Upload 9 files
Browse files- config.json +28 -0
- generation_config.json +7 -0
- model-001.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +40 -0
- trainer_state.json +315 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
| 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": 5632,
|
| 14 |
+
"max_position_embeddings": 2048,
|
| 15 |
+
"model_type": "llama",
|
| 16 |
+
"num_attention_heads": 32,
|
| 17 |
+
"num_hidden_layers": 22,
|
| 18 |
+
"num_key_value_heads": 4,
|
| 19 |
+
"pretraining_tp": 1,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 10000.0,
|
| 23 |
+
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.38.2",
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 32000
|
| 28 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.38.2"
|
| 7 |
+
}
|
model-001.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:818bf98ec4acb9c6dbb660b3b5ce5461129d647f9a86eda853aa5c373478332b
|
| 3 |
+
size 4400216536
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
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 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"bos_token": "<s>",
|
| 29 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
| 30 |
+
"clean_up_tokenization_spaces": false,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"legacy": false,
|
| 33 |
+
"model_max_length": 2048,
|
| 34 |
+
"pad_token": "</s>",
|
| 35 |
+
"padding_side": "right",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
+
"unk_token": "<unk>",
|
| 39 |
+
"use_default_system_prompt": false
|
| 40 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.8560636043548584,
|
| 3 |
+
"best_model_checkpoint": "/content/models/TinyLlama-TinyLlama-1-1B-Chat-v1-0/checkpoint-564",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 141,
|
| 6 |
+
"global_step": 2810,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.25,
|
| 13 |
+
"grad_norm": 5.238644123077393,
|
| 14 |
+
"learning_rate": 4.7491103202846974e-05,
|
| 15 |
+
"loss": 2.103,
|
| 16 |
+
"step": 141
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.25,
|
| 20 |
+
"eval_loss": 1.9888125658035278,
|
| 21 |
+
"eval_runtime": 4.1833,
|
| 22 |
+
"eval_samples_per_second": 56.654,
|
| 23 |
+
"eval_steps_per_second": 7.171,
|
| 24 |
+
"step": 141
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.5,
|
| 28 |
+
"grad_norm": 4.7757039070129395,
|
| 29 |
+
"learning_rate": 4.498220640569395e-05,
|
| 30 |
+
"loss": 1.908,
|
| 31 |
+
"step": 282
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.5,
|
| 35 |
+
"eval_loss": 1.9252748489379883,
|
| 36 |
+
"eval_runtime": 4.1854,
|
| 37 |
+
"eval_samples_per_second": 56.625,
|
| 38 |
+
"eval_steps_per_second": 7.168,
|
| 39 |
+
"step": 282
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.75,
|
| 43 |
+
"grad_norm": 3.813783645629883,
|
| 44 |
+
"learning_rate": 4.247330960854093e-05,
|
| 45 |
+
"loss": 1.8483,
|
| 46 |
+
"step": 423
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.75,
|
| 50 |
+
"eval_loss": 1.9029674530029297,
|
| 51 |
+
"eval_runtime": 4.1786,
|
| 52 |
+
"eval_samples_per_second": 56.717,
|
| 53 |
+
"eval_steps_per_second": 7.179,
|
| 54 |
+
"step": 423
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.0,
|
| 58 |
+
"grad_norm": 4.197076797485352,
|
| 59 |
+
"learning_rate": 3.99644128113879e-05,
|
| 60 |
+
"loss": 1.8007,
|
| 61 |
+
"step": 564
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.0,
|
| 65 |
+
"eval_loss": 1.8560636043548584,
|
| 66 |
+
"eval_runtime": 4.1817,
|
| 67 |
+
"eval_samples_per_second": 56.675,
|
| 68 |
+
"eval_steps_per_second": 7.174,
|
| 69 |
+
"step": 564
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.25,
|
| 73 |
+
"grad_norm": 5.801040172576904,
|
| 74 |
+
"learning_rate": 3.7455516014234874e-05,
|
| 75 |
+
"loss": 1.4215,
