Upload folder using huggingface_hub
Browse files- 18_128_e3_3e-5/README.md +63 -0
- 18_128_e3_3e-5/adapter_config.json +39 -0
- 18_128_e3_3e-5/adapter_model.safetensors +3 -0
- 18_128_e3_3e-5/all_results.json +9 -0
- 18_128_e3_3e-5/config.json +32 -0
- 18_128_e3_3e-5/merges.txt +0 -0
- 18_128_e3_3e-5/special_tokens_map.json +45 -0
- 18_128_e3_3e-5/tokenizer.json +0 -0
- 18_128_e3_3e-5/tokenizer_config.json +188 -0
- 18_128_e3_3e-5/train_results.json +9 -0
- 18_128_e3_3e-5/trainer_state.json +1548 -0
- 18_128_e3_3e-5/training_args.bin +3 -0
- 18_128_e3_3e-5/vocab.json +0 -0
18_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: 18_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 |
+
# 18_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
|
18_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 |
+
"up_proj",
|
| 29 |
+
"v_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"k_proj",
|
| 32 |
+
"q_proj",
|
| 33 |
+
"o_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
18_128_e3_3e-5/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ca8f1539efff0d4b8462cd6bcdc67b05e28a9e1bb9f09199fabdac25495e5cc
|
| 3 |
+
size 791751704
|
18_128_e3_3e-5/all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.5565310221311017e+18,
|
| 4 |
+
"train_loss": 0.579777075055582,
|
| 5 |
+
"train_runtime": 706.5394,
|
| 6 |
+
"train_samples": 11460,
|
| 7 |
+
"train_samples_per_second": 48.66,
|
| 8 |
+
"train_steps_per_second": 1.524
|
| 9 |
+
}
|
18_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 |
+
}
|
18_128_e3_3e-5/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
18_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 |
+
}
|
18_128_e3_3e-5/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
18_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 |
+
}
|
18_128_e3_3e-5/train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1.5565310221311017e+18,
|
| 4 |
+
"train_loss": 0.579777075055582,
|
| 5 |
+
"train_runtime": 706.5394,
|
| 6 |
+
"train_samples": 11460,
|
| 7 |
+
"train_samples_per_second": 48.66,
|
| 8 |
+
"train_steps_per_second": 1.524
|
| 9 |
+
}
|
18_128_e3_3e-5/trainer_state.json
ADDED
|
@@ -0,0 +1,1548 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1077,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01394700139470014,
|
| 14 |
+
"grad_norm": 1.066906452178955,
|
| 15 |
+
"learning_rate": 2.222222222222222e-06,
|
| 16 |
+
"loss": 1.2865,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.02789400278940028,
|
| 21 |
+
"grad_norm": 0.7506229877471924,
|
| 22 |
+
"learning_rate": 4.9999999999999996e-06,
|
| 23 |
+
"loss": 1.3416,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.04184100418410042,
|
| 28 |
+
"grad_norm": 1.1370344161987305,
|
| 29 |
+
"learning_rate": 7.777777777777777e-06,
|
| 30 |
+
"loss": 1.3304,
|
| 31 |
+
"step": 15
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05578800557880056,
|
| 35 |
+
"grad_norm": 0.622694730758667,
|
| 36 |
+
"learning_rate": 1.0555555555555555e-05,
|
| 37 |
+
"loss": 1.2918,
|
| 38 |
+
"step": 20
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0697350069735007,
|
| 42 |
+
"grad_norm": 0.5598952770233154,
|
| 43 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 44 |
+
"loss": 1.2934,
|
| 45 |
+
"step": 25
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.08368200836820083,
|
| 49 |
+
"grad_norm": 0.5644311308860779,
|
| 50 |
+
"learning_rate": 1.6111111111111115e-05,
|
| 51 |
+
"loss": 1.2611,
|
| 52 |
+
"step": 30
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.09762900976290098,
|
| 56 |
+
"grad_norm": 0.4402819573879242,
|
| 57 |
+
"learning_rate": 1.888888888888889e-05,
|
| 58 |
+
"loss": 1.1888,
|
| 59 |
+
"step": 35
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.11157601115760112,
|
| 63 |
+
"grad_norm": 0.46063461899757385,
|
| 64 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 65 |
+
"loss": 1.2805,
|
| 66 |
+
"step": 40
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.12552301255230125,
|
| 70 |
+
"grad_norm": 0.4759824872016907,
|
| 71 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 72 |
+
"loss": 1.1848,
|
| 73 |
+
"step": 45
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1394700139470014,
|
| 77 |
+
"grad_norm": 0.5271196961402893,
|
| 78 |
+
"learning_rate": 2.7222222222222223e-05,
|
| 79 |
+
"loss": 1.2368,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.15341701534170155,
|
| 84 |
+
"grad_norm": 0.45571476221084595,
|
| 85 |
+
"learning_rate": 3e-05,
|
| 86 |
+
"loss": 1.1643,
|
| 87 |
+
"step": 55
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.16736401673640167,
|
| 91 |
+
"grad_norm": 0.4694708287715912,
|
| 92 |
+
"learning_rate": 2.99982317599734e-05,
|
| 93 |
+
"loss": 1.2301,
|
| 94 |
+
"step": 60
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.18131101813110181,
|
| 98 |
+
"grad_norm": 0.4949331283569336,
|
| 99 |
+
"learning_rate": 2.999292745678331e-05,
|
| 100 |
+
"loss": 1.1678,
|
| 101 |
+
"step": 65
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.19525801952580196,
|
| 105 |
+
"grad_norm": 0.4888177812099457,
|
| 106 |
+
"learning_rate": 2.9984088341000547e-05,
|
| 107 |
+
"loss": 1.1756,
|
| 108 |
+
"step": 70
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.20920502092050208,
|
| 112 |
+
"grad_norm": 0.5729331374168396,
|
| 113 |
+
"learning_rate": 2.9971716496582237e-05,
|
| 114 |
+
"loss": 1.1372,
|
| 115 |
+
"step": 75
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.22315202231520223,
|
| 119 |
+
"grad_norm": 0.7023358345031738,
|
| 120 |
+
"learning_rate": 2.9955814840380432e-05,
|
| 121 |
+
"loss": 1.1401,
|
| 122 |
+
"step": 80
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.23709902370990238,
|
| 126 |
+
"grad_norm": 0.5472949743270874,
|
| 127 |
+
"learning_rate": 2.9936387121454473e-05,
|
| 128 |
+
"loss": 1.148,
|
| 129 |
+
"step": 85
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2510460251046025,
|
| 133 |
+
"grad_norm": 0.5103905200958252,
|
| 134 |
+
"learning_rate": 2.9913437920187055e-05,
|
| 135 |
+
"loss": 1.1077,
|
| 136 |
+
"step": 90
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.2649930264993027,
|
| 140 |
+
"grad_norm": 0.5134495496749878,
|
| 141 |
+
"learning_rate": 2.9886972647204343e-05,
|
| 142 |
+
"loss": 1.1272,
|
| 143 |
+
"step": 95
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.2789400278940028,
|
| 147 |
+
