commit from chengluli
Browse files- config.json +38 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +772 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2-xl",
|
| 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": 1600,
|
| 16 |
+
"n_head": 25,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 48,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"output_past": true,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 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 |
+
"task_specific_params": {
|
| 29 |
+
"text-generation": {
|
| 30 |
+
"do_sample": true,
|
| 31 |
+
"max_length": 50
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.11.3",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50273
|
| 38 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2486793472f93e289bdb358059e38bee43b221a983c5aecfb6bfa458ab0d3aec
|
| 3 |
+
size 6281126861
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d18c23beb6dc4e2eddcb2cf8ed400d1268149042f09b8a10a01eed9b414d804
|
| 3 |
+
size 21579
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c79e9f262ed0008cce6545b967cc9ae05077328ca9280fd28aa2cc9913ebf0e7
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,772 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.921671018276763,
|
| 5 |
+
"global_step": 57000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 1.9825935596170586e-05,
|
| 13 |
+
"loss": 2.4238,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 1.9651871192341167e-05,
|
| 19 |
+
"loss": 2.1067,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.26,
|
| 24 |
+
"learning_rate": 1.947780678851175e-05,
|
| 25 |
+
"loss": 1.9034,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.35,
|
| 30 |
+
"learning_rate": 1.9303742384682335e-05,
|
| 31 |
+
"loss": 1.8061,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.44,
|
| 36 |
+
"learning_rate": 1.9129677980852916e-05,
|
| 37 |
+
"loss": 1.7317,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.52,
|
| 42 |
+
"learning_rate": 1.89556135770235e-05,
|
| 43 |
+
"loss": 1.6795,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.61,
|
| 48 |
+
"learning_rate": 1.8781549173194084e-05,
|
| 49 |
+
"loss": 1.6346,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.7,
|
| 54 |
+
"learning_rate": 1.8607484769364665e-05,
|
| 55 |
+
"loss": 1.5838,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.78,
|
| 60 |
+
"learning_rate": 1.843342036553525e-05,
|
| 61 |
+
"loss": 1.5477,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.87,
|
| 66 |
+
"learning_rate": 1.8259355961705833e-05,
|
| 67 |
+
"loss": 1.5084,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.96,
|
| 72 |
+
"learning_rate": 1.8085291557876417e-05,
|
| 73 |
+
"loss": 1.4765,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.0,
|
| 78 |
+
"eval_loss": 1.2889001369476318,
|
| 79 |
+
"eval_runtime": 523.3258,
|
| 80 |
+
"eval_samples_per_second": 126.487,
|
| 81 |
+
"eval_steps_per_second": 1.978,
|
| 82 |
+
"step": 5745
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1.04,
|
| 86 |
+
"learning_rate": 1.7911227154046998e-05,
|
| 87 |
+
"loss": 1.4277,
|
| 88 |
+
"step": 6000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 1.13,
|
| 92 |
+
"learning_rate": 1.7737162750217582e-05,
|
| 93 |
+
"loss": 1.3842,
|
| 94 |
+
"step": 6500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.22,
|
| 98 |
+
"learning_rate": 1.7563098346388167e-05,
|
| 99 |
+
"loss": 1.3659,
|
| 100 |
+
"step": 7000
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.31,
|
| 104 |
+
"learning_rate": 1.7389033942558747e-05,
|
| 105 |
+
"loss": 1.346,
|
| 106 |
+
"step": 7500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.39,
|
| 110 |
+
"learning_rate": 1.721496953872933e-05,
