added model files
Browse files- config.json +41 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer_config.json +33 -0
- trainer_state.json +360 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2-medium",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 1024,
|
| 16 |
+
"n_head": 16,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 24,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"n_special": 0,
|
| 21 |
+
"predict_special_tokens": true,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.28.1",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50257
|
| 41 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.28.1"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6a94ad80c6602d3b58bbb651c04bcfb3ca1f94b464bd74fdd96425640dff58c
|
| 3 |
+
size 2838757125
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1edb700c7c112bc2e8866e67c92bd3d96e50540aa7f0a8ec3762b7e39863d90
|
| 3 |
+
size 1444569373
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0629a344a0af580c9d0e14152034493c1dd3f68ca4011e1f869a5133c1217c2
|
| 3 |
+
size 14583
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f508e0bf1ad921526028851073ee4a3465ed6a8b94bd44113ba3bbaa45da987a
|
| 3 |
+
size 14583
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf451529454c4489838f5ee367584c95eacb778c628998599aa7e73728ab6109
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fbc2af22bc5e1ca15fa86d3fc2a73e2153588f1d741f472dba3e8a18dcaf271
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<PAD>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<|endoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "<|endoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"errors": "replace",
|
| 22 |
+
"model_max_length": 1024,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,360 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.954646181119811,
|
| 5 |
+
"global_step": 100000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 6.249924149859892e-05,
|
| 13 |
+
"loss": 2.9841,
|
| 14 |
+
"step": 2500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.07,
|
| 18 |
+
"eval_loss": 2.880531072616577,
|
| 19 |
+
"eval_runtime": 5041.8037,
|
| 20 |
+
"eval_samples_per_second": 11.934,
|
| 21 |
+
"eval_steps_per_second": 2.984,
|
| 22 |
+
"step": 2500
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.15,
|
| 26 |
+
"learning_rate": 6.249460454641857e-05,
|
| 27 |
+
"loss": 2.9159,
|
| 28 |
+
"step": 5000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.15,
|
| 32 |
+
"eval_loss": 2.843543291091919,
|
| 33 |
+
"eval_runtime": 5041.0801,
|
| 34 |
+
"eval_samples_per_second": 11.936,
|
| 35 |
+
"eval_steps_per_second": 2.984,
|
| 36 |
+
"step": 5000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.22,
|
| 40 |
+
"learning_rate": 6.248574782066793e-05,
|
| 41 |
+
"loss": 2.8874,
|
| 42 |
+
"step": 7500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.22,
|
| 46 |
+
"eval_loss": 2.8224122524261475,
|
| 47 |
+
"eval_runtime": 5041.8102,
|
| 48 |
+
"eval_samples_per_second": 11.934,
|
| 49 |
+
"eval_steps_per_second": 2.984,
|
| 50 |
+
"step": 7500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.3,
|
| 54 |
+
"learning_rate": 6.24726796015593e-05,
|
| 55 |
+
"loss": 2.867,
|
| 56 |
+
"step": 10000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.3,
|
| 60 |
+
"eval_loss": 2.805563449859619,
|
| 61 |
+
"eval_runtime": 5045.7151,
|
| 62 |
+
"eval_samples_per_second": 11.925,
|
| 63 |
+
"eval_steps_per_second": 2.981,
|
| 64 |
+
"step": 10000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.37,
|
| 68 |
+
"learning_rate": 6.245539895286441e-05,
|
| 69 |
+
"loss": 2.8462,
|
| 70 |
+
"step": 12500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.44,
|
| 74 |
+
"learning_rate": 6.243390820601403e-05,
|
| 75 |
+
"loss": 2.8343,
|
| 76 |
+
"step": 15000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.52,
|
| 80 |
+
"learning_rate": 6.240821026044725e-05,
|
| 81 |
+
"loss": 2.8232,
|
| 82 |
+
"step": 17500
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.59,
