Model save
Browse files- README.md +67 -0
- all_results.json +9 -0
- config.json +30 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Sep20_12-08-36_ip-26-0-168-120/events.out.tfevents.1726835177.ip-26-0-168-120.4123050.0 +3 -0
- special_tokens_map.json +28 -0
- tokenizer.json +0 -0
- tokenizer_config.json +154 -0
- train_results.json +9 -0
- trainer_state.json +197 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: loubnabnl/smollm-1.7b-16k
|
3 |
+
tags:
|
4 |
+
- trl
|
5 |
+
- sft
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- generator
|
9 |
+
model-index:
|
10 |
+
- name: smollm-1.7B-16k-instruct-v0
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/7rd4806f)
|
18 |
+
# smollm-1.7B-16k-instruct-v0
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [loubnabnl/smollm-1.7b-16k](https://huggingface.co/loubnabnl/smollm-1.7b-16k) on the generator dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.0118
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.001
|
42 |
+
- train_batch_size: 4
|
43 |
+
- eval_batch_size: 4
|
44 |
+
- seed: 42
|
45 |
+
- distributed_type: multi-GPU
|
46 |
+
- num_devices: 8
|
47 |
+
- gradient_accumulation_steps: 4
|
48 |
+
- total_train_batch_size: 128
|
49 |
+
- total_eval_batch_size: 32
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: cosine
|
52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
53 |
+
- num_epochs: 1
|
54 |
+
|
55 |
+
### Training results
|
56 |
+
|
57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
58 |
+
|:-------------:|:------:|:----:|:---------------:|
|
59 |
+
| 0.6674 | 0.9951 | 102 | 1.0118 |
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- Transformers 4.42.3
|
65 |
+
- Pytorch 2.1.2
|
66 |
+
- Datasets 2.20.0
|
67 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9951219512195122,
|
3 |
+
"total_flos": 128481799176192.0,
|
4 |
+
"train_loss": 0.7558732021088693,
|
5 |
+
"train_runtime": 2589.5829,
|
6 |
+
"train_samples": 321330,
|
7 |
+
"train_samples_per_second": 5.059,
|
8 |
+
"train_steps_per_second": 0.039
|
9 |
+
}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "loubnabnl/smollm-1.7b-16k",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 8192,
|
14 |
+
"max_position_embeddings": 16384,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"num_key_value_heads": 32,
|
20 |
+
"pad_token_id": 2,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 273768.0,
|
25 |
+
"tie_word_embeddings": true,
|
26 |
+
"torch_dtype": "bfloat16",
|
27 |
+
"transformers_version": "4.42.3",
|
28 |
+
"use_cache": false,
|
29 |
+
"vocab_size": 49152
|
30 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 2,
|
6 |
+
"transformers_version": "4.42.3"
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c189fa7f341c47f0289162c461b0e937ed687df099372ceb93d21cbc2b6754b
|
3 |
+
size 3422777952
|
runs/Sep20_12-08-36_ip-26-0-168-120/events.out.tfevents.1726835177.ip-26-0-168-120.4123050.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ad99f9c35fb3a3706cdd1c0b29b1840becedbef3baa46cd633b76fafe13e7b9
|
3 |
+
size 10036
|
special_tokens_map.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|im_start|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|im_end|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
}
|
17 |
+
],
|
18 |
+
"bos_token": "<|im_start|>",
|
19 |
+
"eos_token": "<|im_end|>",
|
20 |
+
"pad_token": "<|im_end|>",
|
21 |
+
"unk_token": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
}
|
28 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<repo_name>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"4": {
|
37 |
+
"content": "<reponame>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"5": {
|
45 |
+
"content": "<file_sep>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"6": {
|
53 |
+
"content": "<filename>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"7": {
