Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- MyBitnet_Llama2_70M.onnx +3 -0
- checkpoint-1250/added_tokens.json +3 -0
- checkpoint-1250/config.json +30 -0
- checkpoint-1250/generation_config.json +8 -0
- checkpoint-1250/model.safetensors +3 -0
- checkpoint-1250/optimizer.pt +3 -0
- checkpoint-1250/rng_state.pth +3 -0
- checkpoint-1250/scheduler.pt +3 -0
- checkpoint-1250/special_tokens_map.json +24 -0
- checkpoint-1250/tokenizer.json +0 -0
- checkpoint-1250/tokenizer.model +3 -0
- checkpoint-1250/tokenizer_config.json +48 -0
- checkpoint-1250/trainer_state.json +117 -0
- checkpoint-1250/training_args.bin +3 -0
- checkpoint-2500/added_tokens.json +3 -0
- checkpoint-2500/config.json +30 -0
- checkpoint-2500/generation_config.json +8 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/special_tokens_map.json +24 -0
- checkpoint-2500/tokenizer.json +0 -0
- checkpoint-2500/tokenizer.model +3 -0
- checkpoint-2500/tokenizer_config.json +48 -0
- checkpoint-2500/trainer_state.json +208 -0
- checkpoint-2500/training_args.bin +3 -0
- checkpoint-3750/added_tokens.json +3 -0
- checkpoint-3750/config.json +30 -0
- checkpoint-3750/generation_config.json +8 -0
- checkpoint-3750/model.safetensors +3 -0
- checkpoint-3750/optimizer.pt +3 -0
- checkpoint-3750/rng_state.pth +3 -0
- checkpoint-3750/scheduler.pt +3 -0
- checkpoint-3750/special_tokens_map.json +24 -0
- checkpoint-3750/tokenizer.json +0 -0
- checkpoint-3750/tokenizer.model +3 -0
- checkpoint-3750/tokenizer_config.json +48 -0
- checkpoint-3750/trainer_state.json +292 -0
- checkpoint-3750/training_args.bin +3 -0
- checkpoint-5000/added_tokens.json +3 -0
- checkpoint-5000/config.json +30 -0
- checkpoint-5000/generation_config.json +8 -0
- checkpoint-5000/model.safetensors +3 -0
- checkpoint-5000/optimizer.pt +3 -0
- checkpoint-5000/rng_state.pth +3 -0
- checkpoint-5000/scheduler.pt +3 -0
- checkpoint-5000/special_tokens_map.json +24 -0
- checkpoint-5000/tokenizer.json +0 -0
- checkpoint-5000/tokenizer.model +3 -0
MyBitnet_Llama2_70M.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:511bd8116078a11909cfe4b76497210aba5cb4eb8006674e0487025fba14c59f
|
| 3 |
+
size 261254825
|
checkpoint-1250/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
checkpoint-1250/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
|
| 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": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1024,
|
| 14 |
+
"max_position_embeddings": 768,
|
| 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": "4.41.2",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"vocab_size": 32001
|
| 30 |
+
}
|
checkpoint-1250/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.41.2",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
checkpoint-1250/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47de634eb309adbf96f30e096efe9128a1af8ff1417ad24f9eafed95d8227f72
|
| 3 |
+
size 309887520
|
checkpoint-1250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe166c66e06a5714ccc86d2ac8214f627cdeb0b66a2f1db80a5f0b0c420afb97
|
| 3 |
+
size 619807162
|
checkpoint-1250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
| 3 |
+
size 14244
|
checkpoint-1250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71eff3e7b3cc8cc2bfb8f1ae5551dc39ffd45a41456a501eaca6a257e2935b9a
|
| 3 |
+
size 1064
|
checkpoint-1250/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": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-1250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1250/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-1250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<pad>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"bos_token": "<s>",
|
| 39 |
+
"clean_up_tokenization_spaces": false,
|
| 40 |
+
"eos_token": "</s>",
|
| 41 |
+
"legacy": false,
|
