Uploading folder contents
Browse files- config.json +29 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +44 -0
- tokenizer.json +0 -0
- tokenizer_config.json +80 -0
- trainer_state.json +953 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "model/Qwen1.5-0.5B-2048",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 5,
|
| 8 |
+
"eos_token_id": 6,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1024,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 2816,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 24,
|
| 18 |
+
"num_key_value_heads": 16,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000.0,
|
| 22 |
+
"sliding_window": null,
|
| 23 |
+
"tie_word_embeddings": true,
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.46.1",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"use_sliding_window": false,
|
| 28 |
+
"vocab_size": 10000
|
| 29 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 5,
|
| 4 |
+
"eos_token_id": 6,
|
| 5 |
+
"transformers_version": "4.46.1"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c43a52d3109cd7b9b6b3696bbc5ebe08962bf227525ba6f40c20c2b908032fe
|
| 3 |
+
size 1274613488
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b55cfb2704ab2cca2daa71564decee338183456eea61e0a39590565f8a3806f8
|
| 3 |
+
size 2549405370
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4af18a946d1ce1168c586b88ffd0baf2f3e897f35ee65446f82902be1bd8691b
|
| 3 |
+
size 15984
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f444236b761142138219480386b6b4b54660cd5e80f4a75a46d97dad2a9088e
|
| 3 |
+
size 15984
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fa4cd9f80d8babcfc51862d18c5073cb5c37c377eb5300a8b32609a55b4b241
|
| 3 |
+
size 15984
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2a5f8619d27df9aa9dc9532fbb02469a26d63eb822f697e6eaf4ad05d7ddceb
|
| 3 |
+
size 15984
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ac4e33445d6574decb4fe266c8c3fad4ee97945783a023042e133df321cb19c
|
| 3 |
+
size 15984
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c54b53ccb50daf795323d7e331186b46551f92370c6fee070191ca71fead2ce
|
| 3 |
+
size 15984
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25f24d088eabd00aa72f6beee45fe4a7cc3e773f29ab3cf93fe7ea7ce22ebee1
|
| 3 |
+
size 15984
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c93e81803ea053a616dbf670a9b0cb29fa331b51fa4229f9f91129dc5cfee471
|
| 3 |
+
size 15984
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:015019ac0291dd18a2c7676b26deda28198807679de01aeffd185044b8b31ee4
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"mask_token": {
|
| 17 |
+
"content": "[MASK]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"pad_token": {
|
| 24 |
+
"content": "[PAD]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"sep_token": {
|
| 31 |
+
"content": "[SEP]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"unk_token": {
|
| 38 |
+
"content": "[UNK]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
}
|
| 44 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "<s>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "</s>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"9006": {
|
| 60 |
+
"content": "<|endoftext|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
}
|
| 67 |
+
},
|
| 68 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\n' }}{% endif %}{% endfor %}",
|
| 69 |
+
"clean_up_tokenization_spaces": false,
|
| 70 |
+
"cls_token": "[CLS]",
|
| 71 |
+
"eos_token": "<|endoftext|>",
|
| 72 |
+
"mask_token": "[MASK]",
|
| 73 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 74 |
+
"pad_token": "[PAD]",
|
| 75 |
+
"padding_side": "right",
|
| 76 |
+
"sep_token": "[SEP]",
|
| 77 |
+
"split_special_tokens": false,
|
| 78 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 79 |
+
"unk_token": "[UNK]"
|
| 80 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,953 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.816696914700545,
|
| 5 |
+
"eval_steps": 5,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.07259528130671507,
|
| 13 |
+
"eval_loss": 9.010322570800781,
|
| 14 |
+
"eval_runtime": 14.7033,
|
| 15 |
+
"eval_samples_per_second": 193.834,
|
| 16 |
+
"eval_steps_per_second": 6.121,
|
| 17 |
+
"step": 5
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.14519056261343014,
|
| 21 |
+
"grad_norm": 61.32562255859375,
|
| 22 |
+
"learning_rate": 5.882352941176471e-07,
