Upload folder using huggingface_hub
Browse files- .gitignore +3 -0
- checkpoint-650/config.json +39 -0
- checkpoint-650/generation_config.json +6 -0
- checkpoint-650/model.safetensors +3 -0
- checkpoint-650/optimizer.pt +3 -0
- checkpoint-650/rng_state.pth +3 -0
- checkpoint-650/scheduler.pt +3 -0
- checkpoint-650/trainer_state.json +513 -0
- checkpoint-650/training_args.bin +3 -0
- config.json +39 -0
- emissions.csv +2 -0
- generation_config.json +6 -0
.gitignore
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
optimizer.pt
|
| 2 |
+
scheduler.pt
|
| 3 |
+
emissions.csv
|
checkpoint-650/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 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": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.35.2",
|
| 37 |
+
"use_cache": false,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
checkpoint-650/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": "4.35.2"
|
| 6 |
+
}
|
checkpoint-650/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:382198e6cd0cac4f332170e12112eb84deda057ba97f6519ca05753033ccd9ab
|
| 3 |
+
size 497774208
|
checkpoint-650/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc99124f8c990480e26e94fe84470cb27ca559f3ebee8ca6904cd99d0d9e7bb5
|
| 3 |
+
size 995641861
|
checkpoint-650/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cad6c28002af6bb4669d6d2df8dcb091a4be5a79ee965e45e468cc707112e210
|
| 3 |
+
size 17641
|
checkpoint-650/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59c9b2dab80c1c8446fc580818f0fd94aa11197aa1aba15285e6efccfa5bd6c9
|
| 3 |
+
size 627
|
checkpoint-650/trainer_state.json
ADDED
|
@@ -0,0 +1,513 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6376384496688843,
|
| 3 |
+
"best_model_checkpoint": "models/gpt2-lora-20g2s/checkpoint-650",
|
| 4 |
+
"epoch": 3.7818181818181817,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 650,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 2e-05,
|
| 14 |
+
"loss": 3.2975,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 1.9703264094955493e-05,
|
| 20 |
+
"loss": 2.4638,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.17,
|
| 25 |
+
"learning_rate": 1.940652818991098e-05,
|
| 26 |
+
"loss": 2.0924,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.23,
|
| 31 |
+
"learning_rate": 1.910979228486647e-05,
|
| 32 |
+
"loss": 1.9836,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.29,
|
| 37 |
+
"learning_rate": 1.8813056379821958e-05,
|
| 38 |
+
"loss": 1.9073,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.29,
|
| 43 |
+
"eval_loss": 1.7905287742614746,
|
| 44 |
+
"eval_runtime": 38.1325,
|
| 45 |
+
"eval_samples_per_second": 52.449,
|
| 46 |
+
"eval_steps_per_second": 6.556,
|
| 47 |
+
"step": 50
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.35,
|
| 51 |
+
"learning_rate": 1.851632047477745e-05,
|
| 52 |
+
"loss": 1.9059,
|
| 53 |
+
"step": 60
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.41,
|
| 57 |
+
"learning_rate": 1.821958456973294e-05,
|
| 58 |
+
"loss": 1.8664,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.47,
|
| 63 |
+
"learning_rate": 1.792284866468843e-05,
|
| 64 |
+
"loss": 1.8451,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.52,
|
| 69 |
+
"learning_rate": 1.7626112759643918e-05,
|
| 70 |
+
"loss": 1.8454,
|
| 71 |
+
"step": 90
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.58,
|
| 75 |
+
"learning_rate": 1.732937685459941e-05,
|
| 76 |
+
"loss": 1.8305,
|
| 77 |
+
"step": 100
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.58,
|
| 81 |
+
"eval_loss": 1.7229812145233154,
|
| 82 |
+
"eval_runtime": 37.9618,
|
| 83 |
+
"eval_samples_per_second": 52.685,
|
| 84 |
+
"eval_steps_per_second": 6.586,
|
| 85 |
+
"step": 100
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.64,
|
| 89 |
+
"learning_rate": 1.7032640949554898e-05,
|
| 90 |
+
"loss": 1.8263,
|
| 91 |
+
"step": 110
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.7,
|
| 95 |
+
"learning_rate": 1.673590504451039e-05,
|
| 96 |
+
"loss": 1.8206,
|
| 97 |
+
"step": 120
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.76,
|
| 101 |
+
"learning_rate": 1.6439169139465877e-05,
|
| 102 |
+
"loss": 1.7967,
|
| 103 |
+
"step": 130
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.81,
|
| 107 |
+
"learning_rate": 1.6142433234421366e-05,
|
| 108 |
+
"loss": 1.7962,
|
| 109 |
+
"step": 140
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.87,
|
| 113 |
+
"learning_rate": 1.5845697329376857e-05,
|
| 114 |
+
"loss": 1.7786,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.87,
|
| 119 |
+
"eval_loss": 1.6951161623001099,
|
| 120 |
+
"eval_runtime": 37.8104,
|
| 121 |
+
"eval_samples_per_second": 52.895,
|
| 122 |
+
"eval_steps_per_second": 6.612,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.93,
|
| 127 |
+
"learning_rate": 1.5548961424332346e-05,
|
| 128 |
+
"loss": 1.7931,
|
| 129 |
+
"step": 160
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.99,
|
| 133 |
+
"learning_rate": 1.5252225519287836e-05,