| 42 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
+
"pad_token": "</s>",
|
| 44 |
+
"sp_model_kwargs": {},
|
| 45 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 46 |
+
"unk_token": "<unk>",
|
| 47 |
+
"use_default_system_prompt": false
|
| 48 |
+
}
|
checkpoint-1250/trainer_state.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0839095119822783,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.006712760958582265,
|
| 13 |
+
"grad_norm": 1.0528477430343628,
|
| 14 |
+
"learning_rate": 0.00014985229447149842,
|
| 15 |
+
"loss": 7.6572,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01342552191716453,
|
| 20 |
+
"grad_norm": 1.1515228748321533,
|
| 21 |
+
"learning_rate": 0.00014940916946874937,
|
| 22 |
+
"loss": 6.1239,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.020138282875746795,
|
| 27 |
+
"grad_norm": 1.2438573837280273,
|
| 28 |
+
"learning_rate": 0.00014867237372557577,
|
| 29 |
+
"loss": 5.4067,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02685104383432906,
|
| 34 |
+
"grad_norm": 1.3082321882247925,
|
| 35 |
+
"learning_rate": 0.00014764481515444297,
|
| 36 |
+
"loss": 5.0934,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03356380479291132,
|
| 41 |
+
"grad_norm": 1.4851253032684326,
|
| 42 |
+
"learning_rate": 0.00014633054922174807,
|
| 43 |
+
"loss": 4.8669,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04027656575149359,
|
| 48 |
+
"grad_norm": 1.3247835636138916,
|
| 49 |
+
"learning_rate": 0.00014473476294210664,
|
| 50 |
+
"loss": 4.7151,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04698932671007586,
|
| 55 |
+
"grad_norm": 1.5466852188110352,
|
| 56 |
+
"learning_rate": 0.0001428637544067573,
|
| 57 |
+
"loss": 4.5684,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05370208766865812,
|
| 62 |
+
"grad_norm": 1.3418868780136108,
|
| 63 |
+
"learning_rate": 0.0001407249079268789,
|
| 64 |
+
"loss": 4.4861,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.060414848627240385,
|
| 69 |
+
"grad_norm": 1.4495049715042114,
|
| 70 |
+
"learning_rate": 0.0001383266648899225,
|
| 71 |
+
"loss": 4.3896,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06712760958582265,
|
| 76 |
+
"grad_norm": 1.2629677057266235,
|
| 77 |
+
"learning_rate": 0.0001356784904439796,
|
| 78 |
+
"loss": 4.3076,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07384037054440491,
|
| 83 |
+
"grad_norm": 1.382216215133667,
|
| 84 |
+
"learning_rate": 0.00013279083614167278,
|
| 85 |
+
"loss": 4.2179,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.08055313150298718,
|
| 90 |
+
"grad_norm": 1.2883789539337158,
|
| 91 |
+
"learning_rate": 0.00012967509869100336,
|
| 92 |
+
"loss": 4.1599,
|
| 93 |
+
"step": 1200
|
| 94 |
+
}
|
| 95 |
+
],
|
| 96 |
+
"logging_steps": 100,
|
| 97 |
+
"max_steps": 5000,
|
| 98 |
+
"num_input_tokens_seen": 0,
|
| 99 |
+
"num_train_epochs": 1,
|
| 100 |
+
"save_steps": 1250,
|
| 101 |
+
"stateful_callbacks": {
|
| 102 |
+
"TrainerControl": {
|
| 103 |
+
"args": {
|
| 104 |
+
"should_epoch_stop": false,
|
| 105 |
+
"should_evaluate": false,
|
| 106 |
+
"should_log": false,
|
| 107 |
+
"should_save": true,
|
| 108 |
+
"should_training_stop": false
|
| 109 |
+
},
|
| 110 |
+
"attributes": {}
|
| 111 |
+
}
|
| 112 |
+
},
|
| 113 |
+
"total_flos": 3249788682240000.0,
|
| 114 |
+
"train_batch_size": 16,
|
| 115 |
+
"trial_name": null,
|
| 116 |
+
"trial_params": null
|
| 117 |
+
}
|
checkpoint-1250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b0bbdca8de25bbc8bf36748f618e50f9b10fabddb7b161369a5bf65d593e10b
|
| 3 |
+
size 5112
|
checkpoint-2500/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
checkpoint-2500/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
|
| 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": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1024,
