Jinchen commited on
Commit
e76c1eb
1 Parent(s): 23b0edb

Add fine-tuned model

Browse files
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - wikitext
7
+ model-index:
8
+ - name: clm_output
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # clm_output
16
+
17
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the wikitext wikitext-103-raw-v1 dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 2.9902
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 1e-05
39
+ - train_batch_size: 1
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - distributed_type: IPU
43
+ - gradient_accumulation_steps: 128
44
+ - total_train_batch_size: 1024
45
+ - total_eval_batch_size: 20
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 10.0
50
+ - training precision: Mixed Precision
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.18.0.dev0
59
+ - Pytorch 1.10.0+cpu
60
+ - Datasets 2.0.0
61
+ - Tokenizers 0.11.6
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_loss": 2.990234375,
4
+ "eval_runtime": 125.3791,
5
+ "eval_samples": 240,
6
+ "eval_samples_per_second": 1.914,
7
+ "eval_steps_per_second": 0.096,
8
+ "perplexity": 19.89034374461794,
9
+ "train_loss": 3.1787637246621623,
10
+ "train_runtime": 4372.4031,
11
+ "train_samples": 114248,
12
+ "train_samples_per_second": 261.293,
13
+ "train_steps_per_second": 0.254
14
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "PoptorchPipelinedGPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float16",
36
+ "transformers_version": "4.18.0.dev0",
37
+ "use_cache": true,
38
+ "vocab_size": 50257
39
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_loss": 2.990234375,
4
+ "eval_runtime": 125.3791,
5
+ "eval_samples": 240,
6
+ "eval_samples_per_second": 1.914,
7
+ "eval_steps_per_second": 0.096,
8
+ "perplexity": 19.89034374461794
9
+ }
ipu_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "device_iterations": 2,
3
+ "embedding_serialization_factor": 4,
4
+ "enable_half_first_order_momentum": true,
5
+ "enable_half_partials": true,
6
+ "executable_cache_dir": "./exe_cache",
7
+ "gradient_accumulation_steps": 128,
8
+ "inference_device_iterations": 5,
9
+ "inference_replication_factor": 4,
10
+ "ipus_per_replica": 4,
11
+ "layers_per_ipu": [
12
+ 0,
13
+ 4,
14
+ 4,
15
+ 4
16
+ ],
17
+ "matmul_proportion": 0.25,
18
+ "optimizer_state_offchip": true,
19
+ "optimum_version": "1.0.0",
20
+ "output_mode": "final",
21
+ "profile_dir": "",
22
+ "recompute_checkpoint_every_layer": true,
23
+ "replicated_tensor_sharding": true,
24
+ "replication_factor": 4,
25
+ "seed": 42,
26
+ "use_popdist": false
27
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b0f59559a81956e16aaa7d8482c91accb63851288c78a3e89f1f5df87ceac70
3
+ size 261514473
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 3.1787637246621623,
4
+ "train_runtime": 4372.4031,
5
+ "train_samples": 114248,
6
+ "train_samples_per_second": 261.293,
7
+ "train_steps_per_second": 0.254
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69aa9f555f383d982973dccbc5622239aa013a037a2e266e9451266070d1febd
3
+ size 2799
vocab.json ADDED
The diff for this file is too large to render. See raw diff