"grad_norm": 0.5091322660446167,
|
| 148 |
+
"learning_rate": 2.985699754210034e-05,
|
| 149 |
+
"loss": 1.069,
|
| 150 |
+
"step": 100
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.2928870292887029,
|
| 154 |
+
"grad_norm": 0.5628131031990051,
|
| 155 |
+
"learning_rate": 2.9823519671965808e-05,
|
| 156 |
+
"loss": 1.0438,
|
| 157 |
+
"step": 105
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.3068340306834031,
|
| 161 |
+
"grad_norm": 0.5659134984016418,
|
| 162 |
+
"learning_rate": 2.9786546929722055e-05,
|
| 163 |
+
"loss": 1.0374,
|
| 164 |
+
"step": 110
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.3207810320781032,
|
| 168 |
+
"grad_norm": 0.5672776103019714,
|
| 169 |
+
"learning_rate": 2.9746088032260134e-05,
|
| 170 |
+
"loss": 1.0907,
|
| 171 |
+
"step": 115
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.33472803347280333,
|
| 175 |
+
"grad_norm": 0.5363381505012512,
|
| 176 |
+
"learning_rate": 2.970215251838562e-05,
|
| 177 |
+
"loss": 1.0219,
|
| 178 |
+
"step": 120
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3486750348675035,
|
| 182 |
+
"grad_norm": 0.6197344064712524,
|
| 183 |
+
"learning_rate": 2.965475074656975e-05,
|
| 184 |
+
"loss": 1.0335,
|
| 185 |
+
"step": 125
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.36262203626220363,
|
| 189 |
+
"grad_norm": 0.6039124131202698,
|
| 190 |
+
"learning_rate": 2.9603893892507226e-05,
|
| 191 |
+
"loss": 1.0383,
|
| 192 |
+
"step": 130
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.37656903765690375,
|
| 196 |
+
"grad_norm": 0.5894793272018433,
|
| 197 |
+
"learning_rate": 2.9549593946481375e-05,
|
| 198 |
+
"loss": 1.0326,
|
| 199 |
+
"step": 135
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.3905160390516039,
|
| 203 |
+
"grad_norm": 0.7624173760414124,
|
| 204 |
+
"learning_rate": 2.949186371053726e-05,
|
| 205 |
+
"loss": 0.9903,
|
| 206 |
+
"step": 140
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.40446304044630405,
|
| 210 |
+
"grad_norm": 0.6892929077148438,
|
| 211 |
+
"learning_rate": 2.9430716795463416e-05,
|
| 212 |
+
"loss": 0.9748,
|
| 213 |
+
"step": 145
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.41841004184100417,
|
| 217 |
+
"grad_norm": 0.6219784617424011,
|
| 218 |
+
"learning_rate": 2.9366167617582872e-05,
|
| 219 |
+
"loss": 1.0037,
|
| 220 |
+
"step": 150
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.43235704323570434,
|
| 224 |
+
"grad_norm": 0.5984349846839905,
|
| 225 |
+
"learning_rate": 2.929823139535429e-05,
|
| 226 |
+
"loss": 0.996,
|
| 227 |
+
"step": 155
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.44630404463040446,
|
| 231 |
+
"grad_norm": 0.6248619556427002,
|
| 232 |
+
"learning_rate": 2.9226924145783995e-05,
|
| 233 |
+
"loss": 0.9285,
|
| 234 |
+
"step": 160
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.4602510460251046,
|
| 238 |
+
"grad_norm": 0.6727274656295776,
|
| 239 |
+
"learning_rate": 2.9152262680649704e-05,
|
| 240 |
+
"loss": 0.9591,
|
| 241 |
+
"step": 165
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.47419804741980476,
|
| 245 |
+
"grad_norm": 0.6496078968048096,
|
| 246 |
+
"learning_rate": 2.9074264602536896e-05,
|
| 247 |
+
"loss": 0.9915,
|
| 248 |
+
"step": 170
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.4881450488145049,
|
| 252 |
+
"grad_norm": 0.6838123202323914,
|
| 253 |
+
"learning_rate": 2.8992948300688734e-05,
|
| 254 |
+
"loss": 0.9202,
|
| 255 |
+
"step": 175
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.502092050209205,
|
| 259 |
+
"grad_norm": 0.762900173664093,
|
| 260 |
+
"learning_rate": 2.8908332946670514e-05,
|
| 261 |
+
"loss": 0.9124,
|
| 262 |
+
"step": 180
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.5160390516039052,
|
| 266 |
+
"grad_norm": 0.6561188697814941,
|
| 267 |
+
"learning_rate": 2.8820438489849687e-05,
|
| 268 |
+
"loss": 0.8728,
|
| 269 |
+
"step": 185
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.5299860529986054,
|
| 273 |
+
"grad_norm": 0.8515373468399048,
|
| 274 |
+
"learning_rate": 2.8729285652692468e-05,
|
| 275 |
+
"loss": 0.916,
|
| 276 |
+
"step": 190
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.5439330543933054,
|
| 280 |
+
"grad_norm": 0.7038597464561462,
|
| 281 |
+
"learning_rate": 2.8634895925878225e-05,
|
| 282 |
+
"loss": 0.8915,
|
| 283 |
+
"step": 195
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.5578800557880056,
|
| 287 |
+
"grad_norm": 0.7447533011436462,
|
| 288 |
+
"learning_rate": 2.8537291563232692e-05,
|
| 289 |
+
"loss": 0.8662,
|
| 290 |
+
"step": 200
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.5718270571827058,
|
| 294 |
+
"grad_norm": 0.8365384936332703,
|
| 295 |
+
"learning_rate": 2.843649557648131e-05,
|
| 296 |
+
"loss": 0.9019,
|
| 297 |
+
"step": 205
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.5857740585774058,
|
| 301 |
+
"grad_norm": 0.7706406712532043,
|
| 302 |
+
"learning_rate": 2.8332531729823853e-05,
|
| 303 |
+
"loss": 0.913,
|
| 304 |
+
"step": 210
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.599721059972106,
|
| 308 |
+
"grad_norm": 0.7835051417350769,
|
| 309 |
+
"learning_rate": 2.822542453433165e-05,
|
| 310 |
+
"loss": 0.8506,
|
| 311 |
+
"step": 215
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.6136680613668062,
|
| 315 |
+
"grad_norm": 0.8733814358711243,
|
| 316 |
+
"learning_rate": 2.811519924216873e-05,
|
| 317 |
+
"loss": 0.8256,
|
| 318 |
+
"step": 220
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.6276150627615062,
|
| 322 |
+
"grad_norm": 0.861761748790741,
|
| 323 |
+
"learning_rate": 2.8001881840638236e-05,
|
| 324 |
+
"loss": 0.8483,
|
| 325 |
+
"step": 225
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.6415620641562064,
|
| 329 |
+
"grad_norm": 0.8026784658432007,
|
| 330 |
+
"learning_rate": 2.7885499046055505e-05,
|
| 331 |
+
"loss": 0.827,
|
| 332 |
+
"step": 230
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.6555090655509066,
|
| 336 |
+
"grad_norm": 0.8849096894264221,
|
| 337 |
+
"learning_rate": 2.776607829744932e-05,
|
| 338 |
+
"loss": 0.793,
|
| 339 |
+
"step": 235
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.6694560669456067,
|
| 343 |
+
"grad_norm": 0.8844088315963745,
|
| 344 |
+
"learning_rate": 2.76436477500927e-05,
|
| 345 |
+
"loss": 0.8201,
|
| 346 |
+
"step": 240
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.6834030683403068,