|
| 23 |
+
"loss": 8.9719,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.14519056261343014,
|
| 28 |
+
"eval_loss": 8.331480026245117,
|
| 29 |
+
"eval_runtime": 14.4782,
|
| 30 |
+
"eval_samples_per_second": 196.847,
|
| 31 |
+
"eval_steps_per_second": 6.216,
|
| 32 |
+
"step": 10
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.2177858439201452,
|
| 36 |
+
"eval_loss": 7.261224746704102,
|
| 37 |
+
"eval_runtime": 14.4912,
|
| 38 |
+
"eval_samples_per_second": 196.672,
|
| 39 |
+
"eval_steps_per_second": 6.211,
|
| 40 |
+
"step": 15
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.29038112522686027,
|
| 44 |
+
"grad_norm": 36.82855224609375,
|
| 45 |
+
"learning_rate": 1.1764705882352942e-06,
|
| 46 |
+
"loss": 7.3553,
|
| 47 |
+
"step": 20
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.29038112522686027,
|
| 51 |
+
"eval_loss": 6.074642181396484,
|
| 52 |
+
"eval_runtime": 14.691,
|
| 53 |
+
"eval_samples_per_second": 193.996,
|
| 54 |
+
"eval_steps_per_second": 6.126,
|
| 55 |
+
"step": 20
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.3629764065335753,
|
| 59 |
+
"eval_loss": 5.163372993469238,
|
| 60 |
+
"eval_runtime": 15.1407,
|
| 61 |
+
"eval_samples_per_second": 188.234,
|
| 62 |
+
"eval_steps_per_second": 5.944,
|
| 63 |
+
"step": 25
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.4355716878402904,
|
| 67 |
+
"grad_norm": 15.787286758422852,
|
| 68 |
+
"learning_rate": 1.7647058823529414e-06,
|
| 69 |
+
"loss": 5.2685,
|
| 70 |
+
"step": 30
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.4355716878402904,
|
| 74 |
+
"eval_loss": 4.470004081726074,
|
| 75 |
+
"eval_runtime": 15.1071,
|
| 76 |
+
"eval_samples_per_second": 188.653,
|
| 77 |
+
"eval_steps_per_second": 5.957,
|
| 78 |
+
"step": 30
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.5081669691470054,
|
| 82 |
+
"eval_loss": 4.0810675621032715,
|
| 83 |
+
"eval_runtime": 14.5048,
|
| 84 |
+
"eval_samples_per_second": 196.487,
|
| 85 |
+
"eval_steps_per_second": 6.205,
|
| 86 |
+
"step": 35
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.5807622504537205,
|
| 90 |
+
"grad_norm": 10.20334529876709,
|
| 91 |
+
"learning_rate": 2.3529411764705885e-06,
|
| 92 |
+
"loss": 4.1368,
|
| 93 |
+
"step": 40
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5807622504537205,
|
| 97 |
+
"eval_loss": 3.8141613006591797,
|
| 98 |
+
"eval_runtime": 15.9364,
|
| 99 |
+
"eval_samples_per_second": 178.836,
|
| 100 |
+
"eval_steps_per_second": 5.647,
|
| 101 |
+
"step": 40
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.6533575317604355,
|
| 105 |
+
"eval_loss": 3.5930957794189453,
|
| 106 |
+
"eval_runtime": 14.4905,
|
| 107 |
+
"eval_samples_per_second": 196.68,
|
| 108 |
+
"eval_steps_per_second": 6.211,
|
| 109 |
+
"step": 45
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.7259528130671506,
|
| 113 |
+
"grad_norm": 7.136198997497559,
|
| 114 |
+
"learning_rate": 2.9411764705882355e-06,
|
| 115 |
+
"loss": 3.6309,
|
| 116 |
+
"step": 50
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.7259528130671506,
|
| 120 |
+
"eval_loss": 3.3911800384521484,
|
| 121 |
+
"eval_runtime": 14.4927,
|
| 122 |
+
"eval_samples_per_second": 196.65,
|
| 123 |
+
"eval_steps_per_second": 6.21,
|
| 124 |
+
"step": 50
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.7985480943738656,
|
| 128 |
+
"eval_loss": 3.1644599437713623,
|
| 129 |
+
"eval_runtime": 14.7036,
|
| 130 |
+
"eval_samples_per_second": 193.83,
|
| 131 |
+
"eval_steps_per_second": 6.121,
|
| 132 |
+
"step": 55
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.8711433756805808,
|
| 136 |
+
"grad_norm": 5.402222633361816,
|
| 137 |
+
"learning_rate": 3.529411764705883e-06,
|
| 138 |
+
"loss": 3.1939,
|
| 139 |
+
"step": 60
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.8711433756805808,
|
| 143 |
+
"eval_loss": 2.9349365234375,
|
| 144 |
+
"eval_runtime": 14.4983,
|
| 145 |
+
"eval_samples_per_second": 196.575,
|
| 146 |
+
"eval_steps_per_second": 6.208,
|
| 147 |
+
"step": 60
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.9437386569872959,
|
| 151 |
+
"eval_loss": 2.723186731338501,
|
| 152 |
+
"eval_runtime": 15.144,
|
| 153 |
+
"eval_samples_per_second": 188.193,
|
| 154 |
+
"eval_steps_per_second": 5.943,
|
| 155 |
+
"step": 65
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.0181488203266789,
|
| 159 |
+
