learning_rate": 2.818005520626832e-07,
|
| 1493 |
+
"loss": 0.2762,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.8411214953271027,
|
| 1498 |
+
"grad_norm": 1.2340041399002075,
|
| 1499 |
+
"learning_rate": 2.408311216093684e-07,
|
| 1500 |
+
"loss": 0.262,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.854472630173565,
|
| 1505 |
+
"grad_norm": 1.2838585376739502,
|
| 1506 |
+
"learning_rate": 2.030543412370811e-07,
|
| 1507 |
+
"loss": 0.2868,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.8678237650200264,
|
| 1512 |
+
"grad_norm": 1.1679357290267944,
|
| 1513 |
+
"learning_rate": 1.684783826824421e-07,
|
| 1514 |
+
"loss": 0.2952,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 2.8811748998664886,
|
| 1519 |
+
"grad_norm": 1.340585708618164,
|
| 1520 |
+
"learning_rate": 1.3711072529187686e-07,
|
| 1521 |
+
"loss": 0.2788,
|
| 1522 |
+
"step": 1080
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.8945260347129507,
|
| 1526 |
+
"grad_norm": 1.2561821937561035,
|
| 1527 |
+
"learning_rate": 1.0895815440368328e-07,
|
| 1528 |
+
"loss": 0.2831,
|
| 1529 |
+
"step": 1085
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.9078771695594128,
|
| 1533 |
+
"grad_norm": 1.0785143375396729,
|
| 1534 |
+
"learning_rate": 8.402675988027076e-08,
|
| 1535 |
+
"loss": 0.3293,
|
| 1536 |
+
"step": 1090
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.9212283044058744,
|
| 1540 |
+
"grad_norm": 1.431428074836731,
|
| 1541 |
+
"learning_rate": 6.23219347908155e-08,
|
| 1542 |
+
"loss": 0.3081,
|
| 1543 |
+
"step": 1095
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 2.9345794392523366,
|
| 1547 |
+
"grad_norm": 1.2981603145599365,
|
| 1548 |
+
"learning_rate": 4.3848374244652156e-08,
|
| 1549 |
+
"loss": 0.2569,
|
| 1550 |
+
"step": 1100
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 2.947930574098798,
|
| 1554 |
+
"grad_norm": 1.1704469919204712,
|
| 1555 |
+
"learning_rate": 2.861007437564622e-08,
|
| 1556 |
+
"loss": 0.317,
|
| 1557 |
+
"step": 1105
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 2.9612817089452603,
|
| 1561 |
+
"grad_norm": 1.2422795295715332,
|
| 1562 |
+
"learning_rate": 1.6610331477763806e-08,
|
| 1563 |
+
"loss": 0.2585,
|
| 1564 |
+
"step": 1110
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 2.9746328437917224,
|
| 1568 |
+
"grad_norm": 1.2116549015045166,
|
| 1569 |
+
"learning_rate": 7.851741292028702e-09,
|
| 1570 |
+
"loss": 0.2864,
|
| 1571 |
+
"step": 1115
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.987983978638184,
|
| 1575 |
+
"grad_norm": 1.228804349899292,
|
| 1576 |
+
"learning_rate": 2.3361984450215314e-09,
|
| 1577 |
+
"loss": 0.2876,
|
| 1578 |
+
"step": 1120
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 3.0,
|
| 1582 |
+
"grad_norm": 1.406020164489746,
|
| 1583 |
+
"learning_rate": 6.489603903925278e-11,
|
| 1584 |
+
"loss": 0.2844,
|
| 1585 |
+
"step": 1125
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 3.0,
|
| 1589 |
+
"step": 1125,
|
| 1590 |
+
"total_flos": 1.6050721755748106e+18,
|
| 1591 |
+
"train_loss": 0.5690460730658637,
|
| 1592 |
+
"train_runtime": 738.6249,
|
| 1593 |
+
"train_samples_per_second": 48.654,
|
| 1594 |
+
"train_steps_per_second": 1.523
|
| 1595 |
+
}
|
| 1596 |
+
],
|
| 1597 |
+
"logging_steps": 5,
|
| 1598 |
+
"max_steps": 1125,
|
| 1599 |
+
"num_input_tokens_seen": 0,
|
| 1600 |
+
"num_train_epochs": 3,
|
| 1601 |
+
"save_steps": 2000,
|
| 1602 |
+
"stateful_callbacks": {
|
| 1603 |
+
"TrainerControl": {
|
| 1604 |
+
"args": {
|
| 1605 |
+
"should_epoch_stop": false,
|
| 1606 |
+
"should_evaluate": false,
|
| 1607 |
+
"should_log": false,
|
| 1608 |
+
"should_save": false,
|
| 1609 |
+
"should_training_stop": false
|
| 1610 |
+
},
|
| 1611 |
+
"attributes": {}
|
| 1612 |
+
}
|
| 1613 |
+
},
|
| 1614 |
+
"total_flos": 1.6050721755748106e+18,
|
| 1615 |
+
"train_batch_size": 2,
|
| 1616 |
+
"trial_name": null,
|
| 1617 |
+
"trial_params": null
|
| 1618 |
+
}
|
11_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac93b462c6fe900d57731114482f8207a33f24f2f8d048a8dd0c3e6a47ebc75f
|
| 3 |
+
size 8145
|
11_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|