Upload 18 files
Browse files- config.json +32 -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 +383 -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 |
+
}
|
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 sha256:27744bbfdbd868d602c7b479a53490c7b410aab6ab95d5e13e6ccfd668418e16
|
| 3 |
+
size 104017304
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19155e35c496234b5757948b895eeefba4fcbfa1e8898ac7c584bca99b4f7e3f
|
| 3 |
+
size 208128954
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf8d9c5472b79847e35f2add7c83c998c4e8f9cc29ab72294c622299dd6d54e
|
| 3 |
+
size 15984
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f464bf594804694d4c5530848ece8e6243b737a39f871f543a03495d32ea1bf2
|
| 3 |
+
size 15984
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22822e4fb460f40d770000b8eec670ec8c2dd935c79693ec04f2891afe6138d3
|
| 3 |
+
size 15984
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc74179b4e5675fe0badde0555f0a0f4123e3afe9eb0a8ae17d249207f388d9f
|
| 3 |
+
size 15984
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f86353e8dcc45aec3150110e4bbc52f6658710986e489e87b1a891035cb371b6
|
| 3 |
+
size 15984
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14e370f0f9f939978afdebdeb3f057722d56b06446727acf2f9816ccfd8eb532
|
| 3 |
+
size 15984
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cf3a5a3a5f320a5c4d392bc2e3c530334e2f4e7ca0f8014f3e6d56ed97e4c31
|
| 3 |
+
size 15984
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0353725ef372ee1bbc86a8abd04aed4dfaf8ea7595d31d3c0ee84a633b48dee
|
| 3 |
+
size 15984
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef4c77b02856a25aaaff42c9517b32d4731cc9302ea0d2b474e28d2ea8366a7
|
| 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 +1,383 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 49.9001996007984,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 25000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.998003992015968,
|
| 13 |
+
"grad_norm": 1.8999210596084595,
|
| 14 |
+
"learning_rate": 3.32667997338656e-06,
|
| 15 |
+
"loss": 8.3804,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.996007984031936,
|
| 20 |
+
"grad_norm": 2.889465093612671,
|
| 21 |
+
"learning_rate": 6.65335994677312e-06,
|
| 22 |
+
"loss": 7.2559,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.9940119760479043,
|
| 27 |
+
"grad_norm": 1.4177864789962769,
|
| 28 |
+
"learning_rate": 9.980039920159681e-06,
|
| 29 |
+
"loss": 6.3336,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 3.992015968063872,
|
| 34 |
+
"grad_norm": 1.6604845523834229,
|
| 35 |
+
"learning_rate": 1.330671989354624e-05,
|
| 36 |
+
"loss": 5.7018,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 4.99001996007984,
|
| 41 |
+
"grad_norm": 1.785506248474121,
|
| 42 |
+
"learning_rate": 1.6633399866932804e-05,
|
| 43 |
+
"loss": 5.3092,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 5.9880239520958085,
|
| 48 |
+
"grad_norm": 1.665967583656311,
|
| 49 |
+
"learning_rate": 1.9960079840319362e-05,
|
| 50 |
+
"loss": 5.0451,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.986027944111776,
|
| 55 |
+
"grad_norm": 2.023294687271118,
|
| 56 |
+
"learning_rate": 2.328675981370592e-05,
|
| 57 |
+
"loss": 4.84,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 7.984031936127744,
|
| 62 |
+
"grad_norm": 2.2120347023010254,
|
| 63 |
+
"learning_rate": 2.661343978709248e-05,
|
| 64 |
+
"loss": 4.6636,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 8.982035928143713,
|
| 69 |
+
"grad_norm": 2.0134084224700928,
|
| 70 |
+
"learning_rate": 2.994011976047904e-05,
|
| 71 |
+
"loss": 4.517,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 9.980039920159681,
|
| 76 |
+
"grad_norm": 1.9846144914627075,
|
| 77 |
+
"learning_rate": 3.326679973386561e-05,
|
| 78 |
+
"loss": 4.3934,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 10.978043912175648,
|
| 83 |
+
"grad_norm": 2.0299410820007324,
|
| 84 |
+
"learning_rate": 3.6593479707252166e-05,
|
| 85 |
+
"loss": 4.2831,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 11.976047904191617,
|
| 90 |
+
"grad_norm": 1.7351747751235962,
|
| 91 |
+
"learning_rate": 3.9920159680638724e-05,
|
| 92 |
+
