DorinSht commited on
Commit
10432a8
1 Parent(s): cb3cf8a

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "JackFram/llama-68m",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 2,
18
+ "num_key_value_heads": 12,
19
+ "pad_token_id": 1,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.41.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.41.0.dev0"
7
+ }
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47fea650ec741b07e6a187541e4217459975b8d59c02f835544382c220ca692
3
+ size 272123144
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a8aed857e58fca9787217eea0e79ed566fc87283905d5129d8c7a662387e4a5
3
+ size 544259743
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dac398be5f56dbc72468a9a99f3dccd46ef72a345b45f80d1e818b6cd90b1bef
3
+ size 1000
last-checkpoint/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 2048,
36
+ "pad_token": "<unk>",
37
+ "padding": "max_length",
38
+ "return_tensors": "pt",
39
+ "sp_model_kwargs": {},
40
+ "spaces_between_special_tokens": false,
41
+ "tokenizer_class": "LlamaTokenizer",
42
+ "unk_token": "<unk>",
43
+ "use_default_system_prompt": false,
44
+ "use_fast": true
45
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.26441036488630354,
5
+ "eval_steps": 1000,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.13220518244315177,
13
+ "grad_norm": 0.8546391725540161,
14
+ "learning_rate": 8.816009873931059e-05,
15
+ "loss": 5.1118,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.26441036488630354,
20
+ "grad_norm": 0.8593688607215881,
21
+ "learning_rate": 9.59831475011252e-05,
22
+ "loss": 3.406,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.26441036488630354,
27
+ "eval_accuracy": 0.5035306174465283,
28
+ "eval_loss": 3.23445987701416,
29
+ "eval_runtime": 73.8676,
30
+ "eval_samples_per_second": 24.909,
31
+ "eval_steps_per_second": 0.528,
32
+ "step": 1000
33
+ }
34
+ ],
35
+ "logging_steps": 500,
36
+ "max_steps": 11346,
37
+ "num_input_tokens_seen": 0,
38
+ "num_train_epochs": 3,
39
+ "save_steps": 1000,
40
+ "stateful_callbacks": {
41
+ "TrainerControl": {
42
+ "args": {
43
+ "should_epoch_stop": false,
44
+ "should_evaluate": false,
45
+ "should_log": false,
46
+ "should_save": true,
47
+ "should_training_stop": false
48
+ },
49
+ "attributes": {}
50
+ }
51
+ },
52
+ "total_flos": 1.2815167389696e+16,
53
+ "train_batch_size": 24,
54
+ "trial_name": null,
55
+ "trial_params": null
56
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ce5f4c1939d798f9579c06cb7c41ca4f80497b830ef82299a5b5b802ba651a2
3
+ size 5176