|
| 350 |
+
"grad_norm": 0.858239471912384,
|
| 351 |
+
"learning_rate": 2.7518236268864885e-05,
|
| 352 |
+
"loss": 0.8048,
|
| 353 |
+
"step": 245
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.697350069735007,
|
| 357 |
+
"grad_norm": 0.8709297776222229,
|
| 358 |
+
"learning_rate": 2.7389873421445996e-05,
|
| 359 |
+
"loss": 0.8578,
|
| 360 |
+
"step": 250
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.7112970711297071,
|
| 364 |
+
"grad_norm": 0.8225599527359009,
|
| 365 |
+
"learning_rate": 2.7258589471346005e-05,
|
| 366 |
+
"loss": 0.7756,
|
| 367 |
+
"step": 255
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.7252440725244073,
|
| 371 |
+
"grad_norm": 1.0289467573165894,
|
| 372 |
+
"learning_rate": 2.7124415370769623e-05,
|
| 373 |
+
"loss": 0.7968,
|
| 374 |
+
"step": 260
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.7391910739191074,
|
| 378 |
+
"grad_norm": 0.9111974239349365,
|
| 379 |
+
"learning_rate": 2.6987382753318885e-05,
|
| 380 |
+
"loss": 0.7948,
|
| 381 |
+
"step": 265
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.7531380753138075,
|
| 385 |
+
"grad_norm": 0.8552051186561584,
|
| 386 |
+
"learning_rate": 2.6847523926535e-05,
|
| 387 |
+
"loss": 0.7877,
|
| 388 |
+
"step": 270
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.7670850767085077,
|
| 392 |
+
"grad_norm": 0.9314124584197998,
|
| 393 |
+
"learning_rate": 2.6704871864281377e-05,
|
| 394 |
+
"loss": 0.7851,
|
| 395 |
+
"step": 275
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.7810320781032078,
|
| 399 |
+
"grad_norm": 1.047489047050476,
|
| 400 |
+
"learning_rate": 2.655946019896954e-05,
|
| 401 |
+
"loss": 0.7374,
|
| 402 |
+
"step": 280
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.7949790794979079,
|
| 406 |
+
"grad_norm": 0.9907748103141785,
|
| 407 |
+
"learning_rate": 2.641132321362974e-05,
|
| 408 |
+
"loss": 0.7482,
|
| 409 |
+
"step": 285
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.8089260808926081,
|
| 413 |
+
"grad_norm": 0.9449021816253662,
|
| 414 |
+
"learning_rate": 2.6260495833828236e-05,
|
| 415 |
+
"loss": 0.7638,
|
| 416 |
+
"step": 290
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.8228730822873083,
|
| 420 |
+
"grad_norm": 0.9518932104110718,
|
| 421 |
+
"learning_rate": 2.6107013619433027e-05,
|
| 422 |
+
"loss": 0.7546,
|
| 423 |
+
"step": 295
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.8368200836820083,
|
| 427 |
+
"grad_norm": 0.8809913992881775,
|
| 428 |
+
"learning_rate": 2.595091275623011e-05,
|
| 429 |
+
"loss": 0.765,
|
| 430 |
+
"step": 300
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.8507670850767085,
|
| 434 |
+
"grad_norm": 0.9280657768249512,
|
| 435 |
+
"learning_rate": 2.5792230047392075e-05,
|
| 436 |
+
"loss": 0.7804,
|
| 437 |
+
"step": 305
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.8647140864714087,
|
| 441 |
+
"grad_norm": 0.9119299650192261,
|
| 442 |
+
"learning_rate": 2.5631002904801226e-05,
|
| 443 |
+
"loss": 0.7486,
|
| 444 |
+
"step": 310
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.8786610878661087,
|
| 448 |
+
"grad_norm": 1.034084439277649,
|
| 449 |
+
"learning_rate": 2.5467269340229158e-05,
|
| 450 |
+
"loss": 0.7105,
|
| 451 |
+
"step": 315
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.8926080892608089,
|
| 455 |
+
"grad_norm": 0.958251416683197,
|
| 456 |
+
"learning_rate": 2.530106795637488e-05,
|
| 457 |
+
"loss": 0.6795,
|
| 458 |
+
"step": 320
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.9065550906555091,
|
| 462 |
+
"grad_norm": 0.9546175599098206,
|
| 463 |
+
"learning_rate": 2.513243793776364e-05,
|
| 464 |
+
"loss": 0.7021,
|
| 465 |
+
"step": 325
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.9205020920502092,
|
| 469 |
+
"grad_norm": 1.1040949821472168,
|
| 470 |
+
"learning_rate": 2.496141904150859e-05,
|
| 471 |
+
"loss": 0.7352,
|
| 472 |
+
"step": 330
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.9344490934449093,
|
| 476 |
+
"grad_norm": 1.1172016859054565,
|
| 477 |
+
"learning_rate": 2.478805158793741e-05,
|
| 478 |
+
"loss": 0.6983,
|
| 479 |
+
"step": 335
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.9483960948396095,
|
| 483 |
+
"grad_norm": 0.9482975602149963,
|
| 484 |
+
"learning_rate": 2.461237645108621e-05,
|
| 485 |
+
"loss": 0.6914,
|
| 486 |
+
"step": 340
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.9623430962343096,
|
| 490 |
+
"grad_norm": 1.0134937763214111,
|
| 491 |
+
"learning_rate": 2.4434435049062795e-05,
|
| 492 |
+
"loss": 0.6994,
|
| 493 |
+
"step": 345
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.9762900976290098,
|
| 497 |
+
"grad_norm": 0.9843146204948425,
|
| 498 |
+
"learning_rate": 2.425426933428177e-05,
|
| 499 |
+
"loss": 0.6637,
|
| 500 |
+
"step": 350
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.9902370990237099,
|
| 504 |
+
"grad_norm": 1.001772165298462,
|
| 505 |
+
"learning_rate": 2.407192178357357e-05,
|
| 506 |
+
"loss": 0.6799,
|
| 507 |
+
"step": 355
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.00278940027894,
|
| 511 |
+
"grad_norm": 0.9672765135765076,
|
| 512 |
+
"learning_rate": 2.3887435388169918e-05,
|
| 513 |
+
"loss": 0.6486,
|
| 514 |
+
"step": 360
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.0167364016736402,
|
| 518 |
+
"grad_norm": 1.112261176109314,
|
| 519 |
+
"learning_rate": 2.3700853643567973e-05,
|
| 520 |
+
"loss": 0.615,
|
| 521 |
+
"step": 365
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.0306834030683403,
|
| 525 |
+
"grad_norm": 1.137927770614624,
|
| 526 |
+
"learning_rate": 2.351222053927561e-05,
|
| 527 |
+
"loss": 0.5779,
|
| 528 |
+
"step": 370
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.0446304044630403,
|
| 532 |
+
"grad_norm": 1.1074265241622925,
|
| 533 |
+
"learning_rate": 2.3321580548440212e-05,
|
| 534 |
+
"loss": 0.5831,
|
| 535 |
+
"step": 375
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.0585774058577406,
|
| 539 |
+
"grad_norm": 0.8795539140701294,
|
| 540 |
+
"learning_rate": 2.312897861736343e-05,
|
| 541 |
+
"loss": 0.6054,
|
| 542 |
+
"step": 380
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.0725244072524407,
|
| 546 |
+
"grad_norm": 1.0793238878250122,
|
| 547 |
+
"learning_rate": 2.2934460154904436e-05,
|
| 548 |
+
"loss": 0.5792,
|
| 549 |
+
"step": 385
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.086471408647141,