"grad_norm": 3.256094455718994,
|
| 160 |
+
"learning_rate": 4.11764705882353e-06,
|
| 161 |
+
"loss": 2.8201,
|
| 162 |
+
"step": 70
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.0181488203266789,
|
| 166 |
+
"eval_loss": 2.5700125694274902,
|
| 167 |
+
"eval_runtime": 14.5104,
|
| 168 |
+
"eval_samples_per_second": 196.411,
|
| 169 |
+
"eval_steps_per_second": 6.202,
|
| 170 |
+
"step": 70
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.0907441016333939,
|
| 174 |
+
"eval_loss": 2.458405017852783,
|
| 175 |
+
"eval_runtime": 15.1448,
|
| 176 |
+
"eval_samples_per_second": 188.184,
|
| 177 |
+
"eval_steps_per_second": 5.943,
|
| 178 |
+
"step": 75
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.1633393829401089,
|
| 182 |
+
"grad_norm": 3.2226405143737793,
|
| 183 |
+
"learning_rate": 4.705882352941177e-06,
|
| 184 |
+
"loss": 2.4782,
|
| 185 |
+
"step": 80
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.1633393829401089,
|
| 189 |
+
"eval_loss": 2.372328042984009,
|
| 190 |
+
"eval_runtime": 15.1094,
|
| 191 |
+
"eval_samples_per_second": 188.624,
|
| 192 |
+
"eval_steps_per_second": 5.957,
|
| 193 |
+
"step": 80
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.235934664246824,
|
| 197 |
+
"eval_loss": 2.295482873916626,
|
| 198 |
+
"eval_runtime": 14.5213,
|
| 199 |
+
"eval_samples_per_second": 196.264,
|
| 200 |
+
"eval_steps_per_second": 6.198,
|
| 201 |
+
"step": 85
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.308529945553539,
|
| 205 |
+
"grad_norm": 2.7453877925872803,
|
| 206 |
+
"learning_rate": 5.294117647058824e-06,
|
| 207 |
+
"loss": 2.2965,
|
| 208 |
+
"step": 90
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.308529945553539,
|
| 212 |
+
"eval_loss": 2.2384285926818848,
|
| 213 |
+
"eval_runtime": 14.5142,
|
| 214 |
+
"eval_samples_per_second": 196.359,
|
| 215 |
+
"eval_steps_per_second": 6.201,
|
| 216 |
+
"step": 90
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.381125226860254,
|
| 220 |
+
"eval_loss": 2.17990779876709,
|
| 221 |
+
"eval_runtime": 14.501,
|
| 222 |
+
"eval_samples_per_second": 196.538,
|
| 223 |
+
"eval_steps_per_second": 6.206,
|
| 224 |
+
"step": 95
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.453720508166969,
|
| 228 |
+
"grad_norm": 6.855352401733398,
|
| 229 |
+
"learning_rate": 5.882352941176471e-06,
|
| 230 |
+
"loss": 2.1878,
|
| 231 |
+
"step": 100
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.453720508166969,
|
| 235 |
+
"eval_loss": 2.145392894744873,
|
| 236 |
+
"eval_runtime": 14.5309,
|
| 237 |
+
"eval_samples_per_second": 196.134,
|
| 238 |
+
"eval_steps_per_second": 6.194,
|
| 239 |
+
"step": 100
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.526315789473684,
|
| 243 |
+
"eval_loss": 2.10636568069458,
|
| 244 |
+
"eval_runtime": 14.7287,
|
| 245 |
+
"eval_samples_per_second": 193.5,
|
| 246 |
+
"eval_steps_per_second": 6.111,
|
| 247 |
+
"step": 105
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.5989110707803993,
|
| 251 |
+
"grad_norm": 4.385169506072998,
|
| 252 |
+
"learning_rate": 6.470588235294119e-06,
|
| 253 |
+
"loss": 2.1062,
|
| 254 |
+
"step": 110
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.5989110707803993,
|
| 258 |
+
"eval_loss": 2.084491729736328,
|
| 259 |
+
"eval_runtime": 14.5242,
|
| 260 |
+
"eval_samples_per_second": 196.224,
|
| 261 |
+
"eval_steps_per_second": 6.197,
|
| 262 |
+
"step": 110
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.6715063520871143,
|
| 266 |
+
"eval_loss": 2.0510075092315674,
|
| 267 |
+
"eval_runtime": 14.7203,
|
| 268 |
+
"eval_samples_per_second": 193.61,
|
| 269 |
+
"eval_steps_per_second": 6.114,
|
| 270 |
+
"step": 115
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.7441016333938295,
|
| 274 |
+
"grad_norm": 4.6851806640625,
|
| 275 |
+
"learning_rate": 7.058823529411766e-06,
|
| 276 |
+
"loss": 2.051,
|
| 277 |
+
"step": 120
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.7441016333938295,
|
| 281 |
+
"eval_loss": 2.0260279178619385,
|
| 282 |
+
"eval_runtime": 14.742,
|
| 283 |
+
"eval_samples_per_second": 193.325,
|
| 284 |
+
"eval_steps_per_second": 6.105,
|
| 285 |
+
"step": 120
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.8166969147005445,
|
| 289 |
+
"eval_loss": 1.9961732625961304,
|
| 290 |
+
"eval_runtime": 14.5594,
|
| 291 |
+
"eval_samples_per_second": 195.75,
|
| 292 |
+