|
61 |
+
"content": "<gh_stars>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"8": {
|
69 |
+
"content": "<issue_start>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"9": {
|
77 |
+
"content": "<issue_comment>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"10": {
|
85 |
+
"content": "<issue_closed>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"11": {
|
93 |
+
"content": "<jupyter_start>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"12": {
|
101 |
+
"content": "<jupyter_text>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"13": {
|
109 |
+
"content": "<jupyter_code>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"14": {
|
117 |
+
"content": "<jupyter_output>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"15": {
|
125 |
+
"content": "<jupyter_script>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"16": {
|
133 |
+
"content": "<empty_output>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
}
|
140 |
+
},
|
141 |
+
"additional_special_tokens": [
|
142 |
+
"<|im_start|>",
|
143 |
+
"<|im_end|>"
|
144 |
+
],
|
145 |
+
"bos_token": "<|im_start|>",
|
146 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
147 |
+
"clean_up_tokenization_spaces": false,
|
148 |
+
"eos_token": "<|im_end|>",
|
149 |
+
"model_max_length": 2048,
|
150 |
+
"pad_token": "<|im_end|>",
|
151 |
+
"tokenizer_class": "GPT2Tokenizer",
|
152 |
+
"unk_token": "<|endoftext|>",
|
153 |
+
"vocab_size": 49152
|
154 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9951219512195122,
|
3 |
+
"total_flos": 128481799176192.0,
|
4 |
+
"train_loss": 0.7558732021088693,
|
5 |
+
"train_runtime": 2589.5829,
|
6 |
+
"train_samples": 321330,
|
7 |
+
"train_samples_per_second": 5.059,
|
8 |
+
"train_steps_per_second": 0.039
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9951219512195122,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 102,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.00975609756097561,
|
13 |
+
"grad_norm": 6.261786177237342,
|
14 |
+
"learning_rate": 9.090909090909092e-05,
|
15 |
+
"loss": 1.1256,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04878048780487805,
|
20 |
+
"grad_norm": 2.1112596954065914,
|
21 |
+
"learning_rate": 0.00045454545454545455,
|
22 |
+
"loss": 1.049,
|
23 |
+
"step": 5
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0975609756097561,
|
27 |
+
"grad_norm": 1.5895813487100507,
|
28 |
+
"learning_rate": 0.0009090909090909091,
|
29 |
+
"loss": 1.0974,
|
30 |
+
"step": 10
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.14634146341463414,
|
34 |
+
"grad_norm": 0.32863787167794134,
|
35 |
+
"learning_rate": 0.0009952402219937815,
|
36 |
+
"loss": 0.9164,
|
37 |
+
"step": 15
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.1951219512195122,
|
41 |
+
"grad_norm": 0.23963144918280163,
|
42 |
+
"learning_rate": 0.0009760588329553571,
|
43 |
+
"loss": 0.8434,
|
44 |
+
"step": 20
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.24390243902439024,
|
48 |
+
"grad_norm": 0.14493890865001488,
|
49 |
+
"learning_rate": 0.0009427280128266049,
|
50 |
+
"loss": 0.8011,
|
51 |
+
"step": 25
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2926829268292683,
|
55 |
+
"grad_norm": 0.12052712473534186,
|
56 |
+
"learning_rate": 0.0008962384209755452,
|
57 |
+
"loss": 0.7652,
|
58 |
+
"step": 30
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.34146341463414637,
|
62 |
+
"grad_norm": 0.0981844421832599,
|
63 |
+
"learning_rate": 0.0008379718220723773,
|
64 |
+
"loss": 0.7453,
|
65 |
+
"step": 35
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3902439024390244,
|
69 |
+
"grad_norm": 0.18540719570949135,
|
70 |
+
"learning_rate": 0.0007696600172495997,
|
71 |
+
"loss": 0.7317,
|
72 |
+
"step": 40
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.43902439024390244,
|
76 |
+