|
| 553 |
+
"grad_norm": 1.217804193496704,
|
| 554 |
+
"learning_rate": 2.2738071021774062e-05,
|
| 555 |
+
"loss": 0.5793,
|
| 556 |
+
"step": 390
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.100418410041841,
|
| 560 |
+
"grad_norm": 1.0535447597503662,
|
| 561 |
+
"learning_rate": 2.253985751972244e-05,
|
| 562 |
+
"loss": 0.5692,
|
| 563 |
+
"step": 395
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.114365411436541,
|
| 567 |
+
"grad_norm": 1.0112451314926147,
|
| 568 |
+
"learning_rate": 2.2339866380622657e-05,
|
| 569 |
+
"loss": 0.5748,
|
| 570 |
+
"step": 400
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.1283124128312414,
|
| 574 |
+
"grad_norm": 1.1328134536743164,
|
| 575 |
+
"learning_rate": 2.213814475545299e-05,
|
| 576 |
+
"loss": 0.5457,
|
| 577 |
+
"step": 405
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.1422594142259415,
|
| 581 |
+
"grad_norm": 0.9204275012016296,
|
| 582 |
+
"learning_rate": 2.193474020318035e-05,
|
| 583 |
+
"loss": 0.5751,
|
| 584 |
+
"step": 410
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.1562064156206415,
|
| 588 |
+
"grad_norm": 1.20762038230896,
|
| 589 |
+
"learning_rate": 2.1729700679547537e-05,
|
| 590 |
+
"loss": 0.5988,
|
| 591 |
+
"step": 415
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.1701534170153418,
|
| 595 |
+
"grad_norm": 1.0492533445358276,
|
| 596 |
+
"learning_rate": 2.1523074525766906e-05,
|
| 597 |
+
"loss": 0.5314,
|
| 598 |
+
"step": 420
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.1841004184100419,
|
| 602 |
+
"grad_norm": 1.0287057161331177,
|
| 603 |
+
"learning_rate": 2.1314910457123216e-05,
|
| 604 |
+
"loss": 0.5481,
|
| 605 |
+
"step": 425
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.198047419804742,
|
| 609 |
+
"grad_norm": 1.0473965406417847,
|
| 610 |
+
"learning_rate": 2.1105257551488236e-05,
|
| 611 |
+
"loss": 0.5267,
|
| 612 |
+
"step": 430
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.2119944211994422,
|
| 616 |
+
"grad_norm": 1.138533592224121,
|
| 617 |
+
"learning_rate": 2.089416523774989e-05,
|
| 618 |
+
"loss": 0.5286,
|
| 619 |
+
"step": 435
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.2259414225941423,
|
| 623 |
+
"grad_norm": 1.242431640625,
|
| 624 |
+
"learning_rate": 2.068168328415864e-05,
|
| 625 |
+
"loss": 0.5275,
|
| 626 |
+
"step": 440
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.2398884239888424,
|
| 630 |
+
"grad_norm": 1.2236562967300415,
|
| 631 |
+
"learning_rate": 2.0467861786593858e-05,
|
| 632 |
+
"loss": 0.5437,
|
| 633 |
+
"step": 445
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.2538354253835426,
|
| 637 |
+
"grad_norm": 1.095345377922058,
|
| 638 |
+
"learning_rate": 2.0252751156752943e-05,
|
| 639 |
+
"loss": 0.5558,
|
| 640 |
+
"step": 450
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.2677824267782427,
|
| 644 |
+
"grad_norm": 1.1019301414489746,
|
| 645 |
+
"learning_rate": 2.003640211026601e-05,
|
| 646 |
+
"loss": 0.5159,
|
| 647 |
+
"step": 455
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.2817294281729428,
|
| 651 |
+
"grad_norm": 1.0805221796035767,
|
| 652 |
+
"learning_rate": 1.9818865654738886e-05,
|
| 653 |
+
"loss": 0.5366,
|
| 654 |
+
"step": 460
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.295676429567643,
|
| 658 |
+
"grad_norm": 1.0400440692901611,
|
| 659 |
+
"learning_rate": 1.9600193077727297e-05,
|
| 660 |
+
"loss": 0.5417,
|
| 661 |
+
"step": 465
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.3096234309623431,
|
| 665 |
+
"grad_norm": 1.0411120653152466,
|
| 666 |
+
"learning_rate": 1.938043593464502e-05,
|
| 667 |
+
"loss": 0.5317,
|
| 668 |
+
"step": 470
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.3235704323570432,
|
| 672 |
+
"grad_norm": 0.9950515627861023,
|
| 673 |
+
"learning_rate": 1.915964603660893e-05,
|
| 674 |
+
"loss": 0.4817,
|
| 675 |
+
"step": 475
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.3375174337517435,
|
| 679 |
+
"grad_norm": 1.0710848569869995,
|
| 680 |
+
"learning_rate": 1.8937875438223722e-05,
|
| 681 |
+
"loss": 0.5305,
|
| 682 |
+
"step": 480
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.3514644351464435,
|
| 686 |
+
"grad_norm": 1.2810304164886475,
|
| 687 |
+
"learning_rate": 1.871517642530923e-05,
|
| 688 |
+
"loss": 0.5071,
|
| 689 |
+
"step": 485
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.3654114365411436,
|
| 693 |
+
"grad_norm": 1.0427031517028809,
|
| 694 |
+
"learning_rate": 1.8491601502573254e-05,
|
| 695 |
+
"loss": 0.5458,
|
| 696 |
+
"step": 490
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.379358437935844,
|
| 700 |
+
"grad_norm": 1.2561126947402954,
|
| 701 |
+
"learning_rate": 1.8267203381232774e-05,
|
| 702 |
+
"loss": 0.5331,
|
| 703 |
+
"step": 495
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.393305439330544,
|
| 707 |
+
"grad_norm": 1.2695318460464478,
|
| 708 |
+
"learning_rate": 1.804203496658646e-05,
|
| 709 |
+
"loss": 0.4987,
|
| 710 |
+
"step": 500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.407252440725244,
|
| 714 |
+
"grad_norm": 1.139713168144226,
|
| 715 |
+
"learning_rate": 1.7816149345541454e-05,
|
| 716 |
+
"loss": 0.5277,
|
| 717 |
+
"step": 505
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.4211994421199443,
|
| 721 |
+
"grad_norm": 1.2892489433288574,
|
| 722 |
+
"learning_rate": 1.7589599774097287e-05,
|
| 723 |
+
"loss": 0.505,
|
| 724 |
+
"step": 510
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.4351464435146444,
|
| 728 |
+
"grad_norm": 1.1347765922546387,
|
| 729 |
+
"learning_rate": 1.736243966479e-05,
|
| 730 |
+
"loss": 0.5058,
|
| 731 |
+
"step": 515
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.4490934449093444,
|
| 735 |
+
"grad_norm": 1.0624372959136963,
|
| 736 |
+
"learning_rate": 1.713472257409928e-05,
|
| 737 |
+
"loss": 0.4615,
|
| 738 |
+
"step": 520
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.4630404463040447,
|
| 742 |
+
"grad_norm": 1.1356580257415771,
|
| 743 |
+
"learning_rate": 1.690650218982173e-05,
|
| 744 |
+
"loss": 0.4887,
|
| 745 |
+
"step": 525
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.4769874476987448,
|
| 749 |
+
"grad_norm": 1.065077781677246,
|
| 750 |
+
"learning_rate": 1.6677832318413138e-05,
|
| 751 |
+
"loss": 0.4569,
|
| 752 |
+
"step": 530
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.4909344490934449,