"eval_steps_per_second": 6.182,
|
| 293 |
+
"step": 125
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.8892921960072595,
|
| 297 |
+
"grad_norm": 3.5994365215301514,
|
| 298 |
+
"learning_rate": 7.647058823529411e-06,
|
| 299 |
+
"loss": 1.9917,
|
| 300 |
+
"step": 130
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.8892921960072595,
|
| 304 |
+
"eval_loss": 1.978654384613037,
|
| 305 |
+
"eval_runtime": 14.7363,
|
| 306 |
+
"eval_samples_per_second": 193.4,
|
| 307 |
+
"eval_steps_per_second": 6.107,
|
| 308 |
+
"step": 130
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.9618874773139745,
|
| 312 |
+
"eval_loss": 1.9525541067123413,
|
| 313 |
+
"eval_runtime": 14.5176,
|
| 314 |
+
"eval_samples_per_second": 196.313,
|
| 315 |
+
"eval_steps_per_second": 6.199,
|
| 316 |
+
"step": 135
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 2.0362976406533577,
|
| 320 |
+
"grad_norm": 4.9513163566589355,
|
| 321 |
+
"learning_rate": 8.23529411764706e-06,
|
| 322 |
+
"loss": 1.9962,
|
| 323 |
+
"step": 140
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 2.0362976406533577,
|
| 327 |
+
"eval_loss": 1.924938678741455,
|
| 328 |
+
"eval_runtime": 15.1427,
|
| 329 |
+
"eval_samples_per_second": 188.21,
|
| 330 |
+
"eval_steps_per_second": 5.943,
|
| 331 |
+
"step": 140
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.1088929219600727,
|
| 335 |
+
"eval_loss": 1.9016236066818237,
|
| 336 |
+
"eval_runtime": 14.7313,
|
| 337 |
+
"eval_samples_per_second": 193.465,
|
| 338 |
+
"eval_steps_per_second": 6.109,
|
| 339 |
+
"step": 145
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.1814882032667877,
|
| 343 |
+
"grad_norm": 3.568028211593628,
|
| 344 |
+
"learning_rate": 8.823529411764707e-06,
|
| 345 |
+
"loss": 1.8953,
|
| 346 |
+
"step": 150
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 2.1814882032667877,
|
| 350 |
+
"eval_loss": 1.8843510150909424,
|
| 351 |
+
"eval_runtime": 14.7585,
|
| 352 |
+
"eval_samples_per_second": 193.109,
|
| 353 |
+
"eval_steps_per_second": 6.098,
|
| 354 |
+
"step": 150
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.2540834845735027,
|
| 358 |
+
"eval_loss": 1.8601508140563965,
|
| 359 |
+
"eval_runtime": 15.9653,
|
| 360 |
+
"eval_samples_per_second": 178.512,
|
| 361 |
+
"eval_steps_per_second": 5.637,
|
| 362 |
+
"step": 155
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.3266787658802177,
|
| 366 |
+
"grad_norm": 3.6408910751342773,
|
| 367 |
+
"learning_rate": 9.411764705882354e-06,
|
| 368 |
+
"loss": 1.8575,
|
| 369 |
+
"step": 160
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.3266787658802177,
|
| 373 |
+
"eval_loss": 1.8396055698394775,
|
| 374 |
+
"eval_runtime": 14.7412,
|
| 375 |
+
"eval_samples_per_second": 193.335,
|
| 376 |
+
"eval_steps_per_second": 6.105,
|
| 377 |
+
"step": 160
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.3992740471869327,
|
| 381 |
+
"eval_loss": 1.8177093267440796,
|
| 382 |
+
"eval_runtime": 14.4208,
|
| 383 |
+
"eval_samples_per_second": 197.631,
|
| 384 |
+
"eval_steps_per_second": 6.241,
|
| 385 |
+
"step": 165
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 2.471869328493648,
|
| 389 |
+
"grad_norm": 2.8271830081939697,
|
| 390 |
+
"learning_rate": 1e-05,
|
| 391 |
+
"loss": 1.8155,
|
| 392 |
+
"step": 170
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 2.471869328493648,
|
| 396 |
+
"eval_loss": 1.8003019094467163,
|
| 397 |
+
"eval_runtime": 14.5315,
|
| 398 |
+
"eval_samples_per_second": 196.126,
|
| 399 |
+
"eval_steps_per_second": 6.193,
|
| 400 |
+
"step": 170
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.5444646098003627,
|
| 404 |
+
"eval_loss": 1.7784119844436646,
|
| 405 |
+
"eval_runtime": 15.154,
|
| 406 |
+
"eval_samples_per_second": 188.069,
|
| 407 |
+
"eval_steps_per_second": 5.939,
|
| 408 |
+
"step": 175
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.617059891107078,
|
| 412 |
+
"grad_norm": 3.2862439155578613,
|
| 413 |
+
"learning_rate": 1.0588235294117648e-05,
|
| 414 |
+
"loss": 1.7693,
|
| 415 |
+
"step": 180
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.617059891107078,
|
| 419 |
+
"eval_loss": 1.7559484243392944,
|
| 420 |
+
"eval_runtime": 14.5122,
|
| 421 |
+
"eval_samples_per_second": 196.387,
|
| 422 |
+
"eval_steps_per_second": 6.202,
|
| 423 |
+
"step": 180
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.689655172413793,
