Upload 19 files
Browse files- config.json +32 -0
- config.json~ +31 -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 +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +44 -0
- trainer_state.json +453 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"pad_token_id": 3,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_embd": 384,
|
| 15 |
+
"n_head": 12,
|
| 16 |
+
"n_inner": null,
|
| 17 |
+
"n_layer": 12,
|
| 18 |
+
"n_positions": 256,
|
| 19 |
+
"reorder_and_upcast_attn": false,
|
| 20 |
+
"resid_pdrop": 0.1,
|
| 21 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.43.4",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 12000
|
| 32 |
+
}
|
config.json~
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GPT2LMHeadModel"
|
| 5 |
+
],
|
| 6 |
+
"attn_pdrop": 0.1,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"embd_pdrop": 0.1,
|
| 9 |
+
"eos_token_id": 3,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"layer_norm_epsilon": 1e-05,
|
| 12 |
+
"model_type": "gpt2",
|
| 13 |
+
"n_embd": 384,
|
| 14 |
+
"n_head": 12,
|
| 15 |
+
"n_inner": null,
|
| 16 |
+
"n_layer": 12,
|
| 17 |
+
"n_positions": 256,
|
| 18 |
+
"reorder_and_upcast_attn": false,
|
| 19 |
+
"resid_pdrop": 0.1,
|
| 20 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 21 |
+
"scale_attn_weights": true,
|
| 22 |
+
"summary_activation": null,
|
| 23 |
+
"summary_first_dropout": 0.1,
|
| 24 |
+
"summary_proj_to_labels": true,
|
| 25 |
+
"summary_type": "cls_index",
|
| 26 |
+
"summary_use_proj": true,
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.43.4",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"vocab_size": 12000
|
| 31 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 2,
|
| 4 |
+
"eos_token_id": 3,
|
| 5 |
+
"transformers_version": "4.43.4"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:201a59ea15fbb02f5c2003d95182ee443989156c77cf930a68e756089b2f0164
|
| 3 |
+
size 104017304
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e93edcbdd8256e303a2860eb788d89b9d659880d2fe7d7fc14ba0e3edae998b
|
| 3 |
+
size 208128954
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7c9db256e3003ea20933b90ef1bad74da3b52f2616433941b0fce2e16d4039a
|
| 3 |
+
size 15984
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04c4166e30452e386379c4006f058de1d0f1dd955e9ac0dfb282612c8b37d4e7
|
| 3 |
+
size 15984
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a7bed564d79ad8007dafec767eab26ad408705c153454f17eee92d9b3434bbe
|
| 3 |
+
size 15984
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2fd7f2c8ea33814b15c0f28ebd486709c7a16eef83a538802bb2a17898371e1
|
| 3 |
+
size 15984
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a1fa058e97c8a955ff19079f1e05d4c30f71fa1432df132c0fa08b2529f5482
|
| 3 |
+
size 15984
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d82777a365c6f208df3ec5aa059a6a0d07254ce2509c580ca1448b78c5735a1
|
| 3 |
+
size 15984
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7cfe685ae4faa0f82e0840500fc28db06d0e3c7bfb13e2aefdb697576c4b4ba
|
| 3 |
+
size 15984
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb4f0146bd692165f8767a4adb5e77bb39c97aadd4b384c903164bc921b61472
|
| 3 |
+
size 15984
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6aa0d82f6dd8d5107cffa98be66f487e6e5d8761b8c6b88bcf0897d5d4751d6
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|bos|>",
|
| 3 |
+
"eos_token": "<|eos|>",
|
| 4 |
+
"mask_token": "<|mask|>",
|
| 5 |
+
"pad_token": "<|pad|>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<|mask|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|bos|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<|eos|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<|pad|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<|bos|>",
|
| 37 |
+
"clean_up_tokenization_spaces": true,
|
| 38 |
+
"eos_token": "<|eos|>",
|
| 39 |
+
"mask_token": "<|mask|>",
|
| 40 |
+
"model_max_length": 256,
|
| 41 |
+
"pad_token": "<|pad|>",
|
| 42 |
+
"return_tensors": "pt",
|
| 43 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 44 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,453 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.522384161312229,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 30000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.00870640268853715,