"grad_norm": 0.12172997652512386,
|
77 |
+
"learning_rate": 0.0006933333714707094,
|
78 |
+
"loss": 0.7179,
|
79 |
+
"step": 45
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.4878048780487805,
|
83 |
+
"grad_norm": 0.1050067175867305,
|
84 |
+
"learning_rate": 0.0006112604669781572,
|
85 |
+
"loss": 0.7047,
|
86 |
+
"step": 50
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5365853658536586,
|
90 |
+
"grad_norm": 0.0824375568337565,
|
91 |
+
"learning_rate": 0.0005258806764421047,
|
92 |
+
"loss": 0.6991,
|
93 |
+
"step": 55
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5853658536585366,
|
97 |
+
"grad_norm": 0.09661916029526949,
|
98 |
+
"learning_rate": 0.00043973165987233853,
|
99 |
+
"loss": 0.6865,
|
100 |
+
"step": 60
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.6341463414634146,
|
104 |
+
"grad_norm": 0.07527219081930579,
|
105 |
+
"learning_rate": 0.0003553739402317162,
|
106 |
+
"loss": 0.6833,
|
107 |
+
"step": 65
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6829268292682927,
|
111 |
+
"grad_norm": 0.07406811411334399,
|
112 |
+
"learning_rate": 0.00027531479951641924,
|
113 |
+
"loss": 0.6793,
|
114 |
+
"step": 70
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.7317073170731707,
|
118 |
+
"grad_norm": 0.21265879474641486,
|
119 |
+
"learning_rate": 0.00020193375726538737,
|
120 |
+
"loss": 0.6726,
|
121 |
+
"step": 75
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.7804878048780488,
|
125 |
+
"grad_norm": 0.06699755926217109,
|
126 |
+
"learning_rate": 0.0001374118464283119,
|
127 |
+
"loss": 0.6685,
|
128 |
+
"step": 80
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.8292682926829268,
|
132 |
+
"grad_norm": 0.0915919461803413,
|
133 |
+
"learning_rate": 8.366678865639687e-05,
|
134 |
+
"loss": 0.6716,
|
135 |
+
"step": 85
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.8780487804878049,
|
139 |
+
"grad_norm": 0.06490947271665126,
|
140 |
+
"learning_rate": 4.2295995737316854e-05,
|
141 |
+
"loss": 0.6692,
|
142 |
+
"step": 90
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.926829268292683,
|
146 |
+
"grad_norm": 0.1069137841001841,
|
147 |
+
"learning_rate": 1.4529091286973995e-05,
|
148 |
+
"loss": 0.6654,
|
149 |
+
"step": 95
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.975609756097561,
|
153 |
+
"grad_norm": 0.043578368206132125,
|
154 |
+
"learning_rate": 1.1913638493762368e-06,
|
155 |
+
"loss": 0.6674,
|
156 |
+
"step": 100
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.9951219512195122,
|
160 |
+
"eval_loss": 1.0117870569229126,
|
161 |
+
"eval_runtime": 125.6267,
|
162 |
+
"eval_samples_per_second": 20.871,
|
163 |
+
"eval_steps_per_second": 0.653,
|
164 |
+
"step": 102
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.9951219512195122,
|
168 |
+
"step": 102,
|
169 |
+
"total_flos": 128481799176192.0,
|
170 |
+
"train_loss": 0.7558732021088693,
|
171 |
+
"train_runtime": 2589.5829,
|
172 |
+
"train_samples_per_second": 5.059,
|
173 |
+
"train_steps_per_second": 0.039
|
174 |
+
}
|
175 |
+
],
|
176 |
+
"logging_steps": 5,
|
177 |
+
"max_steps": 102,
|
178 |
+
"num_input_tokens_seen": 0,
|
179 |
+
"num_train_epochs": 1,
|
180 |
+
"save_steps": 500,
|
181 |
+
"stateful_callbacks": {
|
182 |
+
"TrainerControl": {
|
183 |
+
"args": {
|
184 |
+
"should_epoch_stop": false,
|
185 |
+
"should_evaluate": false,
|
186 |
+
"should_log": false,
|
187 |
+
"should_save": false,
|
188 |
+
"should_training_stop": false
|
189 |
+
},
|
190 |
+
"attributes": {}
|
191 |
+
}
|
192 |
+
},
|
193 |
+
"total_flos": 128481799176192.0,
|
194 |
+
"train_batch_size": 4,
|
195 |
+
"trial_name": null,
|
196 |
+
"trial_params": null
|
197 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5b552ff60fe9be12b76be82bbe1f7c0e6683b3fea9e4dda9abf21f03cc8277e
|
3 |
+
size 6392
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|