|
| 756 |
+
"grad_norm": 1.1207159757614136,
|
| 757 |
+
"learning_rate": 1.6448766872302767e-05,
|
| 758 |
+
"loss": 0.4677,
|
| 759 |
+
"step": 535
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.5048814504881451,
|
| 763 |
+
"grad_norm": 1.2944550514221191,
|
| 764 |
+
"learning_rate": 1.6219359857182693e-05,
|
| 765 |
+
"loss": 0.4727,
|
| 766 |
+
"step": 540
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.5188284518828452,
|
| 770 |
+
"grad_norm": 1.0558358430862427,
|
| 771 |
+
"learning_rate": 1.5989665359275104e-05,
|
| 772 |
+
"loss": 0.4804,
|
| 773 |
+
"step": 545
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.5327754532775453,
|
| 777 |
+
"grad_norm": 1.3540595769882202,
|
| 778 |
+
"learning_rate": 1.5759737532580692e-05,
|
| 779 |
+
"loss": 0.4437,
|
| 780 |
+
"step": 550
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.5467224546722456,
|
| 784 |
+
"grad_norm": 1.0707370042800903,
|
| 785 |
+
"learning_rate": 1.552963058611097e-05,
|
| 786 |
+
"loss": 0.458,
|
| 787 |
+
"step": 555
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.5606694560669456,
|
| 791 |
+
"grad_norm": 1.5930432081222534,
|
| 792 |
+
"learning_rate": 1.529939877110769e-05,
|
| 793 |
+
"loss": 0.463,
|
| 794 |
+
"step": 560
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.5746164574616457,
|
| 798 |
+
"grad_norm": 1.1141725778579712,
|
| 799 |
+
"learning_rate": 1.5069096368252277e-05,
|
| 800 |
+
"loss": 0.4691,
|
| 801 |
+
"step": 565
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.588563458856346,
|
| 805 |
+
"grad_norm": 1.382080316543579,
|
| 806 |
+
"learning_rate": 1.4838777674868328e-05,
|
| 807 |
+
"loss": 0.4754,
|
| 808 |
+
"step": 570
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.602510460251046,
|
| 812 |
+
"grad_norm": 1.2500920295715332,
|
| 813 |
+
"learning_rate": 1.4608496992120179e-05,
|
| 814 |
+
"loss": 0.4632,
|
| 815 |
+
"step": 575
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.616457461645746,
|
| 819 |
+
"grad_norm": 1.1228262186050415,
|
| 820 |
+
"learning_rate": 1.4378308612210569e-05,
|
| 821 |
+
"loss": 0.4648,
|
| 822 |
+
"step": 580
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.6304044630404464,
|
| 826 |
+
"grad_norm": 1.1510865688323975,
|
| 827 |
+
"learning_rate": 1.4148266805580437e-05,
|
| 828 |
+
"loss": 0.4668,
|
| 829 |
+
"step": 585
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.6443514644351465,
|
| 833 |
+
"grad_norm": 1.1644593477249146,
|
| 834 |
+
"learning_rate": 1.391842580811382e-05,
|
| 835 |
+
"loss": 0.4544,
|
| 836 |
+
"step": 590
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.6582984658298465,
|
| 840 |
+
"grad_norm": 1.2412949800491333,
|
| 841 |
+
"learning_rate": 1.368883980835091e-05,
|
| 842 |
+
"loss": 0.4285,
|
| 843 |
+
"step": 595
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.6722454672245468,
|
| 847 |
+
"grad_norm": 1.0620049238204956,
|
| 848 |
+
"learning_rate": 1.3459562934712292e-05,
|
| 849 |
+
"loss": 0.4634,
|
| 850 |
+
"step": 600
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.6861924686192469,
|
| 854 |
+
"grad_norm": 1.29376220703125,
|
| 855 |
+
"learning_rate": 1.3230649242737312e-05,
|
| 856 |
+
"loss": 0.4417,
|
| 857 |
+
"step": 605
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.700139470013947,
|
| 861 |
+
"grad_norm": 1.114341139793396,
|
| 862 |
+
"learning_rate": 1.3002152702339678e-05,
|
| 863 |
+
"loss": 0.4284,
|
| 864 |
+
"step": 610
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.7140864714086472,
|
| 868 |
+
"grad_norm": 1.1611167192459106,
|
| 869 |
+
"learning_rate": 1.2774127185083212e-05,
|
| 870 |
+
"loss": 0.4176,
|
| 871 |
+
"step": 615
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.7280334728033473,
|
| 875 |
+
"grad_norm": 1.2490227222442627,
|
| 876 |
+
"learning_rate": 1.2546626451480808e-05,
|
| 877 |
+
"loss": 0.4379,
|
| 878 |
+
"step": 620
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.7419804741980474,
|
| 882 |
+
"grad_norm": 1.101513385772705,
|
| 883 |
+
"learning_rate": 1.2319704138319558e-05,
|
| 884 |
+
"loss": 0.4241,
|
| 885 |
+
"step": 625
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.7559274755927476,
|
| 889 |
+
"grad_norm": 1.1283235549926758,
|
| 890 |
+
"learning_rate": 1.2093413746015079e-05,
|
| 891 |
+
"loss": 0.4851,
|
| 892 |
+
"step": 630
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.7698744769874477,
|
| 896 |
+
"grad_norm": 1.2496988773345947,
|
| 897 |
+
"learning_rate": 1.1867808625997936e-05,
|
| 898 |
+
"loss": 0.401,
|
| 899 |
+
"step": 635
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.7838214783821478,
|
| 903 |
+
"grad_norm": 1.29635751247406,
|
| 904 |
+
"learning_rate": 1.164294196813526e-05,
|
| 905 |
+
"loss": 0.3992,
|
| 906 |
+
"step": 640
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.797768479776848,
|
| 910 |
+
"grad_norm": 1.143762469291687,
|
| 911 |
+
"learning_rate": 1.1418866788190394e-05,
|
| 912 |
+
"loss": 0.4257,
|
| 913 |
+
"step": 645
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.8117154811715481,
|
| 917 |
+
"grad_norm": 1.1981691122055054,
|
| 918 |
+
"learning_rate": 1.1195635915323622e-05,
|
| 919 |
+
"loss": 0.4289,
|
| 920 |
+
"step": 650
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.8256624825662482,
|
| 924 |
+
"grad_norm": 1.2914341688156128,
|
| 925 |
+
"learning_rate": 1.0973301979636888e-05,
|
| 926 |
+
"loss": 0.436,
|
| 927 |
+
"step": 655
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.8396094839609485,
|
| 931 |
+
"grad_norm": 1.2486486434936523,
|
| 932 |
+
"learning_rate": 1.075191739976544e-05,
|
| 933 |
+
"loss": 0.4496,
|
| 934 |
+
"step": 660
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.8535564853556485,
|
| 938 |
+
"grad_norm": 1.2522389888763428,
|
| 939 |
+
"learning_rate": 1.053153437051933e-05,
|
| 940 |
+
"loss": 0.4012,
|
| 941 |
+
"step": 665
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.8675034867503486,
|
| 945 |
+
"grad_norm": 1.161327600479126,
|
| 946 |
+
"learning_rate": 1.0312204850577687e-05,
|
| 947 |
+
"loss": 0.4373,
|
| 948 |
+
"step": 670
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.881450488145049,
|
| 952 |
+
"grad_norm": 1.268589973449707,
|
| 953 |
+
"learning_rate": 1.0093980550238676e-05,
|
| 954 |
+
"loss": 0.4333,
|
| 955 |
+
"step": 675
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.895397489539749,