|
| 13 |
+
"grad_norm": 1.7332943677902222,
|
| 14 |
+
"learning_rate": 2.902083696093795e-06,
|
| 15 |
+
"loss": 8.5163,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.0174128053770743,
|
| 20 |
+
"grad_norm": 1.3953511714935303,
|
| 21 |
+
"learning_rate": 5.80416739218759e-06,
|
| 22 |
+
"loss": 7.5133,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.02611920806561145,
|
| 27 |
+
"grad_norm": 1.0311133861541748,
|
| 28 |
+
"learning_rate": 8.706251088281386e-06,
|
| 29 |
+
"loss": 6.6845,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.0348256107541486,
|
| 34 |
+
"grad_norm": 0.9061997532844543,
|
| 35 |
+
"learning_rate": 1.160833478437518e-05,
|
| 36 |
+
"loss": 6.0887,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04353201344268575,
|
| 41 |
+
"grad_norm": 1.1524709463119507,
|
| 42 |
+
"learning_rate": 1.4510418480468977e-05,
|
| 43 |
+
"loss": 5.6897,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0522384161312229,
|
| 48 |
+
"grad_norm": 1.559319019317627,
|
| 49 |
+
"learning_rate": 1.7412502176562773e-05,
|
| 50 |
+
"loss": 5.401,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06094481881976005,
|
| 55 |
+
"grad_norm": 1.388635516166687,
|
| 56 |
+
"learning_rate": 2.031458587265657e-05,
|
| 57 |
+
"loss": 5.1785,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0696512215082972,
|
| 62 |
+
"grad_norm": 1.545809030532837,
|
| 63 |
+
"learning_rate": 2.321666956875036e-05,
|
| 64 |
+
"loss": 4.9864,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.07835762419683436,
|
| 69 |
+
"grad_norm": 1.8368648290634155,
|
| 70 |
+
"learning_rate": 2.611875326484416e-05,
|
| 71 |
+
"loss": 4.8379,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0870640268853715,
|
| 76 |
+
"grad_norm": 1.6053112745285034,
|
| 77 |
+
"learning_rate": 2.9020836960937954e-05,
|
| 78 |
+
"loss": 4.6993,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.09577042957390865,
|
| 83 |
+
"grad_norm": 1.5248411893844604,
|
| 84 |
+
"learning_rate": 3.1922920657031755e-05,
|
| 85 |
+
"loss": 4.5834,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1044768322624458,
|
| 90 |
+
"grad_norm": 1.6166003942489624,
|
| 91 |
+
"learning_rate": 3.4825004353125546e-05,
|
| 92 |
+
"loss": 4.4827,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.11318323495098295,
|
| 97 |
+
"grad_norm": 1.7350354194641113,
|
| 98 |
+
"learning_rate": 3.772128388182715e-05,
|
| 99 |
+
"loss": 4.3958,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1218896376395201,
|
| 104 |
+
"grad_norm": 1.6347730159759521,
|
| 105 |
+
"learning_rate": 4.062336757792095e-05,
|
| 106 |
+
"loss": 4.3159,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.13059604032805724,
|
| 111 |
+
"grad_norm": 1.7262680530548096,
|
| 112 |
+
"learning_rate": 4.3525451274014746e-05,
|
| 113 |
+
"loss": 4.2414,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.1393024430165944,
|
| 118 |
+
"grad_norm": 1.6050870418548584,
|
| 119 |
+
"learning_rate": 4.642753497010854e-05,
|
| 120 |
+
"loss": 4.1787,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.14800884570513156,
|
| 125 |
+
"grad_norm": 1.6479125022888184,
|
| 126 |
+
"learning_rate": 4.9329618666202335e-05,
|
| 127 |
+
"loss": 4.1177,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.1567152483936687,
|
| 132 |
+
"grad_norm": 1.5750055313110352,
|
| 133 |
+
"learning_rate": 5.222589819490395e-05,
|
| 134 |
+
"loss": 4.0634,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.16542165108220586,
|
| 139 |
+
"grad_norm": 1.5032442808151245,
|
| 140 |
+
"learning_rate": 5.512798189099774e-05,
|
| 141 |
+
"loss": 4.007,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.174128053770743,
|
| 146 |
+
"grad_norm": 1.47872793674469,
|
| 147 |
+
"learning_rate": 5.803006558709153e-05,
|
| 148 |
+
"loss": 3.9545,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.18283445645928015,
|
| 153 |
+
"grad_norm": 1.5958372354507446,
|
| 154 |
+
"learning_rate": 6.0932149283185326e-05,
|
| 155 |
+
"loss": 3.9063,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.1915408591478173,
|
| 160 |
+
"grad_norm": 1.4950892925262451,
|
| 161 |
+
"learning_rate": 6.383423297927912e-05,
|
| 162 |
+
