Upload folder using huggingface_hub
Browse files- checkpoint-396/config.json +30 -0
- checkpoint-396/generation_config.json +7 -0
- checkpoint-396/model.safetensors +3 -0
- checkpoint-396/optimizer.pt +3 -0
- checkpoint-396/rng_state.pth +3 -0
- checkpoint-396/scheduler.pt +3 -0
- checkpoint-396/special_tokens_map.json +24 -0
- checkpoint-396/tokenizer.json +0 -0
- checkpoint-396/tokenizer.model +3 -0
- checkpoint-396/tokenizer_config.json +42 -0
- checkpoint-396/trainer_state.json +385 -0
- checkpoint-396/training_args.bin +3 -0
- config.json +30 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- runs/Apr22_05-37-15_4f97a4faf13f/events.out.tfevents.1745300264.4f97a4faf13f.989.9 +3 -0
- runs/Apr22_05-38-08_4f97a4faf13f/events.out.tfevents.1745300349.4f97a4faf13f.989.10 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- training_args.bin +3 -0
checkpoint-396/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1024,
|
| 14 |
+
"max_position_embeddings": 256,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 6,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"num_key_value_heads": 6,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.51.3",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 32000
|
| 30 |
+
}
|
checkpoint-396/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": 0,
|
| 6 |
+
"transformers_version": "4.51.3"
|
| 7 |
+
}
|
checkpoint-396/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:275414a0c076db571ed3c7ef9229c919137297e56c68227309ded8272182e2f7
|
| 3 |
+
size 309900448
|
checkpoint-396/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3fbdaee14d249145f61d2a130f8893010639e48d8ae89cb9b798e3efabdd05fb
|
| 3 |
+
size 619836730
|
checkpoint-396/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
|
| 3 |
+
size 14244
|
checkpoint-396/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2db77dee59aa32a586c56bfbb61f6af6744a96b2a51f34eebb26e56720b232a
|
| 3 |
+
size 1064
|
checkpoint-396/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": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-396/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-396/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-396/tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 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 |
+
"extra_special_tokens": {},
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false
|
| 42 |
+
}
|
checkpoint-396/trainer_state.json
ADDED
|
@@ -0,0 +1,385 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 396,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.050505050505050504,
|
| 14 |
+
"grad_norm": 2.394207715988159,
|
| 15 |
+
"learning_rate": 1.9545454545454546e-05,
|
| 16 |
+
"loss": 5.1582,
|
| 17 |
+
"mean_token_accuracy": 0.2001233294606209,
|
| 18 |
+
"num_tokens": 870609.0,
|
| 19 |
+
"step": 10
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.10101010101010101,
|
| 23 |
+
"grad_norm": 1.912199854850769,
|
| 24 |
+
"learning_rate": 1.904040404040404e-05,
|
| 25 |
+
"loss": 4.9452,
|
| 26 |
+
"mean_token_accuracy": 0.2211832121014595,
|
| 27 |
+
"num_tokens": 1740025.0,
|
| 28 |
+
"step": 20
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.15151515151515152,
|
| 32 |
+
"grad_norm": 1.7625455856323242,
|
| 33 |
+
"learning_rate": 1.8535353535353537e-05,
|
| 34 |
+
"loss": 4.793,
|
| 35 |
+
"mean_token_accuracy": 0.23438227660953997,
|
| 36 |
+
"num_tokens": 2612799.0,
|
| 37 |
+
"step": 30