|
| 86 |
+
"learning_rate": 6.237830858322031e-05,
|
| 87 |
+
"loss": 2.8154,
|
| 88 |
+
"step": 20000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.59,
|
| 92 |
+
"eval_loss": 2.7630834579467773,
|
| 93 |
+
"eval_runtime": 5044.7761,
|
| 94 |
+
"eval_samples_per_second": 11.927,
|
| 95 |
+
"eval_steps_per_second": 2.982,
|
| 96 |
+
"step": 20000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.66,
|
| 100 |
+
"learning_rate": 6.234420720853886e-05,
|
| 101 |
+
"loss": 2.8085,
|
| 102 |
+
"step": 22500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.74,
|
| 106 |
+
"learning_rate": 6.230591073721361e-05,
|
| 107 |
+
"loss": 2.7959,
|
| 108 |
+
"step": 25000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.81,
|
| 112 |
+
"learning_rate": 6.22634243360397e-05,
|
| 113 |
+
"loss": 2.7934,
|
| 114 |
+
"step": 27500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.89,
|
| 118 |
+
"learning_rate": 6.221675373709958e-05,
|
| 119 |
+
"loss": 2.7856,
|
| 120 |
+
"step": 30000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.89,
|
| 124 |
+
"eval_loss": 2.7356297969818115,
|
| 125 |
+
"eval_runtime": 5045.7013,
|
| 126 |
+
"eval_samples_per_second": 11.925,
|
| 127 |
+
"eval_steps_per_second": 2.981,
|
| 128 |
+
"step": 30000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.96,
|
| 132 |
+
"learning_rate": 6.216590523698961e-05,
|
| 133 |
+
"loss": 2.7796,
|
| 134 |
+
"step": 32500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.03,
|
| 138 |
+
"learning_rate": 6.211090854583099e-05,
|
| 139 |
+
"loss": 2.7579,
|
| 140 |
+
"step": 35000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.11,
|
| 144 |
+
"learning_rate": 6.205172705145689e-05,
|
| 145 |
+
"loss": 2.7374,
|
| 146 |
+
"step": 37500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.18,
|
| 150 |
+
"learning_rate": 6.198836374494218e-05,
|
| 151 |
+
"loss": 2.7324,
|
| 152 |
+
"step": 40000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.18,
|
| 156 |
+
"eval_loss": 2.7184464931488037,
|
| 157 |
+
"eval_runtime": 5041.2928,
|
| 158 |
+
"eval_samples_per_second": 11.935,
|
| 159 |
+
"eval_steps_per_second": 2.984,
|
| 160 |
+
"step": 40000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.26,
|
| 164 |
+
"learning_rate": 6.192087786506709e-05,
|
| 165 |
+
"loss": 2.7345,
|
| 166 |
+
"step": 42500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.33,
|
| 170 |
+
"learning_rate": 6.18492540023217e-05,
|
| 171 |
+
"loss": 2.7306,
|
| 172 |
+
"step": 45000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.4,
|
| 176 |
+
"learning_rate": 6.177350181988941e-05,
|
| 177 |
+
"loss": 2.7291,
|
| 178 |
+
"step": 47500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.48,
|
| 182 |
+
"learning_rate": 6.169363153792874e-05,
|
| 183 |
+
"loss": 2.7255,
|
| 184 |
+
"step": 50000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.48,
|
| 188 |
+
"eval_loss": 2.7048535346984863,
|
| 189 |
+
"eval_runtime": 5061.5104,
|
| 190 |
+
"eval_samples_per_second": 11.888,
|
| 191 |
+
"eval_steps_per_second": 2.972,
|
| 192 |
+
"step": 50000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.55,
|
| 196 |
+
"learning_rate": 6.160961950708177e-05,
|
| 197 |
+
"loss": 2.725,
|
| 198 |
+
"step": 52500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.63,
|
| 202 |
+
"learning_rate": 6.152154427075951e-05,
|
| 203 |
+
"loss": 2.7212,
|
| 204 |
+
"step": 55000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.7,
|
| 208 |
+
"learning_rate": 6.142938492793726e-05,
|
| 209 |
+
"loss": 2.7196,
|
| 210 |
+
"step": 57500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.77,
|
| 214 |
+
"learning_rate": 6.133315391235702e-05,
|
| 215 |
+
"loss": 2.7169,
|
| 216 |
+
"step": 60000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.77,
|
| 220 |
+
"eval_loss": 2.6941745281219482,
|
| 221 |
+
"eval_runtime": 5046.2528,
|
| 222 |
+
"eval_samples_per_second": 11.924,
|
| 223 |
+
"eval_steps_per_second": 2.981,
|
| 224 |
+
"step": 60000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.85,