|
| 14 |
+
"max_position_embeddings": 768,
|
| 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": "4.41.2",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"vocab_size": 32001
|
| 30 |
+
}
|
checkpoint-2500/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.41.2",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
checkpoint-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c0fa0eb7d1a057092ef6c6d1bf36375fa29218c2b034e0c7751a0614c8ce533
|
| 3 |
+
size 309887520
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4fdadc199491da39c42cfbdf9dcbb479abd3edbcd872ab10563cffbc9770320
|
| 3 |
+
size 619807162
|
checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
| 3 |
+
size 14244
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cdd43b6935ceda70a8d16b96dd9a8e3d51ed27d22e5a6c5aa441a1273a52af5
|
| 3 |
+
size 1064
|
checkpoint-2500/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": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-2500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-2500/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-2500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<pad>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"bos_token": "<s>",
|
| 39 |
+
"clean_up_tokenization_spaces": false,
|
| 40 |
+
"eos_token": "</s>",
|
| 41 |
+
"legacy": false,
|
| 42 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
+
"pad_token": "</s>",
|
| 44 |
+
"sp_model_kwargs": {},
|
| 45 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 46 |
+
"unk_token": "<unk>",
|
| 47 |
+
"use_default_system_prompt": false
|
| 48 |
+
}
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.1678190239645566,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.006712760958582265,
|
| 13 |
+
"grad_norm": 1.0528477430343628,
|
| 14 |
+
"learning_rate": 0.00014985229447149842,
|
| 15 |
+
"loss": 7.6572,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01342552191716453,
|
| 20 |
+
"grad_norm": 1.1515228748321533,
|
| 21 |
+
"learning_rate": 0.00014940916946874937,
|
| 22 |
+
"loss": 6.1239,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.020138282875746795,
|
| 27 |
+
"grad_norm": 1.2438573837280273,
|
| 28 |
+
"learning_rate": 0.00014867237372557577,
|
| 29 |
+
"loss": 5.4067,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02685104383432906,
|
| 34 |
+
"grad_norm": 1.3082321882247925,
|
| 35 |
+
"learning_rate": 0.00014764481515444297,
|
| 36 |
+
"loss": 5.0934,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03356380479291132,
|
| 41 |
+
"grad_norm": 1.4851253032684326,
|
| 42 |
+
"learning_rate": 0.00014633054922174807,
|
| 43 |
+
"loss": 4.8669,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04027656575149359,
|
| 48 |
+
"grad_norm": 1.3247835636138916,
|
| 49 |
+
"learning_rate": 0.00014473476294210664,
|
| 50 |
+
"loss": 4.7151,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04698932671007586,
|
| 55 |
+
"grad_norm": 1.5466852188110352,
|
| 56 |
+
"learning_rate": 0.0001428637544067573,
|
| 57 |
+
"loss": 4.5684,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05370208766865812,
|
| 62 |
+
"grad_norm": 1.3418868780136108,
|
| 63 |
+
"learning_rate": 0.0001407249079268789,
|
| 64 |
+
"loss": 4.4861,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.060414848627240385,
|
| 69 |
+
"grad_norm": 1.4495049715042114,
|
| 70 |
+
"learning_rate": 0.0001383266648899225,
|
| 71 |
+
"loss": 4.3896,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06712760958582265,
|
| 76 |
+
"grad_norm": 1.2629677057266235,
|
| 77 |
+
"learning_rate": 0.0001356784904439796,
|
| 78 |
+
"loss": 4.3076,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07384037054440491,
|
| 83 |
+
"grad_norm": 1.382216215133667,
|
| 84 |
+
"learning_rate": 0.00013279083614167278,
|
| 85 |
+