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.20202020202020202,
|
| 41 |
+
"grad_norm": 1.8361155986785889,
|
| 42 |
+
"learning_rate": 1.803030303030303e-05,
|
| 43 |
+
"loss": 4.6586,
|
| 44 |
+
"mean_token_accuracy": 0.2492609653621912,
|
| 45 |
+
"num_tokens": 3481685.0,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.25252525252525254,
|
| 50 |
+
"grad_norm": 1.7993879318237305,
|
| 51 |
+
"learning_rate": 1.752525252525253e-05,
|
| 52 |
+
"loss": 4.5569,
|
| 53 |
+
"mean_token_accuracy": 0.2619336560368538,
|
| 54 |
+
"num_tokens": 4345672.0,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.30303030303030304,
|
| 59 |
+
"grad_norm": 1.399275541305542,
|
| 60 |
+
"learning_rate": 1.7020202020202023e-05,
|
| 61 |
+
"loss": 4.4388,
|
| 62 |
+
"mean_token_accuracy": 0.27335850447416304,
|
| 63 |
+
"num_tokens": 5211312.0,
|
| 64 |
+
"step": 60
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.35353535353535354,
|
| 68 |
+
"grad_norm": 1.0864430665969849,
|
| 69 |
+
"learning_rate": 1.6515151515151517e-05,
|
| 70 |
+
"loss": 4.3731,
|
| 71 |
+
"mean_token_accuracy": 0.2805166557431221,
|
| 72 |
+
"num_tokens": 6083451.0,
|
| 73 |
+
"step": 70
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.40404040404040403,
|
| 77 |
+
"grad_norm": 1.1086381673812866,
|
| 78 |
+
"learning_rate": 1.601010101010101e-05,
|
| 79 |
+
"loss": 4.2975,
|
| 80 |
+
"mean_token_accuracy": 0.28774467632174494,
|
| 81 |
+
"num_tokens": 6945294.0,
|
| 82 |
+
"step": 80
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.45454545454545453,
|
| 86 |
+
"grad_norm": 3.123107671737671,
|
| 87 |
+
"learning_rate": 1.5505050505050508e-05,
|
| 88 |
+
"loss": 4.2324,
|
| 89 |
+
"mean_token_accuracy": 0.2966753713786602,
|
| 90 |
+
"num_tokens": 7817939.0,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.5050505050505051,
|
| 95 |
+
"grad_norm": 0.9251999855041504,
|
| 96 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 97 |
+
"loss": 4.1625,
|
| 98 |
+
"mean_token_accuracy": 0.3053535230457783,
|
| 99 |
+
"num_tokens": 8691417.0,
|
| 100 |
+
"step": 100
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5555555555555556,
|
| 104 |
+
"grad_norm": 0.9401581287384033,
|
| 105 |
+
"learning_rate": 1.4494949494949494e-05,
|
| 106 |
+
"loss": 4.1047,
|
| 107 |
+
"mean_token_accuracy": 0.31215064153075217,
|
| 108 |
+
"num_tokens": 9562161.0,
|
| 109 |
+
"step": 110
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.6060606060606061,
|
| 113 |
+
"grad_norm": 1.956444263458252,
|
| 114 |
+
"learning_rate": 1.3989898989898992e-05,
|
| 115 |
+
"loss": 4.0634,
|
| 116 |
+
"mean_token_accuracy": 0.31729411631822585,
|
| 117 |
+
"num_tokens": 10428287.0,
|
| 118 |
+
"step": 120
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.6565656565656566,
|
| 122 |
+
"grad_norm": 1.4297130107879639,
|
| 123 |
+
"learning_rate": 1.3484848484848486e-05,
|
| 124 |
+
"loss": 4.0134,
|
| 125 |
+
"mean_token_accuracy": 0.321382661908865,
|
| 126 |
+
"num_tokens": 11297263.0,
|
| 127 |
+
"step": 130
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.7070707070707071,
|
| 131 |
+
"grad_norm": 0.9279031753540039,
|
| 132 |
+
"learning_rate": 1.2979797979797981e-05,
|
| 133 |
+
"loss": 3.9757,
|
| 134 |
+
"mean_token_accuracy": 0.3249970510601997,
|
| 135 |
+
"num_tokens": 12166798.0,
|
| 136 |
+
"step": 140
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.7575757575757576,
|
| 140 |
+
"grad_norm": 0.7721190452575684,
|