|
| 76 |
+
"step": 705
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.25,
|
| 80 |
+
"eval_loss": 1.9399982690811157,
|
| 81 |
+
"eval_runtime": 4.1763,
|
| 82 |
+
"eval_samples_per_second": 56.749,
|
| 83 |
+
"eval_steps_per_second": 7.183,
|
| 84 |
+
"step": 705
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.51,
|
| 88 |
+
"grad_norm": 3.8744606971740723,
|
| 89 |
+
"learning_rate": 3.494661921708185e-05,
|
| 90 |
+
"loss": 1.4322,
|
| 91 |
+
"step": 846
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.51,
|
| 95 |
+
"eval_loss": 1.8941714763641357,
|
| 96 |
+
"eval_runtime": 4.1838,
|
| 97 |
+
"eval_samples_per_second": 56.648,
|
| 98 |
+
"eval_steps_per_second": 7.171,
|
| 99 |
+
"step": 846
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.76,
|
| 103 |
+
"grad_norm": 5.074963092803955,
|
| 104 |
+
"learning_rate": 3.243772241992883e-05,
|
| 105 |
+
"loss": 1.4325,
|
| 106 |
+
"step": 987
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.76,
|
| 110 |
+
"eval_loss": 1.8861587047576904,
|
| 111 |
+
"eval_runtime": 4.1802,
|
| 112 |
+
"eval_samples_per_second": 56.696,
|
| 113 |
+
"eval_steps_per_second": 7.177,
|
| 114 |
+
"step": 987
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.01,
|
| 118 |
+
"grad_norm": 4.776240348815918,
|
| 119 |
+
"learning_rate": 2.9928825622775803e-05,
|
| 120 |
+
"loss": 1.4241,
|
| 121 |
+
"step": 1128
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.01,
|
| 125 |
+
"eval_loss": 1.9016921520233154,
|
| 126 |
+
"eval_runtime": 4.1862,
|
| 127 |
+
"eval_samples_per_second": 56.614,
|
| 128 |
+
"eval_steps_per_second": 7.166,
|
| 129 |
+
"step": 1128
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.26,
|
| 133 |
+
"grad_norm": 6.694357395172119,
|
| 134 |
+
"learning_rate": 2.7419928825622775e-05,
|
| 135 |
+
"loss": 0.7606,
|
| 136 |
+
"step": 1269
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.26,
|
| 140 |
+
"eval_loss": 2.2999789714813232,
|
| 141 |
+
"eval_runtime": 4.1771,
|
| 142 |
+
"eval_samples_per_second": 56.738,
|
| 143 |
+
"eval_steps_per_second": 7.182,
|
| 144 |
+
"step": 1269
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 2.51,
|
| 148 |
+
"grad_norm": 24.188169479370117,
|
| 149 |
+
"learning_rate": 2.4911032028469753e-05,
|
| 150 |
+
"loss": 0.7631,
|
| 151 |
+
"step": 1410
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.51,
|
| 155 |
+
"eval_loss": 2.3000378608703613,
|
| 156 |
+
"eval_runtime": 4.1828,
|
| 157 |
+
"eval_samples_per_second": 56.661,
|
| 158 |
+
"eval_steps_per_second": 7.172,
|
| 159 |
+
"step": 1410
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.76,
|
| 163 |
+
"grad_norm": 5.172097206115723,
|
| 164 |
+
"learning_rate": 2.2402135231316725e-05,
|
| 165 |
+
"loss": 0.7264,
|
| 166 |
+
"step": 1551
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.76,
|
| 170 |
+
"eval_loss": 2.3029186725616455,
|
| 171 |
+
"eval_runtime": 4.1769,
|
| 172 |
+
"eval_samples_per_second": 56.741,
|
| 173 |
+
"eval_steps_per_second": 7.182,
|
| 174 |
+
"step": 1551
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 3.01,
|
| 178 |
+
"grad_norm": 3.475619077682495,
|
| 179 |
+
"learning_rate": 1.9893238434163703e-05,
|
| 180 |
+
"loss": 0.7021,
|
| 181 |
+
"step": 1692
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 3.01,
|
| 185 |
+
"eval_loss": 2.3999218940734863,
|
| 186 |
+
"eval_runtime": 4.1882,
|
| 187 |
+
"eval_samples_per_second": 56.587,
|
| 188 |
+
"eval_steps_per_second": 7.163,
|
| 189 |
+
"step": 1692
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 3.26,
|
| 193 |
+
"grad_norm": 4.135960102081299,
|
| 194 |
+
"learning_rate": 1.7384341637010675e-05,
|
| 195 |
+
"loss": 0.2238,
|
| 196 |
+
"step": 1833
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.26,