|
| 427 |
+
"eval_loss": 1.7348463535308838,
|
| 428 |
+
"eval_runtime": 14.7357,
|
| 429 |
+
"eval_samples_per_second": 193.408,
|
| 430 |
+
"eval_steps_per_second": 6.108,
|
| 431 |
+
"step": 185
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.762250453720508,
|
| 435 |
+
"grad_norm": 2.25696063041687,
|
| 436 |
+
"learning_rate": 1.1176470588235295e-05,
|
| 437 |
+
"loss": 1.7385,
|
| 438 |
+
"step": 190
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.762250453720508,
|
| 442 |
+
"eval_loss": 1.7172671556472778,
|
| 443 |
+
"eval_runtime": 15.1701,
|
| 444 |
+
"eval_samples_per_second": 187.869,
|
| 445 |
+
"eval_steps_per_second": 5.933,
|
| 446 |
+
"step": 190
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.834845735027223,
|
| 450 |
+
"eval_loss": 1.695427656173706,
|
| 451 |
+
"eval_runtime": 14.4705,
|
| 452 |
+
"eval_samples_per_second": 196.952,
|
| 453 |
+
"eval_steps_per_second": 6.22,
|
| 454 |
+
"step": 195
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 2.907441016333938,
|
| 458 |
+
"grad_norm": 2.0395424365997314,
|
| 459 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 460 |
+
"loss": 1.6946,
|
| 461 |
+
"step": 200
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 2.907441016333938,
|
| 465 |
+
"eval_loss": 1.671271562576294,
|
| 466 |
+
"eval_runtime": 14.7358,
|
| 467 |
+
"eval_samples_per_second": 193.406,
|
| 468 |
+
"eval_steps_per_second": 6.108,
|
| 469 |
+
"step": 200
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.9800362976406536,
|
| 473 |
+
"eval_loss": 1.6319493055343628,
|
| 474 |
+
"eval_runtime": 14.5206,
|
| 475 |
+
"eval_samples_per_second": 196.272,
|
| 476 |
+
"eval_steps_per_second": 6.198,
|
| 477 |
+
"step": 205
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.0544464609800364,
|
| 481 |
+
"grad_norm": 2.749896764755249,
|
| 482 |
+
"learning_rate": 1.235294117647059e-05,
|
| 483 |
+
"loss": 1.6563,
|
| 484 |
+
"step": 210
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 3.0544464609800364,
|
| 488 |
+
"eval_loss": 1.5363059043884277,
|
| 489 |
+
"eval_runtime": 14.7218,
|
| 490 |
+
"eval_samples_per_second": 193.591,
|
| 491 |
+
"eval_steps_per_second": 6.113,
|
| 492 |
+
"step": 210
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 3.1270417422867514,
|
| 496 |
+
"eval_loss": 1.4164518117904663,
|
| 497 |
+
"eval_runtime": 14.5379,
|
| 498 |
+
"eval_samples_per_second": 196.04,
|
| 499 |
+
"eval_steps_per_second": 6.191,
|
| 500 |
+
"step": 215
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.1996370235934664,
|
| 504 |
+
"grad_norm": 5.012214183807373,
|
| 505 |
+
"learning_rate": 1.2941176470588238e-05,
|
| 506 |
+
"loss": 1.4353,
|
| 507 |
+
"step": 220
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 3.1996370235934664,
|
| 511 |
+
"eval_loss": 1.386569857597351,
|
| 512 |
+
"eval_runtime": 14.5397,
|
| 513 |
+
"eval_samples_per_second": 196.015,
|
| 514 |
+
"eval_steps_per_second": 6.19,
|
| 515 |
+
"step": 220
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 3.2722323049001814,
|
| 519 |
+
"eval_loss": 1.3649249076843262,
|
| 520 |
+
"eval_runtime": 14.7399,
|
| 521 |
+
"eval_samples_per_second": 193.353,
|
| 522 |
+
"eval_steps_per_second": 6.106,
|
| 523 |
+
"step": 225
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 3.344827586206897,
|
| 527 |
+
"grad_norm": 4.3066840171813965,
|
| 528 |
+
"learning_rate": 1.3529411764705885e-05,
|
| 529 |
+
"loss": 1.358,
|
| 530 |
+
"step": 230
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.344827586206897,
|
| 534 |
+
"eval_loss": 1.3398939371109009,
|
| 535 |
+
"eval_runtime": 14.8356,
|
| 536 |
+
"eval_samples_per_second": 192.106,
|
| 537 |
+
"eval_steps_per_second": 6.067,
|
| 538 |
+
"step": 230
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 3.417422867513612,
|
| 542 |
+
"eval_loss": 1.3146777153015137,
|
| 543 |
+
"eval_runtime": 14.4166,
|
| 544 |
+
"eval_samples_per_second": 197.688,
|
| 545 |
+
"eval_steps_per_second": 6.243,
|
| 546 |
+
"step": 235
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 3.490018148820327,
|
| 550 |
+
"grad_norm": 4.974428653717041,
|
| 551 |
+
"learning_rate": 1.4117647058823532e-05,
|
| 552 |
+
"loss": 1.319,
|
| 553 |
+
"step": 240
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 3.490018148820327,
|
| 557 |
+
"eval_loss": 1.306829810142517,
|
| 558 |
+
"eval_runtime": 14.737,