|
| 959 |
+
"grad_norm": 1.1720470190048218,
|
| 960 |
+
"learning_rate": 9.876912919227976e-06,
|
| 961 |
+
"loss": 0.4371,
|
| 962 |
+
"step": 680
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.909344490934449,
|
| 966 |
+
"grad_norm": 1.2306352853775024,
|
| 967 |
+
"learning_rate": 9.66105313456874e-06,
|
| 968 |
+
"loss": 0.4109,
|
| 969 |
+
"step": 685
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.9232914923291493,
|
| 973 |
+
"grad_norm": 1.320695400238037,
|
| 974 |
+
"learning_rate": 9.44645208851582e-06,
|
| 975 |
+
"loss": 0.4392,
|
| 976 |
+
"step": 690
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.9372384937238494,
|
| 980 |
+
"grad_norm": 1.1919153928756714,
|
| 981 |
+
"learning_rate": 9.233160376557125e-06,
|
| 982 |
+
"loss": 0.3803,
|
| 983 |
+
"step": 695
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.9511854951185494,
|
| 987 |
+
"grad_norm": 1.2437540292739868,
|
| 988 |
+
"learning_rate": 9.021228285484985e-06,
|
| 989 |
+
"loss": 0.4159,
|
| 990 |
+
"step": 700
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.9651324965132497,
|
| 994 |
+
"grad_norm": 1.2799781560897827,
|
| 995 |
+
"learning_rate": 8.810705781540247e-06,
|
| 996 |
+
"loss": 0.4303,
|
| 997 |
+
"step": 705
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.9790794979079498,
|
| 1001 |
+
"grad_norm": 1.1391472816467285,
|
| 1002 |
+
"learning_rate": 8.601642498631973e-06,
|
| 1003 |
+
"loss": 0.3875,
|
| 1004 |
+
"step": 710
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.9930264993026499,
|
| 1008 |
+
"grad_norm": 1.2021998167037964,
|
| 1009 |
+
"learning_rate": 8.394087726635483e-06,
|
| 1010 |
+
"loss": 0.3914,
|
| 1011 |
+
"step": 715
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.00557880055788,
|
| 1015 |
+
"grad_norm": 1.1943093538284302,
|
| 1016 |
+
"learning_rate": 8.188090399771533e-06,
|
| 1017 |
+
"loss": 0.3746,
|
| 1018 |
+
"step": 720
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.01952580195258,
|
| 1022 |
+
"grad_norm": 1.3413909673690796,
|
| 1023 |
+
"learning_rate": 7.983699085069267e-06,
|
| 1024 |
+
"loss": 0.3322,
|
| 1025 |
+
"step": 725
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.0334728033472804,
|
| 1029 |
+
"grad_norm": 1.1652683019638062,
|
| 1030 |
+
"learning_rate": 7.780961970915867e-06,
|
| 1031 |
+
"loss": 0.3324,
|
| 1032 |
+
"step": 730
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.0474198047419803,
|
| 1036 |
+
"grad_norm": 1.2593529224395752,
|
| 1037 |
+
"learning_rate": 7.579926855695338e-06,
|
| 1038 |
+
"loss": 0.3625,
|
| 1039 |
+
"step": 735
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.0613668061366806,
|
| 1043 |
+
"grad_norm": 1.2410223484039307,
|
| 1044 |
+
"learning_rate": 7.3806411365193585e-06,
|
| 1045 |
+
"loss": 0.3246,
|
| 1046 |
+
"step": 740
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.075313807531381,
|
| 1050 |
+
"grad_norm": 1.10285222530365,
|
| 1051 |
+
"learning_rate": 7.183151798052628e-06,
|
| 1052 |
+
"loss": 0.3265,
|
| 1053 |
+
"step": 745
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.0892608089260807,
|
| 1057 |
+
"grad_norm": 1.2353794574737549,
|
| 1058 |
+
"learning_rate": 6.987505401435571e-06,
|
| 1059 |
+
"loss": 0.3147,
|
| 1060 |
+
"step": 750
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.103207810320781,
|
| 1064 |
+
"grad_norm": 1.2734289169311523,
|
| 1065 |
+
"learning_rate": 6.793748073306796e-06,
|
| 1066 |
+
"loss": 0.3248,
|
| 1067 |
+
"step": 755
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.1171548117154813,
|
| 1071 |
+
"grad_norm": 1.152282953262329,
|
| 1072 |
+
"learning_rate": 6.601925494928032e-06,
|
| 1073 |
+
"loss": 0.329,
|
| 1074 |
+
"step": 760
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.131101813110181,
|
| 1078 |
+
"grad_norm": 1.2059096097946167,
|
| 1079 |
+
"learning_rate": 6.412082891414109e-06,
|
| 1080 |
+
"loss": 0.3274,
|
| 1081 |
+
"step": 765
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.1450488145048814,
|
| 1085 |
+
"grad_norm": 1.2305474281311035,
|
| 1086 |
+
"learning_rate": 6.224265021070383e-06,
|
| 1087 |
+
"loss": 0.3297,
|
| 1088 |
+
"step": 770
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.1589958158995817,
|
| 1092 |
+
"grad_norm": 1.2619471549987793,
|
| 1093 |
+
"learning_rate": 6.038516164840341e-06,
|
| 1094 |
+
"loss": 0.3344,
|
| 1095 |
+
"step": 775
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.172942817294282,
|
| 1099 |
+
"grad_norm": 1.2583692073822021,
|
| 1100 |
+
"learning_rate": 5.854880115865632e-06,
|
| 1101 |
+
"loss": 0.3225,
|
| 1102 |
+
"step": 780
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.186889818688982,
|
| 1106 |
+
"grad_norm": 1.1709176301956177,
|
| 1107 |
+
"learning_rate": 5.673400169161221e-06,
|
| 1108 |
+
"loss": 0.3265,
|
| 1109 |
+
"step": 785
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.200836820083682,
|
| 1113 |
+
"grad_norm": 1.2599228620529175,
|
| 1114 |
+
"learning_rate": 5.494119111407865e-06,
|
| 1115 |
+
"loss": 0.3249,
|
| 1116 |
+
"step": 790
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.214783821478382,
|
| 1120 |
+
"grad_norm": 1.2965203523635864,
|
| 1121 |
+
"learning_rate": 5.31707921086455e-06,
|
| 1122 |
+
"loss": 0.2921,
|
| 1123 |
+
"step": 795
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.228730822873082,
|
| 1127 |
+
"grad_norm": 1.2999876737594604,
|
| 1128 |
+
"learning_rate": 5.142322207403074e-06,
|
| 1129 |
+
"loss": 0.2948,
|
| 1130 |
+
"step": 800
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.2426778242677825,
|
| 1134 |
+
"grad_norm": 1.3367228507995605,
|
| 1135 |
+
"learning_rate": 4.969889302667217e-06,
|
| 1136 |
+
"loss": 0.3425,
|
| 1137 |
+
"step": 805
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.256624825662483,
|
| 1141 |
+
"grad_norm": 1.3120561838150024,
|
| 1142 |
+
"learning_rate": 4.799821150358864e-06,
|
| 1143 |
+
"loss": 0.3243,
|
| 1144 |
+
"step": 810
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.2705718270571826,
|
| 1148 |
+
"grad_norm": 1.4088741540908813,
|
| 1149 |
+
"learning_rate": 4.632157846653229e-06,
|
| 1150 |
+
"loss": 0.2955,
|
| 1151 |
+
"step": 815
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.284518828451883,
|
| 1155 |
+
"grad_norm": 1.2665886878967285,
|
| 1156 |
+
"learning_rate": 4.466938920745602e-06,
|
| 1157 |
+
"loss": 0.3141,
|