|
| 200 |
+
"eval_loss": 2.7608110904693604,
|
| 201 |
+
"eval_runtime": 4.1782,
|
| 202 |
+
"eval_samples_per_second": 56.723,
|
| 203 |
+
"eval_steps_per_second": 7.18,
|
| 204 |
+
"step": 1833
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.51,
|
| 208 |
+
"grad_norm": 3.5472917556762695,
|
| 209 |
+
"learning_rate": 1.4875444839857652e-05,
|
| 210 |
+
"loss": 0.3114,
|
| 211 |
+
"step": 1974
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.51,
|
| 215 |
+
"eval_loss": 2.845644474029541,
|
| 216 |
+
"eval_runtime": 4.1819,
|
| 217 |
+
"eval_samples_per_second": 56.673,
|
| 218 |
+
"eval_steps_per_second": 7.174,
|
| 219 |
+
"step": 1974
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 3.76,
|
| 223 |
+
"grad_norm": 4.326556205749512,
|
| 224 |
+
"learning_rate": 1.2366548042704627e-05,
|
| 225 |
+
"loss": 0.2282,
|
| 226 |
+
"step": 2115
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.76,
|
| 230 |
+
"eval_loss": 2.8092262744903564,
|
| 231 |
+
"eval_runtime": 4.1782,
|
| 232 |
+
"eval_samples_per_second": 56.723,
|
| 233 |
+
"eval_steps_per_second": 7.18,
|
| 234 |
+
"step": 2115
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.01,
|
| 238 |
+
"grad_norm": 2.737431049346924,
|
| 239 |
+
"learning_rate": 9.857651245551602e-06,
|
| 240 |
+
"loss": 0.2086,
|
| 241 |
+
"step": 2256
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 4.01,
|
| 245 |
+
"eval_loss": 2.9099254608154297,
|
| 246 |
+
"eval_runtime": 4.1802,
|
| 247 |
+
"eval_samples_per_second": 56.696,
|
| 248 |
+
"eval_steps_per_second": 7.177,
|
| 249 |
+
"step": 2256
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 4.27,
|
| 253 |
+
"grad_norm": 3.1757376194000244,
|
| 254 |
+
"learning_rate": 7.348754448398577e-06,
|
| 255 |
+
"loss": 0.0954,
|
| 256 |
+
"step": 2397
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.27,
|
| 260 |
+
"eval_loss": 3.1383473873138428,
|
| 261 |
+
"eval_runtime": 4.1771,
|
| 262 |
+
"eval_samples_per_second": 56.738,
|
| 263 |
+
"eval_steps_per_second": 7.182,
|
| 264 |
+
"step": 2397
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.52,
|
| 268 |
+
"grad_norm": 2.6402652263641357,
|
| 269 |
+
"learning_rate": 4.839857651245551e-06,
|
| 270 |
+
"loss": 0.1015,
|
| 271 |
+
"step": 2538
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 4.52,
|
| 275 |
+
"eval_loss": 3.1500625610351562,
|
| 276 |
+
"eval_runtime": 4.1764,
|
| 277 |
+
"eval_samples_per_second": 56.747,
|
| 278 |
+
"eval_steps_per_second": 7.183,
|
| 279 |
+
"step": 2538
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 4.77,
|
| 283 |
+
"grad_norm": 3.826103687286377,
|
| 284 |
+
"learning_rate": 2.330960854092527e-06,
|
| 285 |
+
"loss": 0.0769,
|
| 286 |
+
"step": 2679
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 4.77,
|
| 290 |
+
"eval_loss": 3.1649973392486572,
|
| 291 |
+
"eval_runtime": 4.1784,
|
| 292 |
+
"eval_samples_per_second": 56.72,
|
| 293 |
+
"eval_steps_per_second": 7.18,
|
| 294 |
+
"step": 2679
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.0,
|
| 298 |
+
"step": 2810,
|
| 299 |
+
"total_flos": 6693708929433600.0,
|
| 300 |
+
"train_loss": 0.8862062440648197,
|
| 301 |
+
"train_runtime": 1654.6028,
|
| 302 |
+
"train_samples_per_second": 5.092,
|
| 303 |
+
"train_steps_per_second": 1.698
|
| 304 |
+
}
|
| 305 |
+
],
|
| 306 |
+
"logging_steps": 141,
|
| 307 |
+
"max_steps": 2810,
|
| 308 |
+
"num_input_tokens_seen": 0,
|
| 309 |
+
"num_train_epochs": 5,
|
| 310 |
+
"save_steps": 141,
|
| 311 |
+
"total_flos": 6693708929433600.0,
|
| 312 |
+
"train_batch_size": 3,
|
| 313 |
+
"trial_name": null,
|
| 314 |
+
"trial_params": null
|
| 315 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4dc1f7732f7b8af990c8255a90721acbe80826b89155ba2c5c8f68c78d032de5
|
| 3 |
+
size 4856
|