|
| 228 |
+
"learning_rate": 6.12328232645584e-05,
|
| 229 |
+
"loss": 2.7174,
|
| 230 |
+
"step": 62500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.92,
|
| 234 |
+
"learning_rate": 6.112848678433687e-05,
|
| 235 |
+
"loss": 2.7153,
|
| 236 |
+
"step": 65000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.99,
|
| 240 |
+
"learning_rate": 6.102011922724016e-05,
|
| 241 |
+
"loss": 2.7117,
|
| 242 |
+
"step": 67500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.07,
|
| 246 |
+
"learning_rate": 6.090778098663474e-05,
|
| 247 |
+
"loss": 2.6718,
|
| 248 |
+
"step": 70000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.07,
|
| 252 |
+
"eval_loss": 2.6850435733795166,
|
| 253 |
+
"eval_runtime": 5045.0709,
|
| 254 |
+
"eval_samples_per_second": 11.926,
|
| 255 |
+
"eval_steps_per_second": 2.982,
|
| 256 |
+
"step": 70000
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 2.14,
|
| 260 |
+
"learning_rate": 6.0791397277177804e-05,
|
| 261 |
+
"loss": 2.6687,
|
| 262 |
+
"step": 72500
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 2.22,
|
| 266 |
+
"learning_rate": 6.0671027969511556e-05,
|
| 267 |
+
"loss": 2.6724,
|
| 268 |
+
"step": 75000
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 2.29,
|
| 272 |
+
"learning_rate": 6.0546638755690396e-05,
|
| 273 |
+
"loss": 2.6703,
|
| 274 |
+
"step": 77500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.36,
|
| 278 |
+
"learning_rate": 6.041839805391616e-05,
|
| 279 |
+
"loss": 2.6717,
|
| 280 |
+
"step": 80000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 2.36,
|
| 284 |
+
"eval_loss": 2.67754864692688,
|
| 285 |
+
"eval_runtime": 5038.9811,
|
| 286 |
+
"eval_samples_per_second": 11.941,
|
| 287 |
+
"eval_steps_per_second": 2.985,
|
| 288 |
+
"step": 80000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.44,
|
| 292 |
+
"learning_rate": 6.028617152972819e-05,
|
| 293 |
+
"loss": 2.6733,
|
| 294 |
+
"step": 82500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.51,
|
| 298 |
+
"learning_rate": 6.0150027570214874e-05,
|
| 299 |
+
"loss": 2.6751,
|
| 300 |
+
"step": 85000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.59,
|
| 304 |
+
"learning_rate": 6.000998454333341e-05,
|
| 305 |
+
"loss": 2.6738,
|
| 306 |
+
"step": 87500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.66,
|
| 310 |
+
"learning_rate": 5.9866061343086405e-05,
|
| 311 |
+
"loss": 2.6747,
|
| 312 |
+
"step": 90000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.66,
|
| 316 |
+
"eval_loss": 2.6707887649536133,
|
| 317 |
+
"eval_runtime": 5038.9349,
|
| 318 |
+
"eval_samples_per_second": 11.941,
|
| 319 |
+
"eval_steps_per_second": 2.985,
|
| 320 |
+
"step": 90000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.73,
|
| 324 |
+
"learning_rate": 5.971821747960996e-05,
|
| 325 |
+
"loss": 2.676,
|
| 326 |
+
"step": 92500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.81,
|
| 330 |
+
"learning_rate": 5.9566591173123494e-05,
|
| 331 |
+
"loss": 2.6739,
|
| 332 |
+
"step": 95000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.88,
|
| 336 |
+
"learning_rate": 5.941120747883403e-05,
|
| 337 |
+
"loss": 2.6756,
|
| 338 |
+
"step": 97500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.95,
|
| 342 |
+
"learning_rate": 5.925196295535967e-05,
|
| 343 |
+
"loss": 2.6714,
|
| 344 |
+
"step": 100000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.95,
|
| 348 |
+
"eval_loss": 2.663831949234009,
|
| 349 |
+
"eval_runtime": 5038.524,
|
| 350 |
+
"eval_samples_per_second": 11.942,
|
| 351 |
+
"eval_steps_per_second": 2.986,
|
| 352 |
+
"step": 100000
|
| 353 |
+
}
|
| 354 |
+
],
|
| 355 |
+
"max_steps": 676900,
|
| 356 |
+
"num_train_epochs": 20,
|
| 357 |
+
"total_flos": 2.418000801633927e+18,
|
| 358 |
+
"trial_name": null,
|
| 359 |
+
"trial_params": null
|
| 360 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd3651258ed940af85171de2819bf72d874235015938629f5235440e64cf7354
|
| 3 |
+
size 3515
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|