"loss": 4.2179,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.08055313150298718,
|
| 90 |
+
"grad_norm": 1.2883789539337158,
|
| 91 |
+
"learning_rate": 0.00012967509869100336,
|
| 92 |
+
"loss": 4.1599,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08726589246156945,
|
| 97 |
+
"grad_norm": 1.3527660369873047,
|
| 98 |
+
"learning_rate": 0.00012634357497595263,
|
| 99 |
+
"loss": 4.0976,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09397865342015171,
|
| 104 |
+
"grad_norm": 1.3394412994384766,
|
| 105 |
+
"learning_rate": 0.00012280941352435837,
|
| 106 |
+
"loss": 4.0805,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.10069141437873397,
|
| 111 |
+
"grad_norm": 1.4646199941635132,
|
| 112 |
+
"learning_rate": 0.00011908656261460721,
|
| 113 |
+
"loss": 4.0032,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.10740417533731624,
|
| 118 |
+
"grad_norm": 1.2548878192901611,
|
| 119 |
+
"learning_rate": 0.00011518971522595105,
|
| 120 |
+
"loss": 3.9702,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1141169362958985,
|
| 125 |
+
"grad_norm": 1.363207221031189,
|
| 126 |
+
"learning_rate": 0.00011113425104971176,
|
| 127 |
+
"loss": 3.9321,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.12082969725448077,
|
| 132 |
+
"grad_norm": 1.3911628723144531,
|
| 133 |
+
"learning_rate": 0.00010693617579023885,
|
| 134 |
+
"loss": 3.8974,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12754245821306304,
|
| 139 |
+
"grad_norm": 1.3630716800689697,
|
| 140 |
+
"learning_rate": 0.00010261205799518043,
|
| 141 |
+
"loss": 3.8514,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.1342552191716453,
|
| 146 |
+
"grad_norm": 1.2687169313430786,
|
| 147 |
+
"learning_rate": 9.817896366438074e-05,
|
| 148 |
+
"loss": 3.818,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.14096798013022757,
|
| 153 |
+
"grad_norm": 1.3437057733535767,
|
| 154 |
+
"learning_rate": 9.36543888954819e-05,
|
| 155 |
+
"loss": 3.8071,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.14768074108880982,
|
| 160 |
+
"grad_norm": 1.3673392534255981,
|
| 161 |
+
"learning_rate": 8.905619083205881e-05,
|
| 162 |
+
"loss": 3.7842,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1543935020473921,
|
| 167 |
+
"grad_norm": 1.2775851488113403,
|
| 168 |
+
"learning_rate": 8.440251718681331e-05,
|
| 169 |
+
"loss": 3.7666,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.16110626300597436,
|
| 174 |
+
"grad_norm": 1.382295846939087,
|
| 175 |
+
"learning_rate": 7.971173461797922e-05,
|
| 176 |
+
"loss": 3.679,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1678190239645566,
|
| 181 |
+
"grad_norm": 1.269216775894165,
|
| 182 |
+
"learning_rate": 7.500235624161463e-05,
|
| 183 |
+
"loss": 3.7059,
|
| 184 |
+
"step": 2500
|
| 185 |
+
}
|
| 186 |
+
],
|
| 187 |
+
"logging_steps": 100,
|
| 188 |
+
"max_steps": 5000,
|
| 189 |
+
"num_input_tokens_seen": 0,
|
| 190 |
+
"num_train_epochs": 1,
|
| 191 |
+
"save_steps": 1250,
|
| 192 |
+
"stateful_callbacks": {
|
| 193 |
+
"TrainerControl": {
|
| 194 |
+
"args": {
|
| 195 |
+
"should_epoch_stop": false,
|
| 196 |
+
"should_evaluate": false,
|
| 197 |
+
"should_log": false,
|
| 198 |
+
"should_save": true,
|
| 199 |
+
"should_training_stop": false
|
| 200 |
+
},
|
| 201 |
+
"attributes": {}
|
| 202 |
+
}
|
| 203 |
+
},
|
| 204 |
+
"total_flos": 6499577364480000.0,
|
| 205 |
+
"train_batch_size": 16,
|
| 206 |
+
"trial_name": null,
|
| 207 |
+
"trial_params": null
|
| 208 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b0bbdca8de25bbc8bf36748f618e50f9b10fabddb7b161369a5bf65d593e10b
|
| 3 |
+
size 5112
|
checkpoint-3750/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
checkpoint-3750/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
|
| 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": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1024,