| 141 |
+
"learning_rate": 1.2474747474747475e-05,
|
| 142 |
+
"loss": 3.9472,
|
| 143 |
+
"mean_token_accuracy": 0.32724879309535027,
|
| 144 |
+
"num_tokens": 13039570.0,
|
| 145 |
+
"step": 150
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.8080808080808081,
|
| 149 |
+
"grad_norm": 0.8442203402519226,
|
| 150 |
+
"learning_rate": 1.1969696969696971e-05,
|
| 151 |
+
"loss": 3.9148,
|
| 152 |
+
"mean_token_accuracy": 0.3321701854467392,
|
| 153 |
+
"num_tokens": 13914152.0,
|
| 154 |
+
"step": 160
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.8585858585858586,
|
| 158 |
+
"grad_norm": 2.19596266746521,
|
| 159 |
+
"learning_rate": 1.1464646464646465e-05,
|
| 160 |
+
"loss": 3.8928,
|
| 161 |
+
"mean_token_accuracy": 0.3358906783163548,
|
| 162 |
+
"num_tokens": 14784924.0,
|
| 163 |
+
"step": 170
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9090909090909091,
|
| 167 |
+
"grad_norm": 0.7308172583580017,
|
| 168 |
+
"learning_rate": 1.0959595959595961e-05,
|
| 169 |
+
"loss": 3.8529,
|
| 170 |
+
"mean_token_accuracy": 0.33917868658900263,
|
| 171 |
+
"num_tokens": 15653435.0,
|
| 172 |
+
"step": 180
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.9595959595959596,
|
| 176 |
+
"grad_norm": 0.6991971135139465,
|
| 177 |
+
"learning_rate": 1.0454545454545455e-05,
|
| 178 |
+
"loss": 3.847,
|
| 179 |
+
"mean_token_accuracy": 0.3425107732415199,
|
| 180 |
+
"num_tokens": 16520037.0,
|
| 181 |
+
"step": 190
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.0101010101010102,
|
| 185 |
+
"grad_norm": 0.6827145218849182,
|
| 186 |
+
"learning_rate": 9.94949494949495e-06,
|
| 187 |
+
"loss": 3.832,
|
| 188 |
+
"mean_token_accuracy": 0.34413780048489573,
|
| 189 |
+
"num_tokens": 17380162.0,
|
| 190 |
+
"step": 200
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.0606060606060606,
|
| 194 |
+
"grad_norm": 0.7619866132736206,
|
| 195 |
+
"learning_rate": 9.444444444444445e-06,
|
| 196 |
+
"loss": 3.7904,
|
| 197 |
+
"mean_token_accuracy": 0.3476664200425148,
|
| 198 |
+
"num_tokens": 18252280.0,
|
| 199 |
+
"step": 210
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.1111111111111112,
|
| 203 |
+
"grad_norm": 0.6569390892982483,
|
| 204 |
+
"learning_rate": 8.93939393939394e-06,
|
| 205 |
+
"loss": 3.7948,
|
| 206 |
+
"mean_token_accuracy": 0.3474963568150997,
|
| 207 |
+
"num_tokens": 19118807.0,
|
| 208 |
+
"step": 220
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.1616161616161615,
|
| 212 |
+
"grad_norm": 1.1422395706176758,
|
| 213 |
+
"learning_rate": 8.434343434343434e-06,
|
| 214 |
+
"loss": 3.7545,
|
| 215 |
+
"mean_token_accuracy": 0.350558465719223,
|
| 216 |
+
"num_tokens": 19987183.0,
|
| 217 |
+
"step": 230
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.2121212121212122,
|
| 221 |
+
"grad_norm": 0.9118938446044922,
|
| 222 |
+
"learning_rate": 7.92929292929293e-06,
|
| 223 |
+
"loss": 3.7356,
|
| 224 |
+
"mean_token_accuracy": 0.3532609537243843,
|
| 225 |
+
"num_tokens": 20864146.0,
|
| 226 |
+
"step": 240
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.2626262626262625,
|
| 230 |
+
"grad_norm": 0.830457329750061,
|
| 231 |
+
"learning_rate": 7.424242424242425e-06,
|
| 232 |
+
"loss": 3.7153,
|
| 233 |
+
"mean_token_accuracy": 0.3551630362868309,
|
| 234 |
+
"num_tokens": 21719950.0,
|
| 235 |
+
"step": 250
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.3131313131313131,
|
| 239 |
+
"grad_norm": 0.735416054725647,
|
| 240 |