|
| 559 |
+
"eval_samples_per_second": 193.391,
|
| 560 |
+
"eval_steps_per_second": 6.107,
|
| 561 |
+
"step": 240
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 3.562613430127042,
|
| 565 |
+
"eval_loss": 1.2938297986984253,
|
| 566 |
+
"eval_runtime": 14.5503,
|
| 567 |
+
"eval_samples_per_second": 195.872,
|
| 568 |
+
"eval_steps_per_second": 6.185,
|
| 569 |
+
"step": 245
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.635208711433757,
|
| 573 |
+
"grad_norm": 3.983586549758911,
|
| 574 |
+
"learning_rate": 1.4705882352941179e-05,
|
| 575 |
+
"loss": 1.2901,
|
| 576 |
+
"step": 250
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 3.635208711433757,
|
| 580 |
+
"eval_loss": 1.2760024070739746,
|
| 581 |
+
"eval_runtime": 14.542,
|
| 582 |
+
"eval_samples_per_second": 195.984,
|
| 583 |
+
"eval_steps_per_second": 6.189,
|
| 584 |
+
"step": 250
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.707803992740472,
|
| 588 |
+
"eval_loss": 1.2649155855178833,
|
| 589 |
+
"eval_runtime": 14.5224,
|
| 590 |
+
"eval_samples_per_second": 196.249,
|
| 591 |
+
"eval_steps_per_second": 6.197,
|
| 592 |
+
"step": 255
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 3.780399274047187,
|
| 596 |
+
"grad_norm": 3.8143765926361084,
|
| 597 |
+
"learning_rate": 1.5294117647058822e-05,
|
| 598 |
+
"loss": 1.2606,
|
| 599 |
+
"step": 260
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 3.780399274047187,
|
| 603 |
+
"eval_loss": 1.2517699003219604,
|
| 604 |
+
"eval_runtime": 14.7363,
|
| 605 |
+
"eval_samples_per_second": 193.4,
|
| 606 |
+
"eval_steps_per_second": 6.107,
|
| 607 |
+
"step": 260
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 3.8529945553539022,
|
| 611 |
+
"eval_loss": 1.2391242980957031,
|
| 612 |
+
"eval_runtime": 14.7355,
|
| 613 |
+
"eval_samples_per_second": 193.411,
|
| 614 |
+
"eval_steps_per_second": 6.108,
|
| 615 |
+
"step": 265
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.925589836660617,
|
| 619 |
+
"grad_norm": 1.8632169961929321,
|
| 620 |
+
"learning_rate": 1.5882352941176473e-05,
|
| 621 |
+
"loss": 1.235,
|
| 622 |
+
"step": 270
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 3.925589836660617,
|
| 626 |
+
"eval_loss": 1.2270861864089966,
|
| 627 |
+
"eval_runtime": 14.5585,
|
| 628 |
+
"eval_samples_per_second": 195.761,
|
| 629 |
+
"eval_steps_per_second": 6.182,
|
| 630 |
+
"step": 270
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 3.9981851179673322,
|
| 634 |
+
"eval_loss": 1.2150429487228394,
|
| 635 |
+
"eval_runtime": 14.5451,
|
| 636 |
+
"eval_samples_per_second": 195.943,
|
| 637 |
+
"eval_steps_per_second": 6.188,
|
| 638 |
+
"step": 275
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 4.072595281306715,
|
| 642 |
+
"grad_norm": 1.5080467462539673,
|
| 643 |
+
"learning_rate": 1.647058823529412e-05,
|
| 644 |
+
"loss": 1.245,
|
| 645 |
+
"step": 280
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 4.072595281306715,
|
| 649 |
+
"eval_loss": 1.2036006450653076,
|
| 650 |
+
"eval_runtime": 14.5464,
|
| 651 |
+
"eval_samples_per_second": 195.925,
|
| 652 |
+
"eval_steps_per_second": 6.187,
|
| 653 |
+
"step": 280
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 4.14519056261343,
|
| 657 |
+
"eval_loss": 1.1897691488265991,
|
| 658 |
+
"eval_runtime": 15.1706,
|
| 659 |
+
"eval_samples_per_second": 187.863,
|
| 660 |
+
"eval_steps_per_second": 5.933,
|
| 661 |
+
"step": 285
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 4.217785843920145,
|
| 665 |
+
"grad_norm": 1.4935036897659302,
|
| 666 |
+
"learning_rate": 1.7058823529411767e-05,
|
| 667 |
+
"loss": 1.1878,
|
| 668 |
+
"step": 290
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 4.217785843920145,
|
| 672 |
+
"eval_loss": 1.1819372177124023,
|
| 673 |
+
"eval_runtime": 15.1365,
|
| 674 |
+
"eval_samples_per_second": 188.286,
|
| 675 |
+
"eval_steps_per_second": 5.946,
|
| 676 |
+
"step": 290
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 4.29038112522686,
|
| 680 |
+
"eval_loss": 1.1706080436706543,
|
| 681 |
+
"eval_runtime": 14.7363,
|
| 682 |
+
"eval_samples_per_second": 193.399,
|
| 683 |
+
"eval_steps_per_second": 6.107,
|
| 684 |
+
"step": 295
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 4.362976406533575,
|
| 688 |
+
"grad_norm": 1.3859846591949463,
|
| 689 |
+
"learning_rate": 1.7647058823529414e-05,
|
| 690 |
+