|
| 111 |
+
"loss": 1.3252,
|
| 112 |
+
"step": 8000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.48,
|
| 116 |
+
"learning_rate": 1.7040905134899916e-05,
|
| 117 |
+
"loss": 1.3148,
|
| 118 |
+
"step": 8500
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.57,
|
| 122 |
+
"learning_rate": 1.6866840731070497e-05,
|
| 123 |
+
"loss": 1.3071,
|
| 124 |
+
"step": 9000
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.65,
|
| 128 |
+
"learning_rate": 1.669277632724108e-05,
|
| 129 |
+
"loss": 1.287,
|
| 130 |
+
"step": 9500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.74,
|
| 134 |
+
"learning_rate": 1.6518711923411665e-05,
|
| 135 |
+
"loss": 1.2802,
|
| 136 |
+
"step": 10000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.83,
|
| 140 |
+
"learning_rate": 1.6344647519582246e-05,
|
| 141 |
+
"loss": 1.2637,
|
| 142 |
+
"step": 10500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.91,
|
| 146 |
+
"learning_rate": 1.617058311575283e-05,
|
| 147 |
+
"loss": 1.2451,
|
| 148 |
+
"step": 11000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.0,
|
| 152 |
+
"eval_loss": 1.1364690065383911,
|
| 153 |
+
"eval_runtime": 527.405,
|
| 154 |
+
"eval_samples_per_second": 125.509,
|
| 155 |
+
"eval_steps_per_second": 1.962,
|
| 156 |
+
"step": 11490
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.0,
|
| 160 |
+
"learning_rate": 1.599651871192341e-05,
|
| 161 |
+
"loss": 1.2384,
|
| 162 |
+
"step": 11500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.09,
|
| 166 |
+
"learning_rate": 1.5822454308093995e-05,
|
| 167 |
+
"loss": 1.1927,
|
| 168 |
+
"step": 12000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.18,
|
| 172 |
+
"learning_rate": 1.564838990426458e-05,
|
| 173 |
+
"loss": 1.1753,
|
| 174 |
+
"step": 12500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 2.26,
|
| 178 |
+
"learning_rate": 1.5474325500435163e-05,
|
| 179 |
+
"loss": 1.1781,
|
| 180 |
+
"step": 13000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 2.35,
|
| 184 |
+
"learning_rate": 1.5300261096605747e-05,
|
| 185 |
+
"loss": 1.1705,
|
| 186 |
+
"step": 13500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.44,
|
| 190 |
+
"learning_rate": 1.512619669277633e-05,
|
| 191 |
+
"loss": 1.1653,
|
| 192 |
+
"step": 14000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.52,
|
| 196 |
+
"learning_rate": 1.4952132288946912e-05,
|
| 197 |
+
"loss": 1.1541,
|
| 198 |
+
"step": 14500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.61,
|
| 202 |
+
"learning_rate": 1.4778067885117495e-05,
|
| 203 |
+
"loss": 1.1485,
|
| 204 |
+
"step": 15000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.7,
|
| 208 |
+
"learning_rate": 1.4604003481288079e-05,
|
| 209 |
+
"loss": 1.1479,
|
| 210 |
+
"step": 15500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 2.79,
|
| 214 |
+
"learning_rate": 1.4429939077458661e-05,
|
| 215 |
+
"loss": 1.1399,
|
| 216 |
+
"step": 16000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.87,
|
| 220 |
+
"learning_rate": 1.4255874673629244e-05,
|
| 221 |
+
"loss": 1.1355,
|
| 222 |
+
"step": 16500
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.96,
|
| 226 |
+
"learning_rate": 1.4081810269799826e-05,
|
| 227 |
+
"loss": 1.1291,
|
| 228 |
+
"step": 17000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.0,
|
| 232 |
+
"eval_loss": 1.0703651905059814,
|
| 233 |
+
"eval_runtime": 523.7516,
|
| 234 |
+
"eval_samples_per_second": 126.384,
|
| 235 |
+
"eval_steps_per_second": 1.976,
|
| 236 |
+
"step": 17235
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.05,
|
| 240 |
+
"learning_rate": 1.390774586597041e-05,
|
| 241 |
+
"loss": 1.1075,
|
| 242 |
+
"step": 17500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.13,