+
"learning_rate": 6.91919191919192e-06,
|
| 241 |
+
"loss": 3.719,
|
| 242 |
+
"mean_token_accuracy": 0.35566510185599326,
|
| 243 |
+
"num_tokens": 22598888.0,
|
| 244 |
+
"step": 260
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.3636363636363638,
|
| 248 |
+
"grad_norm": 0.7242897152900696,
|
| 249 |
+
"learning_rate": 6.4141414141414145e-06,
|
| 250 |
+
"loss": 3.699,
|
| 251 |
+
"mean_token_accuracy": 0.35784361362457273,
|
| 252 |
+
"num_tokens": 23475457.0,
|
| 253 |
+
"step": 270
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.4141414141414141,
|
| 257 |
+
"grad_norm": 0.876636803150177,
|
| 258 |
+
"learning_rate": 5.90909090909091e-06,
|
| 259 |
+
"loss": 3.6957,
|
| 260 |
+
"mean_token_accuracy": 0.35799761712551115,
|
| 261 |
+
"num_tokens": 24343304.0,
|
| 262 |
+
"step": 280
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.4646464646464645,
|
| 266 |
+
"grad_norm": 0.7917715907096863,
|
| 267 |
+
"learning_rate": 5.404040404040405e-06,
|
| 268 |
+
"loss": 3.6889,
|
| 269 |
+
"mean_token_accuracy": 0.3586253359913826,
|
| 270 |
+
"num_tokens": 25207489.0,
|
| 271 |
+
"step": 290
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.5151515151515151,
|
| 275 |
+
"grad_norm": 0.7085571885108948,
|
| 276 |
+
"learning_rate": 4.898989898989899e-06,
|
| 277 |
+
"loss": 3.668,
|
| 278 |
+
"mean_token_accuracy": 0.36179669201374054,
|
| 279 |
+
"num_tokens": 26072804.0,
|
| 280 |
+
"step": 300
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.5656565656565657,
|
| 284 |
+
"grad_norm": 0.5749636292457581,
|
| 285 |
+
"learning_rate": 4.393939393939394e-06,
|
| 286 |
+
"loss": 3.657,
|
| 287 |
+
"mean_token_accuracy": 0.3627041429281235,
|
| 288 |
+
"num_tokens": 26939192.0,
|
| 289 |
+
"step": 310
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.6161616161616161,
|
| 293 |
+
"grad_norm": 0.8387623429298401,
|
| 294 |
+
"learning_rate": 3.88888888888889e-06,
|
| 295 |
+
"loss": 3.668,
|
| 296 |
+
"mean_token_accuracy": 0.3618996299803257,
|
| 297 |
+
"num_tokens": 27805084.0,
|
| 298 |
+
"step": 320
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.6666666666666665,
|
| 302 |
+
"grad_norm": 0.6559562683105469,
|
| 303 |
+
"learning_rate": 3.3838383838383844e-06,
|
| 304 |
+
"loss": 3.6492,
|
| 305 |
+
"mean_token_accuracy": 0.36368392035365105,
|
| 306 |
+
"num_tokens": 28676488.0,
|
| 307 |
+
"step": 330
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 1.7171717171717171,
|
| 311 |
+
"grad_norm": 0.6847353577613831,
|
| 312 |
+
"learning_rate": 2.8787878787878793e-06,
|
| 313 |
+
"loss": 3.6622,
|
| 314 |
+
"mean_token_accuracy": 0.3614747479557991,
|
| 315 |
+
"num_tokens": 29545994.0,
|
| 316 |
+
"step": 340
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.7676767676767677,
|
| 320 |
+
"grad_norm": 0.8682920336723328,
|
| 321 |
+
"learning_rate": 2.373737373737374e-06,
|
| 322 |
+
"loss": 3.648,
|
| 323 |
+
"mean_token_accuracy": 0.36393540278077124,
|
| 324 |
+
"num_tokens": 30421682.0,
|
| 325 |
+
"step": 350
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.8181818181818183,
|
| 329 |
+
"grad_norm": 0.7822595834732056,
|
| 330 |
+
"learning_rate": 1.868686868686869e-06,
|
| 331 |
+
"loss": 3.6468,
|
| 332 |
+
"mean_token_accuracy": 0.36377949416637423,
|
| 333 |
+
"num_tokens": 31290360.0,
|
| 334 |
+
"step": 360
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.8686868686868687,
|
| 338 |
+
"grad_norm": 0.6070267558097839,
|
| 339 |