"loss": 3.8569,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.20024726183635447,
|
| 167 |
+
"grad_norm": 1.4393689632415771,
|
| 168 |
+
"learning_rate": 6.673631667537293e-05,
|
| 169 |
+
"loss": 3.8082,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2089536645248916,
|
| 174 |
+
"grad_norm": 1.5717238187789917,
|
| 175 |
+
"learning_rate": 6.963840037146672e-05,
|
| 176 |
+
"loss": 3.767,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.21766006721342876,
|
| 181 |
+
"grad_norm": 1.4899908304214478,
|
| 182 |
+
"learning_rate": 7.254048406756051e-05,
|
| 183 |
+
"loss": 3.7333,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2263664699019659,
|
| 188 |
+
"grad_norm": 1.3972300291061401,
|
| 189 |
+
"learning_rate": 7.543676359626212e-05,
|
| 190 |
+
"loss": 3.6949,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.23507287259050305,
|
| 195 |
+
"grad_norm": 1.4396140575408936,
|
| 196 |
+
"learning_rate": 7.833884729235591e-05,
|
| 197 |
+
"loss": 3.6678,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.2437792752790402,
|
| 202 |
+
"grad_norm": 1.2989853620529175,
|
| 203 |
+
"learning_rate": 8.124093098844972e-05,
|
| 204 |
+
"loss": 3.6383,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.25248567796757737,
|
| 209 |
+
"grad_norm": 1.2884502410888672,
|
| 210 |
+
"learning_rate": 8.414301468454351e-05,
|
| 211 |
+
"loss": 3.6071,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.2611920806561145,
|
| 216 |
+
"grad_norm": 1.2769827842712402,
|
| 217 |
+
"learning_rate": 8.703929421324512e-05,
|
| 218 |
+
"loss": 3.5782,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.26989848334465166,
|
| 223 |
+
"grad_norm": 1.2089248895645142,
|
| 224 |
+
"learning_rate": 8.994137790933891e-05,
|
| 225 |
+
"loss": 3.5591,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.2786048860331888,
|
| 230 |
+
"grad_norm": 1.2605466842651367,
|
| 231 |
+
"learning_rate": 9.28434616054327e-05,
|
| 232 |
+
"loss": 3.5359,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.28731128872172595,
|
| 237 |
+
"grad_norm": 1.1653631925582886,
|
| 238 |
+
"learning_rate": 9.57455453015265e-05,
|
| 239 |
+
"loss": 3.5103,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.29601769141026313,
|
| 244 |
+
"grad_norm": 1.1932523250579834,
|
| 245 |
+
"learning_rate": 9.864182483022812e-05,
|
| 246 |
+
"loss": 3.491,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.30472409409880025,
|
| 251 |
+
"grad_norm": 1.115700125694275,
|
| 252 |
+
"learning_rate": 9.998919722621363e-05,
|
| 253 |
+
"loss": 3.4716,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.3134304967873374,
|
| 258 |
+
"grad_norm": 1.0842598676681519,
|
| 259 |
+
"learning_rate": 9.99104397096728e-05,
|
| 260 |
+
"loss": 3.4554,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.32213689947587454,
|
| 265 |
+
"grad_norm": 1.114572525024414,
|
| 266 |
+
"learning_rate": 9.975548766466318e-05,
|
| 267 |
+
"loss": 3.4367,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.3308433021644117,
|
| 272 |
+
"grad_norm": 1.0411341190338135,
|
| 273 |
+
"learning_rate": 9.952511505591483e-05,
|
| 274 |
+
"loss": 3.418,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.3395497048529489,
|
| 279 |
+
"grad_norm": 1.0207189321517944,
|
| 280 |
+
"learning_rate": 9.921875035663696e-05,
|
| 281 |
+
"loss": 3.4066,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.348256107541486,
|
| 286 |
+
"grad_norm": 1.0282100439071655,
|
| 287 |
+
"learning_rate": 9.883724707919666e-05,
|
| 288 |
+
"loss": 3.3898,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3569625102300232,
|
| 293 |
+
"grad_norm": 1.0247931480407715,
|
| 294 |
+
"learning_rate": 9.838118763606121e-05,
|
| 295 |
+
"loss": 3.3797,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3656689129185603,
|
| 300 |
+
"grad_norm": 0.9947717785835266,
|
| 301 |
+
"learning_rate": 9.785240129092532e-05,
|
| 302 |
+
"loss": 3.3638,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.37437531560709747,
|
| 307 |
+
"grad_norm": 0.9564889073371887,
|
| 308 |
+
"learning_rate": 9.724957618833668e-05,
|
| 309 |
+
"loss": 3.3489,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.3830817182956346,
|
| 314 |
+
"grad_norm": 0.9665967226028442,
|
| 315 |
+
"learning_rate": 9.65746186982363e-05,
|