|
| 246 |
+
"learning_rate": 1.3733681462140993e-05,
|
| 247 |
+
"loss": 1.0931,
|
| 248 |
+
"step": 18000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.22,
|
| 252 |
+
"learning_rate": 1.3559617058311576e-05,
|
| 253 |
+
"loss": 1.0864,
|
| 254 |
+
"step": 18500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.31,
|
| 258 |
+
"learning_rate": 1.338555265448216e-05,
|
| 259 |
+
"loss": 1.0822,
|
| 260 |
+
"step": 19000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.39,
|
| 264 |
+
"learning_rate": 1.3211488250652742e-05,
|
| 265 |
+
"loss": 1.0847,
|
| 266 |
+
"step": 19500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.48,
|
| 270 |
+
"learning_rate": 1.3037423846823325e-05,
|
| 271 |
+
"loss": 1.0795,
|
| 272 |
+
"step": 20000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.57,
|
| 276 |
+
"learning_rate": 1.2863359442993907e-05,
|
| 277 |
+
"loss": 1.0704,
|
| 278 |
+
"step": 20500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.66,
|
| 282 |
+
"learning_rate": 1.2689295039164491e-05,
|
| 283 |
+
"loss": 1.072,
|
| 284 |
+
"step": 21000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 3.74,
|
| 288 |
+
"learning_rate": 1.2515230635335076e-05,
|
| 289 |
+
"loss": 1.0704,
|
| 290 |
+
"step": 21500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.83,
|
| 294 |
+
"learning_rate": 1.234116623150566e-05,
|
| 295 |
+
"loss": 1.0623,
|
| 296 |
+
"step": 22000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 3.92,
|
| 300 |
+
"learning_rate": 1.2167101827676242e-05,
|
| 301 |
+
"loss": 1.0657,
|
| 302 |
+
"step": 22500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.0,
|
| 306 |
+
"eval_loss": 1.0373072624206543,
|
| 307 |
+
"eval_runtime": 524.067,
|
| 308 |
+
"eval_samples_per_second": 126.308,
|
| 309 |
+
"eval_steps_per_second": 1.975,
|
| 310 |
+
"step": 22980
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.0,
|
| 314 |
+
"learning_rate": 1.1993037423846825e-05,
|
| 315 |
+
"loss": 1.0612,
|
| 316 |
+
"step": 23000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 4.09,
|
| 320 |
+
"learning_rate": 1.1818973020017407e-05,
|
| 321 |
+
"loss": 1.0267,
|
| 322 |
+
"step": 23500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 4.18,
|
| 326 |
+
"learning_rate": 1.1644908616187991e-05,
|
| 327 |
+
"loss": 1.035,
|
| 328 |
+
"step": 24000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.26,
|
| 332 |
+
"learning_rate": 1.1470844212358574e-05,
|
| 333 |
+
"loss": 1.0298,
|
| 334 |
+
"step": 24500
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 4.35,
|
| 338 |
+
"learning_rate": 1.1296779808529156e-05,
|
| 339 |
+
"loss": 1.0265,
|
| 340 |
+
"step": 25000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 4.44,
|
| 344 |
+
"learning_rate": 1.112271540469974e-05,
|
| 345 |
+
"loss": 1.0337,
|
| 346 |
+
"step": 25500
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.53,
|
| 350 |
+
"learning_rate": 1.0948651000870323e-05,
|
| 351 |
+
"loss": 1.0265,
|
| 352 |
+
"step": 26000
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.61,
|
| 356 |
+
"learning_rate": 1.0774586597040905e-05,
|
| 357 |
+
"loss": 1.0264,
|
| 358 |
+
"step": 26500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 4.7,
|
| 362 |
+
"learning_rate": 1.0600522193211488e-05,
|
| 363 |
+
"loss": 1.0181,
|
| 364 |
+
"step": 27000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 4.79,
|
| 368 |
+
"learning_rate": 1.0426457789382072e-05,
|
| 369 |
+
"loss": 1.021,
|
| 370 |
+
"step": 27500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 4.87,
|
| 374 |
+
"learning_rate": 1.0252393385552655e-05,
|
| 375 |
+
"loss": 1.0249,
|
| 376 |
+
"step": 28000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 4.96,