"loss": 1.1657,
|
| 691 |
+
"step": 300
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 4.362976406533575,
|
| 695 |
+
"eval_loss": 1.1605490446090698,
|
| 696 |
+
"eval_runtime": 14.5424,
|
| 697 |
+
"eval_samples_per_second": 195.979,
|
| 698 |
+
"eval_steps_per_second": 6.189,
|
| 699 |
+
"step": 300
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 4.43557168784029,
|
| 703 |
+
"eval_loss": 1.1499196290969849,
|
| 704 |
+
"eval_runtime": 14.7387,
|
| 705 |
+
"eval_samples_per_second": 193.369,
|
| 706 |
+
"eval_steps_per_second": 6.106,
|
| 707 |
+
"step": 305
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 4.508166969147005,
|
| 711 |
+
"grad_norm": 1.1665586233139038,
|
| 712 |
+
"learning_rate": 1.823529411764706e-05,
|
| 713 |
+
"loss": 1.1403,
|
| 714 |
+
"step": 310
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 4.508166969147005,
|
| 718 |
+
"eval_loss": 1.1420775651931763,
|
| 719 |
+
"eval_runtime": 14.5407,
|
| 720 |
+
"eval_samples_per_second": 196.002,
|
| 721 |
+
"eval_steps_per_second": 6.19,
|
| 722 |
+
"step": 310
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 4.580762250453721,
|
| 726 |
+
"eval_loss": 1.1320960521697998,
|
| 727 |
+
"eval_runtime": 14.449,
|
| 728 |
+
"eval_samples_per_second": 197.245,
|
| 729 |
+
"eval_steps_per_second": 6.229,
|
| 730 |
+
"step": 315
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 4.653357531760435,
|
| 734 |
+
"grad_norm": 0.8766835331916809,
|
| 735 |
+
"learning_rate": 1.8823529411764708e-05,
|
| 736 |
+
"loss": 1.1281,
|
| 737 |
+
"step": 320
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 4.653357531760435,
|
| 741 |
+
"eval_loss": 1.1212010383605957,
|
| 742 |
+
"eval_runtime": 14.5316,
|
| 743 |
+
"eval_samples_per_second": 196.124,
|
| 744 |
+
"eval_steps_per_second": 6.193,
|
| 745 |
+
"step": 320
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 4.725952813067151,
|
| 749 |
+
"eval_loss": 1.1128367185592651,
|
| 750 |
+
"eval_runtime": 14.7418,
|
| 751 |
+
"eval_samples_per_second": 193.328,
|
| 752 |
+
"eval_steps_per_second": 6.105,
|
| 753 |
+
"step": 325
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 4.798548094373865,
|
| 757 |
+
"grad_norm": 0.9714537858963013,
|
| 758 |
+
"learning_rate": 1.9411764705882355e-05,
|
| 759 |
+
"loss": 1.1102,
|
| 760 |
+
"step": 330
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 4.798548094373865,
|
| 764 |
+
"eval_loss": 1.1062639951705933,
|
| 765 |
+
"eval_runtime": 14.5436,
|
| 766 |
+
"eval_samples_per_second": 195.962,
|
| 767 |
+
"eval_steps_per_second": 6.188,
|
| 768 |
+
"step": 330
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 4.871143375680581,
|
| 772 |
+
"eval_loss": 1.0999449491500854,
|
| 773 |
+
"eval_runtime": 14.737,
|
| 774 |
+
"eval_samples_per_second": 193.39,
|
| 775 |
+
"eval_steps_per_second": 6.107,
|
| 776 |
+
"step": 335
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 4.943738656987296,
|
| 780 |
+
"grad_norm": 1.059080719947815,
|
| 781 |
+
"learning_rate": 2e-05,
|
| 782 |
+
"loss": 1.0955,
|
| 783 |
+
"step": 340
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 4.943738656987296,
|
| 787 |
+
"eval_loss": 1.0925077199935913,
|
| 788 |
+
"eval_runtime": 15.1727,
|
| 789 |
+
"eval_samples_per_second": 187.838,
|
| 790 |
+
"eval_steps_per_second": 5.932,
|
| 791 |
+
"step": 340
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 5.018148820326679,
|
| 795 |
+
"eval_loss": 1.0864582061767578,
|
| 796 |
+
"eval_runtime": 15.1712,
|
| 797 |
+
"eval_samples_per_second": 187.857,
|
| 798 |
+
"eval_steps_per_second": 5.932,
|
| 799 |
+
"step": 345
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 5.090744101633394,
|
| 803 |
+
"grad_norm": 0.91865074634552,
|
| 804 |
+
"learning_rate": 1.9999472984871734e-05,
|
| 805 |
+
"loss": 1.1042,
|
| 806 |
+
"step": 350
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 5.090744101633394,
|
| 810 |
+
"eval_loss": 1.0811607837677002,
|
| 811 |
+
"eval_runtime": 14.5348,
|
| 812 |
+
"eval_samples_per_second": 196.082,
|
| 813 |
+
"eval_steps_per_second": 6.192,
|
| 814 |
+
"step": 350
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 5.163339382940109,
|
| 818 |
+
"eval_loss": 1.0728111267089844,
|
| 819 |
+
"eval_runtime": 14.7409,
|
| 820 |
+
"eval_samples_per_second": 193.339,
|
| 821 |
+
"eval_steps_per_second": 6.105,
|
| 822 |
+
"step": 355