|
| 14 |
+
"max_position_embeddings": 768,
|
| 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": "4.41.2",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"vocab_size": 32001
|
| 30 |
+
}
|
checkpoint-3750/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.41.2",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
checkpoint-3750/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e75917f2449514c402ed13acd7bf1035f3c53229aac7eaf8c484596ffcd264e1
|
| 3 |
+
size 309887520
|
checkpoint-3750/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:490896b94f7df9a21789a810628b2c82711071d533a479fda21e44180ace28a2
|
| 3 |
+
size 619807162
|
checkpoint-3750/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
| 3 |
+
size 14244
|
checkpoint-3750/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:141a9d8b8a5e4763ffd6370a8134e721cf2b1dd4f3160cd28a7c003f6056aef3
|
| 3 |
+
size 1064
|
checkpoint-3750/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": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-3750/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3750/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-3750/tokenizer_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<pad>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"bos_token": "<s>",
|
| 39 |
+
"clean_up_tokenization_spaces": false,
|
| 40 |
+
"eos_token": "</s>",
|
| 41 |
+
"legacy": false,
|
| 42 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
+
"pad_token": "</s>",
|
| 44 |
+
"sp_model_kwargs": {},
|
| 45 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 46 |
+
"unk_token": "<unk>",
|
| 47 |
+
"use_default_system_prompt": false
|
| 48 |
+
}
|
checkpoint-3750/trainer_state.json
ADDED
|
@@ -0,0 +1,292 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2517285359468349,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3750,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.006712760958582265,
|
| 13 |
+
"grad_norm": 1.0528477430343628,
|
| 14 |
+
"learning_rate": 0.00014985229447149842,
|
| 15 |
+
"loss": 7.6572,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01342552191716453,
|
| 20 |
+
"grad_norm": 1.1515228748321533,
|
| 21 |
+
"learning_rate": 0.00014940916946874937,
|
| 22 |
+
"loss": 6.1239,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.020138282875746795,
|
| 27 |
+
"grad_norm": 1.2438573837280273,
|
| 28 |
+
"learning_rate": 0.00014867237372557577,
|
| 29 |
+
"loss": 5.4067,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02685104383432906,
|
| 34 |
+
"grad_norm": 1.3082321882247925,
|
| 35 |
+
"learning_rate": 0.00014764481515444297,
|
| 36 |
+
"loss": 5.0934,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03356380479291132,
|
| 41 |
+
"grad_norm": 1.4851253032684326,
|
| 42 |
+
"learning_rate": 0.00014633054922174807,
|
| 43 |
+
"loss": 4.8669,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04027656575149359,
|
| 48 |
+
"grad_norm": 1.3247835636138916,
|
| 49 |
+
"learning_rate": 0.00014473476294210664,
|
| 50 |
+
"loss": 4.7151,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04698932671007586,
|
| 55 |
+
"grad_norm": 1.5466852188110352,
|
| 56 |
+
"learning_rate": 0.0001428637544067573,
|
| 57 |
+
"loss": 4.5684,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.05370208766865812,
|
| 62 |
+
"grad_norm": 1.3418868780136108,
|
| 63 |
+
"learning_rate": 0.0001407249079268789,
|
| 64 |
+
"loss": 4.4861,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.060414848627240385,
|
| 69 |
+
"grad_norm": 1.4495049715042114,
|
| 70 |
+
"learning_rate": 0.0001383266648899225,
|
| 71 |
+
"loss": 4.3896,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.06712760958582265,
|
| 76 |
+
"grad_norm": 1.2629677057266235,
|
| 77 |
+
"learning_rate": 0.0001356784904439796,
|