+
"learning_rate": 1.3636363636363636e-06,
|
| 340 |
+
"loss": 3.6441,
|
| 341 |
+
"mean_token_accuracy": 0.3641804397106171,
|
| 342 |
+
"num_tokens": 32154120.0,
|
| 343 |
+
"step": 370
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 1.9191919191919191,
|
| 347 |
+
"grad_norm": 0.7802349328994751,
|
| 348 |
+
"learning_rate": 8.585858585858587e-07,
|
| 349 |
+
"loss": 3.6413,
|
| 350 |
+
"mean_token_accuracy": 0.3650804080069065,
|
| 351 |
+
"num_tokens": 33021167.0,
|
| 352 |
+
"step": 380
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.9696969696969697,
|
| 356 |
+
"grad_norm": 0.5713841319084167,
|
| 357 |
+
"learning_rate": 3.535353535353536e-07,
|
| 358 |
+
"loss": 3.6402,
|
| 359 |
+
"mean_token_accuracy": 0.3654905065894127,
|
| 360 |
+
"num_tokens": 33894053.0,
|
| 361 |
+
"step": 390
|
| 362 |
+
}
|
| 363 |
+
],
|
| 364 |
+
"logging_steps": 10,
|
| 365 |
+
"max_steps": 396,
|
| 366 |
+
"num_input_tokens_seen": 0,
|
| 367 |
+
"num_train_epochs": 2,
|
| 368 |
+
"save_steps": 500,
|
| 369 |
+
"stateful_callbacks": {
|
| 370 |
+
"TrainerControl": {
|
| 371 |
+
"args": {
|
| 372 |
+
"should_epoch_stop": false,
|
| 373 |
+
"should_evaluate": false,
|
| 374 |
+
"should_log": false,
|
| 375 |
+
"should_save": true,
|
| 376 |
+
"should_training_stop": true
|
| 377 |
+
},
|
| 378 |
+
"attributes": {}
|
| 379 |
+
}
|
| 380 |
+
},
|
| 381 |
+
"total_flos": 1.6464949686042624e+16,
|
| 382 |
+
"train_batch_size": 64,
|
| 383 |
+
"trial_name": null,
|
| 384 |
+
"trial_params": null
|
| 385 |
+
}
|
checkpoint-396/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bab42ec109985bdf397aeca59ca07aa1ac984d973daf17a4290e45a1afacd8fd
|
| 3 |
+
size 5624
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1024,
|
| 14 |
+
"max_position_embeddings": 256,
|
| 15 |
+
"mlp_bias": false,
|
| 16 |
+
"model_type": "llama",
|
| 17 |
+
"num_attention_heads": 6,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"num_key_value_heads": 6,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-05,
|
| 23 |
+
"rope_scaling": null,
|
| 24 |
+
"rope_theta": 10000.0,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.51.3",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 32000
|
| 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": 0,
|
| 6 |
+
"transformers_version": "4.51.3"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:275414a0c076db571ed3c7ef9229c919137297e56c68227309ded8272182e2f7
|
| 3 |
+
size 309900448
|
runs/Apr22_05-37-15_4f97a4faf13f/events.out.tfevents.1745300264.4f97a4faf13f.989.9
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24075e3804d79f326638794bc182bc921ea2399bd88a0faf77346bad0f0ca2a4
|
| 3 |
+
size 5430
|
runs/Apr22_05-38-08_4f97a4faf13f/events.out.tfevents.1745300349.4f97a4faf13f.989.10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c10eeaa621ad0aeb3dbd6cafe0c596e2b1cd837f9388c2edcf983f71f3af52d1
|
| 3 |
+
size 18701
|
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": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 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 |
+
"extra_special_tokens": {},
|
| 35 |
+
"legacy": false,
|
| 36 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
+
"pad_token": "</s>",
|
| 38 |
+
"sp_model_kwargs": {},
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false
|
| 42 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bab42ec109985bdf397aeca59ca07aa1ac984d973daf17a4290e45a1afacd8fd
|
| 3 |
+
size 5624
|