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 5.235934664246824,
|
| 826 |
+
"grad_norm": 1.024660348892212,
|
| 827 |
+
"learning_rate": 1.9997891995035914e-05,
|
| 828 |
+
"loss": 1.071,
|
| 829 |
+
"step": 360
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 5.235934664246824,
|
| 833 |
+
"eval_loss": 1.0691807270050049,
|
| 834 |
+
"eval_runtime": 15.1545,
|
| 835 |
+
"eval_samples_per_second": 188.063,
|
| 836 |
+
"eval_steps_per_second": 5.939,
|
| 837 |
+
"step": 360
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 5.308529945553539,
|
| 841 |
+
"eval_loss": 1.06400465965271,
|
| 842 |
+
"eval_runtime": 14.5462,
|
| 843 |
+
"eval_samples_per_second": 195.928,
|
| 844 |
+
"eval_steps_per_second": 6.187,
|
| 845 |
+
"step": 365
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 5.381125226860254,
|
| 849 |
+
"grad_norm": 0.9005317687988281,
|
| 850 |
+
"learning_rate": 1.999525719713366e-05,
|
| 851 |
+
"loss": 1.0549,
|
| 852 |
+
"step": 370
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 5.381125226860254,
|
| 856 |
+
"eval_loss": 1.0573673248291016,
|
| 857 |
+
"eval_runtime": 14.5465,
|
| 858 |
+
"eval_samples_per_second": 195.923,
|
| 859 |
+
"eval_steps_per_second": 6.187,
|
| 860 |
+
"step": 370
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 5.4537205081669695,
|
| 864 |
+
"eval_loss": 1.0534714460372925,
|
| 865 |
+
"eval_runtime": 14.5473,
|
| 866 |
+
"eval_samples_per_second": 195.913,
|
| 867 |
+
"eval_steps_per_second": 6.187,
|
| 868 |
+
"step": 375
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 5.526315789473684,
|
| 872 |
+
"grad_norm": 1.0956518650054932,
|
| 873 |
+
"learning_rate": 1.999156886888064e-05,
|
| 874 |
+
"loss": 1.0438,
|
| 875 |
+
"step": 380
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 5.526315789473684,
|
| 879 |
+
"eval_loss": 1.0502424240112305,
|
| 880 |
+
"eval_runtime": 14.7423,
|
| 881 |
+
"eval_samples_per_second": 193.321,
|
| 882 |
+
"eval_steps_per_second": 6.105,
|
| 883 |
+
"step": 380
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 5.5989110707803995,
|
| 887 |
+
"eval_loss": 1.0457500219345093,
|
| 888 |
+
"eval_runtime": 14.7486,
|
| 889 |
+
"eval_samples_per_second": 193.239,
|
| 890 |
+
"eval_steps_per_second": 6.102,
|
| 891 |
+
"step": 385
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 5.671506352087114,
|
| 895 |
+
"grad_norm": 0.9397391676902771,
|
| 896 |
+
"learning_rate": 1.998682739903781e-05,
|
| 897 |
+
"loss": 1.041,
|
| 898 |
+
"step": 390
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 5.671506352087114,
|
| 902 |
+
"eval_loss": 1.0433166027069092,
|
| 903 |
+
"eval_runtime": 14.757,
|
| 904 |
+
"eval_samples_per_second": 193.129,
|
| 905 |
+
"eval_steps_per_second": 6.099,
|
| 906 |
+
"step": 390
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 5.7441016333938295,
|
| 910 |
+
"eval_loss": 1.0396827459335327,
|
| 911 |
+
"eval_runtime": 14.7407,
|
| 912 |
+
"eval_samples_per_second": 193.342,
|
| 913 |
+
"eval_steps_per_second": 6.106,
|
| 914 |
+
"step": 395
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 5.816696914700545,
|
| 918 |
+
"grad_norm": 0.8807503581047058,
|
| 919 |
+
"learning_rate": 1.9981033287370443e-05,
|
| 920 |
+
"loss": 1.0326,
|
| 921 |
+
"step": 400
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 5.816696914700545,
|
| 925 |
+
"eval_loss": 1.0372440814971924,
|
| 926 |
+
"eval_runtime": 14.7351,
|
| 927 |
+
"eval_samples_per_second": 193.415,
|
| 928 |
+
"eval_steps_per_second": 6.108,
|
| 929 |
+
"step": 400
|
| 930 |
+
}
|
| 931 |
+
],
|
| 932 |
+
"logging_steps": 10,
|
| 933 |
+
"max_steps": 3400,
|
| 934 |
+
"num_input_tokens_seen": 0,
|
| 935 |
+
"num_train_epochs": 50,
|
| 936 |
+
"save_steps": 100,
|
| 937 |
+
"stateful_callbacks": {
|
| 938 |
+
"TrainerControl": {
|
| 939 |
+
"args": {
|
| 940 |
+
"should_epoch_stop": false,
|
| 941 |
+
"should_evaluate": false,
|
| 942 |
+
"should_log": false,
|
| 943 |
+
"should_save": true,
|
| 944 |
+
"should_training_stop": false
|
| 945 |
+
},
|
| 946 |
+
"attributes": {}
|
| 947 |
+
}
|
| 948 |
+
},
|
| 949 |
+
"total_flos": 1.2418035506950963e+19,
|
| 950 |
+
"train_batch_size": 16,
|
| 951 |
+
"trial_name": null,
|
| 952 |
+
"trial_params": null
|
| 953 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1894455cc0a94db65550ffd96f92019abe4dc3f29968a527e44883b38a863afd
|
| 3 |
+
size 5368
|