| 316 |
+
"loss": 3.3382,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.39178812098417176,
|
| 321 |
+
"grad_norm": 0.9586713314056396,
|
| 322 |
+
"learning_rate": 9.582855922764911e-05,
|
| 323 |
+
"loss": 3.3239,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.40049452367270894,
|
| 328 |
+
"grad_norm": 0.9278811812400818,
|
| 329 |
+
"learning_rate": 9.501423778734501e-05,
|
| 330 |
+
"loss": 3.315,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.40920092636124605,
|
| 335 |
+
"grad_norm": 0.8986345529556274,
|
| 336 |
+
"learning_rate": 9.41296341435732e-05,
|
| 337 |
+
"loss": 3.3005,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.4179073290497832,
|
| 342 |
+
"grad_norm": 0.8818135261535645,
|
| 343 |
+
"learning_rate": 9.317766109402922e-05,
|
| 344 |
+
"loss": 3.2957,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.42661373173832035,
|
| 349 |
+
"grad_norm": 0.9282686710357666,
|
| 350 |
+
"learning_rate": 9.215977194463557e-05,
|
| 351 |
+
"loss": 3.2868,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.4353201344268575,
|
| 356 |
+
"grad_norm": 0.88565993309021,
|
| 357 |
+
"learning_rate": 9.107974828450761e-05,
|
| 358 |
+
"loss": 3.2755,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.44402653711539464,
|
| 363 |
+
"grad_norm": 0.9184048771858215,
|
| 364 |
+
"learning_rate": 8.993491070457932e-05,
|
| 365 |
+
"loss": 3.269,
|
| 366 |
+
"step": 25500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.4527329398039318,
|
| 370 |
+
"grad_norm": 0.9061756134033203,
|
| 371 |
+
"learning_rate": 8.872910748883857e-05,
|
| 372 |
+
"loss": 3.2582,
|
| 373 |
+
"step": 26000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.461439342492469,
|
| 377 |
+
"grad_norm": 0.9069876670837402,
|
| 378 |
+
"learning_rate": 8.746417944670291e-05,
|
| 379 |
+
"loss": 3.2544,
|
| 380 |
+
"step": 26500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.4701457451810061,
|
| 384 |
+
"grad_norm": 0.900641143321991,
|
| 385 |
+
"learning_rate": 8.614475764467431e-05,
|
| 386 |
+
"loss": 3.2427,
|
| 387 |
+
"step": 27000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.4788521478695433,
|
| 391 |
+
"grad_norm": 0.8898523449897766,
|
| 392 |
+
"learning_rate": 8.476756875563143e-05,
|
| 393 |
+
"loss": 3.235,
|
| 394 |
+
"step": 27500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.4875585505580804,
|
| 398 |
+
"grad_norm": 0.9023728370666504,
|
| 399 |
+
"learning_rate": 8.333730282453582e-05,
|
| 400 |
+
"loss": 3.2254,
|
| 401 |
+
"step": 28000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.49626495324661757,
|
| 405 |
+
"grad_norm": 0.8760348558425903,
|
| 406 |
+
"learning_rate": 8.185614333121332e-05,
|
| 407 |
+
"loss": 3.2175,
|
| 408 |
+
"step": 28500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.5049713559351547,
|
| 412 |
+
"grad_norm": 0.8970732092857361,
|
| 413 |
+
"learning_rate": 8.032945802949179e-05,
|
| 414 |
+
"loss": 3.2159,
|
| 415 |
+
"step": 29000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5136777586236919,
|
| 419 |
+
"grad_norm": 0.8672531843185425,
|
| 420 |
+
"learning_rate": 7.875345939638492e-05,
|
| 421 |
+
"loss": 3.2051,
|
| 422 |
+
"step": 29500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.522384161312229,
|
| 426 |
+
"grad_norm": 0.896369457244873,
|
| 427 |
+
"learning_rate": 7.713356501134123e-05,
|
| 428 |
+
"loss": 3.2038,
|
| 429 |
+
"step": 30000
|
| 430 |
+
}
|
| 431 |
+
],
|
| 432 |
+
"logging_steps": 500,
|
| 433 |
+
"max_steps": 57429,
|
| 434 |
+
"num_input_tokens_seen": 0,
|
| 435 |
+
"num_train_epochs": 1,
|
| 436 |
+
"save_steps": 1000,
|
| 437 |
+
"stateful_callbacks": {
|
| 438 |
+
"TrainerControl": {
|
| 439 |
+
"args": {
|
| 440 |
+
"should_epoch_stop": false,
|
| 441 |
+
"should_evaluate": false,
|
| 442 |
+
"should_log": false,
|
| 443 |
+
"should_save": true,
|
| 444 |
+
"should_training_stop": false
|
| 445 |
+
},
|
| 446 |
+
"attributes": {}
|
| 447 |
+
}
|
| 448 |
+
},
|
| 449 |
+
"total_flos": 1.2559910839517184e+17,
|
| 450 |
+
"train_batch_size": 16,
|
| 451 |
+
"trial_name": null,
|
| 452 |
+
"trial_params": null
|
| 453 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f75b3beb08e8c4bc8bc0b8de08ca42d7841ab19fc5773b20778f86041657efa9
|
| 3 |
+
size 5240
|