| 78 |
+
"loss": 4.3076,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.07384037054440491,
|
| 83 |
+
"grad_norm": 1.382216215133667,
|
| 84 |
+
"learning_rate": 0.00013279083614167278,
|
| 85 |
+
"loss": 4.2179,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.08055313150298718,
|
| 90 |
+
"grad_norm": 1.2883789539337158,
|
| 91 |
+
"learning_rate": 0.00012967509869100336,
|
| 92 |
+
"loss": 4.1599,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08726589246156945,
|
| 97 |
+
"grad_norm": 1.3527660369873047,
|
| 98 |
+
"learning_rate": 0.00012634357497595263,
|
| 99 |
+
"loss": 4.0976,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.09397865342015171,
|
| 104 |
+
"grad_norm": 1.3394412994384766,
|
| 105 |
+
"learning_rate": 0.00012280941352435837,
|
| 106 |
+
"loss": 4.0805,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.10069141437873397,
|
| 111 |
+
"grad_norm": 1.4646199941635132,
|
| 112 |
+
"learning_rate": 0.00011908656261460721,
|
| 113 |
+
"loss": 4.0032,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.10740417533731624,
|
| 118 |
+
"grad_norm": 1.2548878192901611,
|
| 119 |
+
"learning_rate": 0.00011518971522595105,
|
| 120 |
+
"loss": 3.9702,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.1141169362958985,
|
| 125 |
+
"grad_norm": 1.363207221031189,
|
| 126 |
+
"learning_rate": 0.00011113425104971176,
|
| 127 |
+
"loss": 3.9321,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.12082969725448077,
|
| 132 |
+
"grad_norm": 1.3911628723144531,
|
| 133 |
+
"learning_rate": 0.00010693617579023885,
|
| 134 |
+
"loss": 3.8974,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12754245821306304,
|
| 139 |
+
"grad_norm": 1.3630716800689697,
|
| 140 |
+
"learning_rate": 0.00010261205799518043,
|
| 141 |
+
"loss": 3.8514,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.1342552191716453,
|
| 146 |
+
"grad_norm": 1.2687169313430786,
|
| 147 |
+
"learning_rate": 9.817896366438074e-05,
|
| 148 |
+
"loss": 3.818,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.14096798013022757,
|
| 153 |
+
"grad_norm": 1.3437057733535767,
|
| 154 |
+
"learning_rate": 9.36543888954819e-05,
|
| 155 |
+
"loss": 3.8071,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.14768074108880982,
|
| 160 |
+
"grad_norm": 1.3673392534255981,
|
| 161 |
+
"learning_rate": 8.905619083205881e-05,
|
| 162 |
+
"loss": 3.7842,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.1543935020473921,
|
| 167 |
+
"grad_norm": 1.2775851488113403,
|
| 168 |
+
"learning_rate": 8.440251718681331e-05,
|
| 169 |
+
"loss": 3.7666,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.16110626300597436,
|
| 174 |
+
"grad_norm": 1.382295846939087,
|
| 175 |
+
"learning_rate": 7.971173461797922e-05,
|
| 176 |
+
"loss": 3.679,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1678190239645566,
|
| 181 |
+
"grad_norm": 1.269216775894165,
|
| 182 |
+
"learning_rate": 7.500235624161463e-05,
|
| 183 |
+
"loss": 3.7059,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1745317849231389,
|
| 188 |
+
"grad_norm": 1.343229055404663,
|
| 189 |
+
"learning_rate": 7.029296856586897e-05,
|
| 190 |
+
"loss": 3.6681,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.18124454588172115,
|
| 195 |
+
"grad_norm": 1.3436596393585205,
|
| 196 |
+
"learning_rate": 6.560215813559365e-05,
|
| 197 |
+
"loss": 3.6667,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.18795730684030343,
|
| 202 |
+
"grad_norm": 1.3680791854858398,
|
| 203 |
+
"learning_rate": 6.094843817680749e-05,
|
| 204 |
+
"loss": 3.6359,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.19467006779888568,
|
| 209 |
+
"grad_norm": 1.3404663801193237,
|
| 210 |
+
"learning_rate": 5.635017553053002e-05,
|
| 211 |
+
"loss": 3.6386,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.20138282875746794,