| 1158 |
+
"step": 820
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.2984658298465828,
|
| 1162 |
+
"grad_norm": 1.307089924812317,
|
| 1163 |
+
"learning_rate": 4.304203325531697e-06,
|
| 1164 |
+
"loss": 0.3006,
|
| 1165 |
+
"step": 825
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.312412831241283,
|
| 1169 |
+
"grad_norm": 1.1148992776870728,
|
| 1170 |
+
"learning_rate": 4.1439894284239474e-06,
|
| 1171 |
+
"loss": 0.2835,
|
| 1172 |
+
"step": 830
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.3263598326359833,
|
| 1176 |
+
"grad_norm": 1.207263708114624,
|
| 1177 |
+
"learning_rate": 3.986335002305783e-06,
|
| 1178 |
+
"loss": 0.2884,
|
| 1179 |
+
"step": 835
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.3403068340306836,
|
| 1183 |
+
"grad_norm": 1.196489691734314,
|
| 1184 |
+
"learning_rate": 3.831277216626077e-06,
|
| 1185 |
+
"loss": 0.292,
|
| 1186 |
+
"step": 840
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.3542538354253835,
|
| 1190 |
+
"grad_norm": 1.204256534576416,
|
| 1191 |
+
"learning_rate": 3.678852628635919e-06,
|
| 1192 |
+
"loss": 0.2942,
|
| 1193 |
+
"step": 845
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.3682008368200838,
|
| 1197 |
+
"grad_norm": 1.4431132078170776,
|
| 1198 |
+
"learning_rate": 3.5290971747696323e-06,
|
| 1199 |
+
"loss": 0.2963,
|
| 1200 |
+
"step": 850
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.3821478382147836,
|
| 1204 |
+
"grad_norm": 1.3184531927108765,
|
| 1205 |
+
"learning_rate": 3.382046162172254e-06,
|
| 1206 |
+
"loss": 0.2962,
|
| 1207 |
+
"step": 855
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.396094839609484,
|
| 1211 |
+
"grad_norm": 1.1647268533706665,
|
| 1212 |
+
"learning_rate": 3.237734260375311e-06,
|
| 1213 |
+
"loss": 0.2889,
|
| 1214 |
+
"step": 860
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.410041841004184,
|
| 1218 |
+
"grad_norm": 1.1136646270751953,
|
| 1219 |
+
"learning_rate": 3.0961954931229385e-06,
|
| 1220 |
+
"loss": 0.3008,
|
| 1221 |
+
"step": 865
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.4239888423988845,
|
| 1225 |
+
"grad_norm": 1.1104133129119873,
|
| 1226 |
+
"learning_rate": 2.9574632303502874e-06,
|
| 1227 |
+
"loss": 0.2868,
|
| 1228 |
+
"step": 870
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.4379358437935843,
|
| 1232 |
+
"grad_norm": 1.25339937210083,
|
| 1233 |
+
"learning_rate": 2.8215701803160175e-06,
|
| 1234 |
+
"loss": 0.3126,
|
| 1235 |
+
"step": 875
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.4518828451882846,
|
| 1239 |
+
"grad_norm": 1.2157018184661865,
|
| 1240 |
+
"learning_rate": 2.688548381890859e-06,
|
| 1241 |
+
"loss": 0.3113,
|
| 1242 |
+
"step": 880
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.4658298465829844,
|
| 1246 |
+
"grad_norm": 1.1960946321487427,
|
| 1247 |
+
"learning_rate": 2.558429197003922e-06,
|
| 1248 |
+
"loss": 0.2595,
|
| 1249 |
+
"step": 885
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.4797768479776847,
|
| 1253 |
+
"grad_norm": 1.2948330640792847,
|
| 1254 |
+
"learning_rate": 2.4312433032486687e-06,
|
| 1255 |
+
"loss": 0.313,
|
| 1256 |
+
"step": 890
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.493723849372385,
|
| 1260 |
+
"grad_norm": 1.1419775485992432,
|
| 1261 |
+
"learning_rate": 2.307020686650187e-06,
|
| 1262 |
+
"loss": 0.3195,
|
| 1263 |
+
"step": 895
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.5076708507670853,
|
| 1267 |
+
"grad_norm": 1.2405985593795776,
|
| 1268 |
+
"learning_rate": 2.1857906345955277e-06,
|
| 1269 |
+
"loss": 0.309,
|
| 1270 |
+
"step": 900
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.521617852161785,
|
| 1274 |
+
"grad_norm": 1.183632731437683,
|
| 1275 |
+
"learning_rate": 2.067581728928757e-06,
|
| 1276 |
+
"loss": 0.2714,
|
| 1277 |
+
"step": 905
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.5355648535564854,
|
| 1281 |
+
"grad_norm": 1.1886118650436401,
|
| 1282 |
+
"learning_rate": 1.952421839212336e-06,
|
| 1283 |
+
"loss": 0.2627,
|
| 1284 |
+
"step": 910
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.5495118549511853,
|
| 1288 |
+
"grad_norm": 1.200496792793274,
|
| 1289 |
+
"learning_rate": 1.840338116156462e-06,
|
| 1290 |
+
"loss": 0.3053,
|
| 1291 |
+
"step": 915
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.5634588563458856,
|
| 1295 |
+
"grad_norm": 1.3056796789169312,
|
| 1296 |
+
"learning_rate": 1.7313569852178573e-06,
|
| 1297 |
+
"loss": 0.3076,
|
| 1298 |
+
"step": 920
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.577405857740586,
|
| 1302 |
+
"grad_norm": 1.343036413192749,
|
| 1303 |
+
"learning_rate": 1.6255041403695748e-06,
|
| 1304 |
+
"loss": 0.264,
|
| 1305 |
+
"step": 925
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.591352859135286,
|
| 1309 |
+
"grad_norm": 1.1288245916366577,
|
| 1310 |
+
"learning_rate": 1.5228045380432353e-06,
|
| 1311 |
+
"loss": 0.3135,
|
| 1312 |
+
"step": 930
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.605299860529986,
|
| 1316 |
+
"grad_norm": 1.2103605270385742,
|
| 1317 |
+
"learning_rate": 1.4232823912451808e-06,
|
| 1318 |
+
"loss": 0.312,
|
| 1319 |
+
"step": 935
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.6192468619246863,
|
| 1323 |
+
"grad_norm": 1.324729561805725,
|
| 1324 |
+
"learning_rate": 1.326961163847883e-06,
|
| 1325 |
+
"loss": 0.3128,
|
| 1326 |
+
"step": 940
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.633193863319386,
|
| 1330 |
+
"grad_norm": 1.3358917236328125,
|
| 1331 |
+
"learning_rate": 1.2338635650579583e-06,
|
| 1332 |
+
"loss": 0.2964,
|
| 1333 |
+
"step": 945
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 2.6471408647140864,
|
| 1337 |
+
"grad_norm": 1.3783016204833984,
|
| 1338 |
+
"learning_rate": 1.1440115440621584e-06,
|
| 1339 |
+
"loss": 0.2718,
|
| 1340 |
+
"step": 950
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 2.6610878661087867,
|
| 1344 |
+
"grad_norm": 1.280258297920227,
|
| 1345 |
+
"learning_rate": 1.0574262848524725e-06,
|
| 1346 |
+
"loss": 0.3109,
|
| 1347 |
+
"step": 955
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 2.675034867503487,
|
| 1351 |
+
"grad_norm": 1.0824254751205444,
|
| 1352 |
+
"learning_rate": 9.74128201231713e-07,
|
| 1353 |
+
"loss": 0.319,
|
| 1354 |
+
"step": 960
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 2.688981868898187,
|
| 1358 |
+