|
| 380 |
+
"learning_rate": 1.0078328981723237e-05,
|
| 381 |
+
"loss": 1.0205,
|
| 382 |
+
"step": 28500
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 5.0,
|
| 386 |
+
"eval_loss": 1.0189781188964844,
|
| 387 |
+
"eval_runtime": 521.0752,
|
| 388 |
+
"eval_samples_per_second": 127.033,
|
| 389 |
+
"eval_steps_per_second": 1.986,
|
| 390 |
+
"step": 28725
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 5.05,
|
| 394 |
+
"learning_rate": 9.904264577893821e-06,
|
| 395 |
+
"loss": 1.0044,
|
| 396 |
+
"step": 29000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 5.13,
|
| 400 |
+
"learning_rate": 9.730200174064405e-06,
|
| 401 |
+
"loss": 0.9887,
|
| 402 |
+
"step": 29500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.22,
|
| 406 |
+
"learning_rate": 9.556135770234988e-06,
|
| 407 |
+
"loss": 0.993,
|
| 408 |
+
"step": 30000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.31,
|
| 412 |
+
"learning_rate": 9.38207136640557e-06,
|
| 413 |
+
"loss": 0.9946,
|
| 414 |
+
"step": 30500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 5.4,
|
| 418 |
+
"learning_rate": 9.208006962576153e-06,
|
| 419 |
+
"loss": 0.9898,
|
| 420 |
+
"step": 31000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 5.48,
|
| 424 |
+
"learning_rate": 9.033942558746737e-06,
|
| 425 |
+
"loss": 0.9902,
|
| 426 |
+
"step": 31500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 5.57,
|
| 430 |
+
"learning_rate": 8.85987815491732e-06,
|
| 431 |
+
"loss": 0.9899,
|
| 432 |
+
"step": 32000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 5.66,
|
| 436 |
+
"learning_rate": 8.685813751087904e-06,
|
| 437 |
+
"loss": 0.9884,
|
| 438 |
+
"step": 32500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 5.74,
|
| 442 |
+
"learning_rate": 8.511749347258486e-06,
|
| 443 |
+
"loss": 0.9906,
|
| 444 |
+
"step": 33000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 5.83,
|
| 448 |
+
"learning_rate": 8.33768494342907e-06,
|
| 449 |
+
"loss": 0.9856,
|
| 450 |
+
"step": 33500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 5.92,
|
| 454 |
+
"learning_rate": 8.163620539599653e-06,
|
| 455 |
+
"loss": 0.9923,
|
| 456 |
+
"step": 34000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 6.0,
|
| 460 |
+
"eval_loss": 1.0085190534591675,
|
| 461 |
+
"eval_runtime": 521.5738,
|
| 462 |
+
"eval_samples_per_second": 126.912,
|
| 463 |
+
"eval_steps_per_second": 1.984,
|
| 464 |
+
"step": 34470
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.01,
|
| 468 |
+
"learning_rate": 7.989556135770235e-06,
|
| 469 |
+
"loss": 0.9843,
|
| 470 |
+
"step": 34500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 6.09,
|
| 474 |
+
"learning_rate": 7.815491731940818e-06,
|
| 475 |
+
"loss": 0.9674,
|
| 476 |
+
"step": 35000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 6.18,
|
| 480 |
+
"learning_rate": 7.641427328111402e-06,
|
| 481 |
+
"loss": 0.9647,
|
| 482 |
+
"step": 35500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 6.27,
|
| 486 |
+
"learning_rate": 7.4673629242819845e-06,
|
| 487 |
+
"loss": 0.9664,
|
| 488 |
+
"step": 36000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 6.35,
|
| 492 |
+
"learning_rate": 7.293298520452569e-06,
|
| 493 |
+
"loss": 0.9689,
|
| 494 |
+
"step": 36500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 6.44,
|
| 498 |
+
"learning_rate": 7.119234116623151e-06,
|
| 499 |
+
"loss": 0.9668,
|
| 500 |
+
"step": 37000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.53,
|
| 504 |
+
"learning_rate": 6.9451697127937345e-06,
|
| 505 |
+
"loss": 0.9617,
|
| 506 |
+
"step": 37500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.61,
|
| 510 |
+
"learning_rate": 6.771105308964318e-06,
|
| 511 |
+