|
| 216 |
+
"grad_norm": 1.2906004190444946,
|
| 217 |
+
"learning_rate": 5.1825518164352286e-05,
|
| 218 |
+
"loss": 3.6036,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.20809558971605022,
|
| 223 |
+
"grad_norm": 1.585774540901184,
|
| 224 |
+
"learning_rate": 4.7392323547835926e-05,
|
| 225 |
+
"loss": 3.6075,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.21480835067463247,
|
| 230 |
+
"grad_norm": 1.3589500188827515,
|
| 231 |
+
"learning_rate": 4.306808817442085e-05,
|
| 232 |
+
"loss": 3.5855,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.22152111163321475,
|
| 237 |
+
"grad_norm": 1.4228436946868896,
|
| 238 |
+
"learning_rate": 3.886987850799785e-05,
|
| 239 |
+
"loss": 3.5662,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.228233872591797,
|
| 244 |
+
"grad_norm": 1.4741946458816528,
|
| 245 |
+
"learning_rate": 3.481426362667913e-05,
|
| 246 |
+
"loss": 3.5487,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.23494663355037926,
|
| 251 |
+
"grad_norm": 1.4674755334854126,
|
| 252 |
+
"learning_rate": 3.0917249829602016e-05,
|
| 253 |
+
"loss": 3.5521,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.24165939450896154,
|
| 258 |
+
"grad_norm": 1.4647969007492065,
|
| 259 |
+
"learning_rate": 2.7194217464852685e-05,
|
| 260 |
+
"loss": 3.5201,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2483721554675438,
|
| 265 |
+
"grad_norm": 1.427472710609436,
|
| 266 |
+
"learning_rate": 2.3659860227831684e-05,
|
| 267 |
+
"loss": 3.5241,
|
| 268 |
+
"step": 3700
|
| 269 |
+
}
|
| 270 |
+
],
|
| 271 |
+
"logging_steps": 100,
|
| 272 |
+
"max_steps": 5000,
|
| 273 |
+
"num_input_tokens_seen": 0,
|
| 274 |
+
"num_train_epochs": 1,
|
| 275 |
+
"save_steps": 1250,
|
| 276 |
+
"stateful_callbacks": {
|
| 277 |
+
"TrainerControl": {
|
| 278 |
+
"args": {
|
| 279 |
+
"should_epoch_stop": false,
|
| 280 |
+
"should_evaluate": false,
|
| 281 |
+
"should_log": false,
|
| 282 |
+
"should_save": true,
|
| 283 |
+
"should_training_stop": false
|
| 284 |
+
},
|
| 285 |
+
"attributes": {}
|
| 286 |
+
}
|
| 287 |
+
},
|
| 288 |
+
"total_flos": 9749366046720000.0,
|
| 289 |
+
"train_batch_size": 16,
|
| 290 |
+
"trial_name": null,
|
| 291 |
+
"trial_params": null
|
| 292 |
+
}
|
checkpoint-3750/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b0bbdca8de25bbc8bf36748f618e50f9b10fabddb7b161369a5bf65d593e10b
|
| 3 |
+
size 5112
|
checkpoint-5000/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
checkpoint-5000/config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "NousResearch/Nous-Hermes-llama-2-7b",
|
| 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": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 1024,
|
| 14 |
+
"max_position_embeddings": 768,
|
| 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": "4.41.2",
|
| 28 |
+
"use_cache": false,
|
| 29 |
+
"vocab_size": 32001
|
| 30 |
+
}
|
checkpoint-5000/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.41.2",
|
| 7 |
+
"use_cache": false
|
| 8 |
+
}
|
checkpoint-5000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc2cee91ab8d43772f4e85e899f0f02cdbc926ba3692a97fe6e1939a59421dd0
|
| 3 |
+
size 309887520
|
checkpoint-5000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d3b1b62a7e98971082b60b8defebf3dd0ac1ef15c2360160151c0331eaad993
|
| 3 |
+
size 619807162
|
checkpoint-5000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
| 3 |
+
size 14244
|
checkpoint-5000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34931feb19b1d341b16bab599d4d16930938300aaca4565d60949ddcdcaad849
|
| 3 |
+
size 1064
|
checkpoint-5000/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": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-5000/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-5000/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|