"grad_norm": 1.2345054149627686,
|
| 1359 |
+
"learning_rate": 8.941369320006298e-07,
|
| 1360 |
+
"loss": 0.2631,
|
| 1361 |
+
"step": 965
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 2.702928870292887,
|
| 1365 |
+
"grad_norm": 1.3091744184494019,
|
| 1366 |
+
"learning_rate": 8.174713363277508e-07,
|
| 1367 |
+
"loss": 0.3154,
|
| 1368 |
+
"step": 970
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.716875871687587,
|
| 1372 |
+
"grad_norm": 1.0909289121627808,
|
| 1373 |
+
"learning_rate": 7.44149489303076e-07,
|
| 1374 |
+
"loss": 0.3036,
|
| 1375 |
+
"step": 975
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 2.730822873082287,
|
| 1379 |
+
"grad_norm": 1.122246503829956,
|
| 1380 |
+
"learning_rate": 6.741886776765649e-07,
|
| 1381 |
+
"loss": 0.3063,
|
| 1382 |
+
"step": 980
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 2.7447698744769875,
|
| 1386 |
+
"grad_norm": 1.1169829368591309,
|
| 1387 |
+
"learning_rate": 6.076053957825411e-07,
|
| 1388 |
+
"loss": 0.2689,
|
| 1389 |
+
"step": 985
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 2.758716875871688,
|
| 1393 |
+
"grad_norm": 1.1027191877365112,
|
| 1394 |
+
"learning_rate": 5.444153416508873e-07,
|
| 1395 |
+
"loss": 0.2896,
|
| 1396 |
+
"step": 990
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 2.7726638772663876,
|
| 1400 |
+
"grad_norm": 1.2159665822982788,
|
| 1401 |
+
"learning_rate": 4.846334133060077e-07,
|
| 1402 |
+
"loss": 0.3074,
|
| 1403 |
+
"step": 995
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 2.786610878661088,
|
| 1407 |
+
"grad_norm": 1.23433256149292,
|
| 1408 |
+
"learning_rate": 4.2827370525437723e-07,
|
| 1409 |
+
"loss": 0.3161,
|
| 1410 |
+
"step": 1000
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.8005578800557878,
|
| 1414 |
+
"grad_norm": 1.1383460760116577,
|
| 1415 |
+
"learning_rate": 3.753495051615491e-07,
|
| 1416 |
+
"loss": 0.2753,
|
| 1417 |
+
"step": 1005
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 2.814504881450488,
|
| 1421 |
+
"grad_norm": 1.2525423765182495,
|
| 1422 |
+
"learning_rate": 3.2587329071938954e-07,
|
| 1423 |
+
"loss": 0.298,
|
| 1424 |
+
"step": 1010
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 2.8284518828451883,
|
| 1428 |
+
"grad_norm": 1.123475193977356,
|
| 1429 |
+
"learning_rate": 2.798567267042601e-07,
|
| 1430 |
+
"loss": 0.2952,
|
| 1431 |
+
"step": 1015
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 2.8423988842398886,
|
| 1435 |
+
"grad_norm": 1.297455072402954,
|
| 1436 |
+
"learning_rate": 2.3731066222688224e-07,
|
| 1437 |
+
"loss": 0.264,
|
| 1438 |
+
"step": 1020
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 2.8563458856345885,
|
| 1442 |
+
"grad_norm": 1.2938209772109985,
|
| 1443 |
+
"learning_rate": 1.982451281744785e-07,
|
| 1444 |
+
"loss": 0.2783,
|
| 1445 |
+
"step": 1025
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 2.8702928870292888,
|
| 1449 |
+
"grad_norm": 1.4270787239074707,
|
| 1450 |
+
"learning_rate": 1.6266933484584578e-07,
|
| 1451 |
+
"loss": 0.2915,
|
| 1452 |
+
"step": 1030
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.8842398884239886,
|
| 1456 |
+
"grad_norm": 1.3201574087142944,
|
| 1457 |
+
"learning_rate": 1.3059166977988258e-07,
|
| 1458 |
+
"loss": 0.3216,
|
| 1459 |
+
"step": 1035
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 2.898186889818689,
|
| 1463 |
+
"grad_norm": 1.1863285303115845,
|
| 1464 |
+
"learning_rate": 1.0201969577809889e-07,
|
| 1465 |
+
"loss": 0.3165,
|
| 1466 |
+
"step": 1040
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 2.912133891213389,
|
| 1470 |
+
"grad_norm": 1.1032975912094116,
|
| 1471 |
+
"learning_rate": 7.696014912157267e-08,
|
| 1472 |
+
"loss": 0.2868,
|
| 1473 |
+
"step": 1045
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 2.9260808926080895,
|
| 1477 |
+
"grad_norm": 1.388165831565857,
|
| 1478 |
+
"learning_rate": 5.5418937982761875e-08,
|
| 1479 |
+
"loss": 0.2937,
|
| 1480 |
+
"step": 1050
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 2.9400278940027893,
|
| 1484 |
+
"grad_norm": 1.407028317451477,
|
| 1485 |
+
"learning_rate": 3.7401141032566975e-08,
|
| 1486 |
+
"loss": 0.296,
|
| 1487 |
+
"step": 1055
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 2.9539748953974896,
|
| 1491 |
+
"grad_norm": 1.1984119415283203,
|
| 1492 |
+
"learning_rate": 2.29110062429555e-08,
|
| 1493 |
+
"loss": 0.2866,
|
| 1494 |
+
"step": 1060
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.9679218967921894,
|
| 1498 |
+
"grad_norm": 1.152653455734253,
|
| 1499 |
+
"learning_rate": 1.1951949885439794e-08,
|
| 1500 |
+
"loss": 0.305,
|
| 1501 |
+
"step": 1065
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 2.9818688981868897,
|
| 1505 |
+
"grad_norm": 1.2716338634490967,
|
| 1506 |
+
"learning_rate": 4.526555725631321e-09,
|
| 1507 |
+
"loss": 0.2937,
|
| 1508 |
+
"step": 1070
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 2.99581589958159,
|
| 1512 |
+
"grad_norm": 1.1536885499954224,
|
| 1513 |
+
"learning_rate": 6.365744140879315e-10,
|
| 1514 |
+
"loss": 0.2845,
|
| 1515 |
+
"step": 1075
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 3.0,
|
| 1519 |
+
"step": 1077,
|
| 1520 |
+
"total_flos": 1.5565310221311017e+18,
|
| 1521 |
+
"train_loss": 0.579777075055582,
|
| 1522 |
+
"train_runtime": 706.5394,
|
| 1523 |
+
"train_samples_per_second": 48.66,
|
| 1524 |
+
"train_steps_per_second": 1.524
|
| 1525 |
+
}
|
| 1526 |
+
],
|
| 1527 |
+
"logging_steps": 5,
|
| 1528 |
+
"max_steps": 1077,
|
| 1529 |
+
"num_input_tokens_seen": 0,
|
| 1530 |
+
"num_train_epochs": 3,
|
| 1531 |
+
"save_steps": 2000,
|
| 1532 |
+
"stateful_callbacks": {
|
| 1533 |
+
"TrainerControl": {
|
| 1534 |
+
"args": {
|
| 1535 |
+
"should_epoch_stop": false,
|
| 1536 |
+
"should_evaluate": false,
|
| 1537 |
+
"should_log": false,
|
| 1538 |
+
"should_save": false,
|
| 1539 |
+
"should_training_stop": false
|
| 1540 |
+
},
|
| 1541 |
+
"attributes": {}
|
| 1542 |
+
}
|
| 1543 |
+
},
|
| 1544 |
+
"total_flos": 1.5565310221311017e+18,
|
| 1545 |
+
"train_batch_size": 2,
|
| 1546 |
+
"trial_name": null,
|
| 1547 |
+
"trial_params": null
|
| 1548 |
+
}
|
18_128_e3_3e-5/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d6c9f6fe3a5e1ada0a2b4155af0a8c8852927e8972d6324fc5f8b4587568c9d
|
| 3 |
+
size 8145
|
18_128_e3_3e-5/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|