"loss": 4.1891,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 12.974051896207584,
|
| 97 |
+
"grad_norm": 1.829405665397644,
|
| 98 |
+
"learning_rate": 4.324018629407851e-05,
|
| 99 |
+
"loss": 4.0984,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 13.972055888223553,
|
| 104 |
+
"grad_norm": 1.727301836013794,
|
| 105 |
+
"learning_rate": 4.656686626746507e-05,
|
| 106 |
+
"loss": 4.0139,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 14.970059880239521,
|
| 111 |
+
"grad_norm": 1.7156864404678345,
|
| 112 |
+
"learning_rate": 4.9893546240851635e-05,
|
| 113 |
+
"loss": 3.938,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 15.968063872255488,
|
| 118 |
+
"grad_norm": 1.5628697872161865,
|
| 119 |
+
"learning_rate": 5.322022621423819e-05,
|
| 120 |
+
"loss": 3.8623,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 16.96606786427146,
|
| 125 |
+
"grad_norm": 1.6095757484436035,
|
| 126 |
+
"learning_rate": 5.6540252827677973e-05,
|
| 127 |
+
"loss": 3.7939,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 17.964071856287426,
|
| 132 |
+
"grad_norm": 1.695480465888977,
|
| 133 |
+
"learning_rate": 5.9866932801064546e-05,
|
| 134 |
+
"loss": 3.7259,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 18.962075848303392,
|
| 139 |
+
"grad_norm": 1.6396301984786987,
|
| 140 |
+
"learning_rate": 6.319361277445111e-05,
|
| 141 |
+
"loss": 3.6648,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 19.960079840319363,
|
| 146 |
+
"grad_norm": 1.6488186120986938,
|
| 147 |
+
"learning_rate": 6.652029274783767e-05,
|
| 148 |
+
"loss": 3.6029,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 20.95808383233533,
|
| 153 |
+
"grad_norm": 1.7244266271591187,
|
| 154 |
+
"learning_rate": 6.984031936127745e-05,
|
| 155 |
+
"loss": 3.5493,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 21.956087824351297,
|
| 160 |
+
"grad_norm": 1.5352064371109009,
|
| 161 |
+
"learning_rate": 7.316699933466401e-05,
|
| 162 |
+
"loss": 3.4955,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 22.954091816367267,
|
| 167 |
+
"grad_norm": 1.5730326175689697,
|
| 168 |
+
"learning_rate": 7.649367930805057e-05,
|
| 169 |
+
"loss": 3.4487,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 23.952095808383234,
|
| 174 |
+
"grad_norm": 1.5208061933517456,
|
| 175 |
+
"learning_rate": 7.982035928143713e-05,
|
| 176 |
+
"loss": 3.4063,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 24.9500998003992,
|
| 181 |
+
"grad_norm": 1.4076310396194458,
|
| 182 |
+
"learning_rate": 8.314703925482368e-05,
|
| 183 |
+
"loss": 3.3677,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 25.948103792415168,
|
| 188 |
+
"grad_norm": 1.5883309841156006,
|
| 189 |
+
"learning_rate": 8.646706586826348e-05,
|
| 190 |
+
"loss": 3.3283,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 26.94610778443114,
|
| 195 |
+
"grad_norm": 1.5784621238708496,
|
| 196 |
+
"learning_rate": 8.979374584165004e-05,
|
| 197 |
+
"loss": 3.2934,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 27.944111776447105,
|
| 202 |
+
"grad_norm": 1.432620882987976,
|
| 203 |
+
"learning_rate": 9.31204258150366e-05,
|
| 204 |
+
"loss": 3.261,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 28.942115768463076,
|
| 209 |
+
"grad_norm": 1.3958067893981934,
|
| 210 |
+
"learning_rate": 9.644710578842315e-05,
|
| 211 |
+
"loss": 3.23,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 29.940119760479043,
|
| 216 |
+
"grad_norm": 1.3833889961242676,
|
| 217 |
+
"learning_rate": 9.977378576180973e-05,
|
| 218 |
+
"loss": 3.2001,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 30.93812375249501,
|
| 223 |
+
"grad_norm": 1.3629279136657715,
|
| 224 |
+
"learning_rate": 9.995644109160385e-05,
|
| 225 |
+
"loss": 3.1728,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 31.936127744510976,
|
| 230 |
+
"grad_norm": 1.4202319383621216,
|
| 231 |
+
"learning_rate": 9.981290962387998e-05,
|
| 232 |
+
"loss": 3.1431,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 32.93413173652694,
|
| 237 |
+
"grad_norm": 1.3846460580825806,
|
| 238 |
+
"learning_rate": 9.956946158420721e-05,
|
| 239 |
+
"loss": 3.1126,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 33.93213572854292,