"loss": 0.962,
|
| 512 |
+
"step": 38000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 6.7,
|
| 516 |
+
"learning_rate": 6.5970409051349e-06,
|
| 517 |
+
"loss": 0.9633,
|
| 518 |
+
"step": 38500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6.79,
|
| 522 |
+
"learning_rate": 6.422976501305484e-06,
|
| 523 |
+
"loss": 0.9611,
|
| 524 |
+
"step": 39000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6.88,
|
| 528 |
+
"learning_rate": 6.248912097476066e-06,
|
| 529 |
+
"loss": 0.9617,
|
| 530 |
+
"step": 39500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.96,
|
| 534 |
+
"learning_rate": 6.0748476936466495e-06,
|
| 535 |
+
"loss": 0.959,
|
| 536 |
+
"step": 40000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 7.0,
|
| 540 |
+
"eval_loss": 1.0030972957611084,
|
| 541 |
+
"eval_runtime": 523.5292,
|
| 542 |
+
"eval_samples_per_second": 126.438,
|
| 543 |
+
"eval_steps_per_second": 1.977,
|
| 544 |
+
"step": 40215
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 7.05,
|
| 548 |
+
"learning_rate": 5.900783289817232e-06,
|
| 549 |
+
"loss": 0.9511,
|
| 550 |
+
"step": 40500
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 7.14,
|
| 554 |
+
"learning_rate": 5.726718885987816e-06,
|
| 555 |
+
"loss": 0.9432,
|
| 556 |
+
"step": 41000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 7.22,
|
| 560 |
+
"learning_rate": 5.5526544821583995e-06,
|
| 561 |
+
"loss": 0.942,
|
| 562 |
+
"step": 41500
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.31,
|
| 566 |
+
"learning_rate": 5.378590078328983e-06,
|
| 567 |
+
"loss": 0.9415,
|
| 568 |
+
"step": 42000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 7.4,
|
| 572 |
+
"learning_rate": 5.204525674499565e-06,
|
| 573 |
+
"loss": 0.9427,
|
| 574 |
+
"step": 42500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 7.48,
|
| 578 |
+
"learning_rate": 5.030461270670149e-06,
|
| 579 |
+
"loss": 0.9477,
|
| 580 |
+
"step": 43000
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 7.57,
|
| 584 |
+
"learning_rate": 4.856396866840731e-06,
|
| 585 |
+
"loss": 0.9439,
|
| 586 |
+
"step": 43500
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 7.66,
|
| 590 |
+
"learning_rate": 4.682332463011314e-06,
|
| 591 |
+
"loss": 0.945,
|
| 592 |
+
"step": 44000
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 7.75,
|
| 596 |
+
"learning_rate": 4.508268059181898e-06,
|
| 597 |
+
"loss": 0.9456,
|
| 598 |
+
"step": 44500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 7.83,
|
| 602 |
+
"learning_rate": 4.334203655352481e-06,
|
| 603 |
+
"loss": 0.9436,
|
| 604 |
+
"step": 45000
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 7.92,
|
| 608 |
+
"learning_rate": 4.1601392515230636e-06,
|
| 609 |
+
"loss": 0.9447,
|
| 610 |
+
"step": 45500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 8.0,
|
| 614 |
+
"eval_loss": 1.0001778602600098,
|
| 615 |
+
"eval_runtime": 520.9721,
|
| 616 |
+
"eval_samples_per_second": 127.059,
|
| 617 |
+
"eval_steps_per_second": 1.987,
|
| 618 |
+
"step": 45960
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 8.01,
|
| 622 |
+
"learning_rate": 3.986074847693647e-06,
|
| 623 |
+
"loss": 0.9459,
|
| 624 |
+
"step": 46000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 8.09,
|
| 628 |
+
"learning_rate": 3.8120104438642302e-06,
|
| 629 |
+
"loss": 0.9265,
|
| 630 |
+
"step": 46500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 8.18,
|
| 634 |
+
"learning_rate": 3.637946040034813e-06,
|
| 635 |
+
"loss": 0.9271,
|
| 636 |
+
"step": 47000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 8.27,
|
| 640 |
+
"learning_rate": 3.463881636205396e-06,
|
| 641 |
+
"loss": 0.9286,
|
| 642 |
+
"step": 47500
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 8.36,
|
| 646 |
+
"learning_rate": 3.2898172323759794e-06,
|
| 647 |
+
"loss": 0.9302,
|
| 648 |
+
"step": 48000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 8.44,
|
| 652 |
+
"learning_rate": 3.1157528285465627e-06,
|
| 653 |
+
"loss": 0.933,
|
| 654 |
+
"step": 48500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 8.53,
|
| 658 |
+
"learning_rate": 2.9416884247171456e-06,
|
| 659 |
+
"loss": 0.9272,
|
| 660 |
+
"step": 49000
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 8.62,
|
| 664 |
+
"learning_rate": 2.7676240208877285e-06,
|
| 665 |
+
"loss": 0.9266,
|
| 666 |
+
"step": 49500
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 8.7,
|
| 670 |
+
"learning_rate": 2.5935596170583114e-06,
|
| 671 |
+
"loss": 0.9294,
|
| 672 |
+
"step": 50000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 8.79,
|
| 676 |
+
"learning_rate": 2.4194952132288948e-06,
|
| 677 |
+
"loss": 0.9312,
|
| 678 |
+
"step": 50500
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 8.88,
|
| 682 |
+
"learning_rate": 2.245430809399478e-06,
|
| 683 |
+
"loss": 0.9306,
|
| 684 |
+
"step": 51000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 8.96,
|
| 688 |
+
"learning_rate": 2.071366405570061e-06,
|
| 689 |
+
"loss": 0.9278,
|
| 690 |
+
"step": 51500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 9.0,
|
| 694 |
+
"eval_loss": 0.9995460510253906,
|
| 695 |
+
"eval_runtime": 522.976,
|
| 696 |
+
"eval_samples_per_second": 126.572,
|
| 697 |
+
"eval_steps_per_second": 1.979,
|
| 698 |
+
"step": 51705
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 9.05,
|
| 702 |
+
"learning_rate": 1.8973020017406443e-06,
|
| 703 |
+
"loss": 0.92,
|
| 704 |
+
"step": 52000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 9.14,
|
| 708 |
+
"learning_rate": 1.7232375979112272e-06,
|
| 709 |
+
"loss": 0.9178,
|
| 710 |
+
"step": 52500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 9.23,
|
| 714 |
+
"learning_rate": 1.5491731940818103e-06,
|
| 715 |
+
"loss": 0.9189,
|
| 716 |
+
"step": 53000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 9.31,
|
| 720 |
+
"learning_rate": 1.3751087902523935e-06,
|
| 721 |
+
"loss": 0.9164,
|
| 722 |
+
"step": 53500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 9.4,
|
| 726 |
+
"learning_rate": 1.2010443864229766e-06,
|
| 727 |
+
"loss": 0.9186,
|
| 728 |
+
"step": 54000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 9.49,
|
| 732 |
+
"learning_rate": 1.0269799825935597e-06,
|
| 733 |
+
"loss": 0.9199,
|
| 734 |
+
"step": 54500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 9.57,
|
| 738 |
+
"learning_rate": 8.529155787641428e-07,
|
| 739 |
+
"loss": 0.918,
|
| 740 |
+
"step": 55000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 9.66,
|
| 744 |
+
"learning_rate": 6.788511749347259e-07,
|
| 745 |
+
"loss": 0.9229,
|
| 746 |
+
"step": 55500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 9.75,
|
| 750 |
+
"learning_rate": 5.04786771105309e-07,
|
| 751 |
+
"loss": 0.9203,
|
| 752 |
+
"step": 56000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 9.83,
|
| 756 |
+
"learning_rate": 3.3072236727589213e-07,
|
| 757 |
+
"loss": 0.9202,
|
| 758 |
+
"step": 56500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 9.92,
|
| 762 |
+
"learning_rate": 1.566579634464752e-07,
|
| 763 |
+
"loss": 0.9168,
|
| 764 |
+
"step": 57000
|
| 765 |
+
}
|
| 766 |
+
],
|
| 767 |
+
"max_steps": 57450,
|
| 768 |
+
"num_train_epochs": 10,
|
| 769 |
+
"total_flos": 8.267810851042099e+18,
|
| 770 |
+
"trial_name": null,
|
| 771 |
+
"trial_params": null
|
| 772 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d98f0cd1f86c279190b4a3e645aece194d8c60dd6900ae98f39118fa7c63049c
|
| 3 |
+
size 2927
|