|
| 244 |
+
"grad_norm": 1.3388583660125732,
|
| 245 |
+
"learning_rate": 9.92273698475866e-05,
|
| 246 |
+
"loss": 3.0906,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 34.930139720558884,
|
| 251 |
+
"grad_norm": 1.2869479656219482,
|
| 252 |
+
"learning_rate": 9.878594971476942e-05,
|
| 253 |
+
"loss": 3.0625,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 35.92814371257485,
|
| 258 |
+
"grad_norm": 1.3220205307006836,
|
| 259 |
+
"learning_rate": 9.824667292407827e-05,
|
| 260 |
+
"loss": 3.0418,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 36.92614770459082,
|
| 265 |
+
"grad_norm": 1.2586220502853394,
|
| 266 |
+
"learning_rate": 9.761062117679632e-05,
|
| 267 |
+
"loss": 3.0155,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 37.924151696606785,
|
| 272 |
+
"grad_norm": 1.3261734247207642,
|
| 273 |
+
"learning_rate": 9.688062775520065e-05,
|
| 274 |
+
"loss": 2.9964,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 38.92215568862275,
|
| 279 |
+
"grad_norm": 1.2898756265640259,
|
| 280 |
+
"learning_rate": 9.605523157182904e-05,
|
| 281 |
+
"loss": 2.9767,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 39.920159680638726,
|
| 286 |
+
"grad_norm": 1.3585063219070435,
|
| 287 |
+
"learning_rate": 9.513745610578322e-05,
|
| 288 |
+
"loss": 2.9549,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 40.91816367265469,
|
| 293 |
+
"grad_norm": 1.3588775396347046,
|
| 294 |
+
"learning_rate": 9.412914226495388e-05,
|
| 295 |
+
"loss": 2.9349,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 41.91616766467066,
|
| 300 |
+
"grad_norm": 1.2472021579742432,
|
| 301 |
+
"learning_rate": 9.303459312750163e-05,
|
| 302 |
+
"loss": 2.92,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 42.91417165668663,
|
| 307 |
+
"grad_norm": 1.3725252151489258,
|
| 308 |
+
"learning_rate": 9.185161794488783e-05,
|
| 309 |
+
"loss": 2.8977,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 43.91217564870259,
|
| 314 |
+
"grad_norm": 1.2629554271697998,
|
| 315 |
+
"learning_rate": 9.058469524290322e-05,
|
| 316 |
+
"loss": 2.8861,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 44.91017964071856,
|
| 321 |
+
"grad_norm": 1.318297266960144,
|
| 322 |
+
"learning_rate": 8.923636626184598e-05,
|
| 323 |
+
"loss": 2.8661,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 45.908183632734534,
|
| 328 |
+
"grad_norm": 1.2896426916122437,
|
| 329 |
+
"learning_rate": 8.781226625872564e-05,
|
| 330 |
+
"loss": 2.8498,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 46.9061876247505,
|
| 335 |
+
"grad_norm": 1.3040919303894043,
|
| 336 |
+
"learning_rate": 8.630954488640488e-05,
|
| 337 |
+
"loss": 2.8351,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 47.90419161676647,
|
| 342 |
+
"grad_norm": 1.3538358211517334,
|
| 343 |
+
"learning_rate": 8.473399248932634e-05,
|
| 344 |
+
"loss": 2.8199,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 48.902195608782435,
|
| 349 |
+
"grad_norm": 1.3103379011154175,
|
| 350 |
+
"learning_rate": 8.308876936861739e-05,
|
| 351 |
+
"loss": 2.8043,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 49.9001996007984,
|
| 356 |
+
"grad_norm": 1.3381751775741577,
|
| 357 |
+
"learning_rate": 8.138066273860004e-05,
|
| 358 |
+
"loss": 2.7906,
|
| 359 |
+
"step": 25000
|
| 360 |
+
}
|
| 361 |
+
],
|
| 362 |
+
"logging_steps": 500,
|
| 363 |
+
"max_steps": 50100,
|
| 364 |
+
"num_input_tokens_seen": 0,
|
| 365 |
+
"num_train_epochs": 100,
|
| 366 |
+
"save_steps": 1000,
|
| 367 |
+
"stateful_callbacks": {
|
| 368 |
+
"TrainerControl": {
|
| 369 |
+
"args": {
|
| 370 |
+
"should_epoch_stop": false,
|
| 371 |
+
"should_evaluate": false,
|
| 372 |
+
"should_log": false,
|
| 373 |
+
"should_save": true,
|
| 374 |
+
"should_training_stop": false
|
| 375 |
+
},
|
| 376 |
+
"attributes": {}
|
| 377 |
+
}
|
| 378 |
+
},
|
| 379 |
+
"total_flos": 1.046659236626432e+17,
|
| 380 |
+
"train_batch_size": 16,
|
| 381 |
+
"trial_name": null,
|
| 382 |
+
"trial_params": null
|
| 383 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c45179548c2e06755e4e71c3cb8be8bd0aa5d70f31c9c57b7e48db4b1de79f21
|
| 3 |
+
size 5240
|