|
| 134 |
+
"loss": 1.7973,
|
| 135 |
+
"step": 170
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.05,
|
| 139 |
+
"learning_rate": 1.4955489614243324e-05,
|
| 140 |
+
"loss": 1.7681,
|
| 141 |
+
"step": 180
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.11,
|
| 145 |
+
"learning_rate": 1.4658753709198814e-05,
|
| 146 |
+
"loss": 1.7741,
|
| 147 |
+
"step": 190
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.16,
|
| 151 |
+
"learning_rate": 1.4362017804154305e-05,
|
| 152 |
+
"loss": 1.7542,
|
| 153 |
+
"step": 200
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.16,
|
| 157 |
+
"eval_loss": 1.6791621446609497,
|
| 158 |
+
"eval_runtime": 37.8129,
|
| 159 |
+
"eval_samples_per_second": 52.892,
|
| 160 |
+
"eval_steps_per_second": 6.612,
|
| 161 |
+
"step": 200
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.22,
|
| 165 |
+
"learning_rate": 1.4065281899109794e-05,
|
| 166 |
+
"loss": 1.7657,
|
| 167 |
+
"step": 210
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.28,
|
| 171 |
+
"learning_rate": 1.3768545994065284e-05,
|
| 172 |
+
"loss": 1.7393,
|
| 173 |
+
"step": 220
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.34,
|
| 177 |
+
"learning_rate": 1.3471810089020773e-05,
|
| 178 |
+
"loss": 1.7611,
|
| 179 |
+
"step": 230
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.4,
|
| 183 |
+
"learning_rate": 1.3175074183976262e-05,
|
| 184 |
+
"loss": 1.7362,
|
| 185 |
+
"step": 240
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.45,
|
| 189 |
+
"learning_rate": 1.2878338278931752e-05,
|
| 190 |
+
"loss": 1.7204,
|
| 191 |
+
"step": 250
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.45,
|
| 195 |
+
"eval_loss": 1.6689482927322388,
|
| 196 |
+
"eval_runtime": 37.8604,
|
| 197 |
+
"eval_samples_per_second": 52.826,
|
| 198 |
+
"eval_steps_per_second": 6.603,
|
| 199 |
+
"step": 250
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.51,
|
| 203 |
+
"learning_rate": 1.258160237388724e-05,
|
| 204 |
+
"loss": 1.7452,
|
| 205 |
+
"step": 260
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.57,
|
| 209 |
+
"learning_rate": 1.2284866468842732e-05,
|
| 210 |
+
"loss": 1.7307,
|
| 211 |
+
"step": 270
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 1.63,
|
| 215 |
+
"learning_rate": 1.1988130563798221e-05,
|
| 216 |
+
"loss": 1.7232,
|
| 217 |
+
"step": 280
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.69,
|
| 221 |
+
"learning_rate": 1.169139465875371e-05,
|
| 222 |
+
"loss": 1.7132,
|
| 223 |
+
"step": 290
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 1.75,
|
| 227 |
+
"learning_rate": 1.13946587537092e-05,
|
| 228 |
+
"loss": 1.7233,
|
| 229 |
+
"step": 300
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 1.75,
|
| 233 |
+
"eval_loss": 1.6592705249786377,
|
| 234 |
+
"eval_runtime": 37.8213,
|
| 235 |
+
"eval_samples_per_second": 52.88,
|
| 236 |
+
"eval_steps_per_second": 6.61,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.8,
|
| 241 |
+
"learning_rate": 1.1097922848664688e-05,
|
| 242 |
+
"loss": 1.7342,
|
| 243 |
+
"step": 310
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.86,
|
| 247 |
+
"learning_rate": 1.080118694362018e-05,
|
| 248 |
+
"loss": 1.698,
|
| 249 |
+
"step": 320
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.92,
|
| 253 |
+
"learning_rate": 1.050445103857567e-05,
|
| 254 |
+
"loss": 1.714,
|
| 255 |
+
"step": 330
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.98,
|
| 259 |
+
"learning_rate": 1.0207715133531158e-05,
|
| 260 |
+
"loss": 1.7059,
|
| 261 |
+
"step": 340
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.04,
|
| 265 |
+
"learning_rate": 9.910979228486648e-06,
|
| 266 |
+
"loss": 1.7033,
|
| 267 |
+
"step": 350
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.04,
|
| 271 |
+
"eval_loss": 1.6531213521957397,
|
| 272 |
+
"eval_runtime": 37.9884,
|
| 273 |
+
"eval_samples_per_second": 52.648,
|
| 274 |
+
"eval_steps_per_second": 6.581,
|
| 275 |
+
"step": 350
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.09,
|
| 279 |
+
"learning_rate": 9.614243323442138e-06,
|
| 280 |
+
"loss": 1.7045,
|
| 281 |
+
"step": 360
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.15,
|
| 285 |
+
"learning_rate": 9.317507418397626e-06,
|
| 286 |
+
"loss": 1.6734,
|
| 287 |
+
"step": 370
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.21,
|
| 291 |
+
"learning_rate": 9.020771513353116e-06,
|
| 292 |
+
"loss": 1.6923,
|
| 293 |
+
"step": 380
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.27,
|
| 297 |
+
"learning_rate": 8.724035608308606e-06,
|
| 298 |
+
"loss": 1.6846,
|
| 299 |
+
"step": 390
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.33,
|
| 303 |
+
"learning_rate": 8.427299703264096e-06,
|
| 304 |
+
"loss": 1.689,
|
| 305 |
+
"step": 400
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.33,
|
| 309 |
+
"eval_loss": 1.6485120058059692,
|
| 310 |
+
"eval_runtime": 37.8818,
|
| 311 |
+
"eval_samples_per_second": 52.796,
|
| 312 |
+
"eval_steps_per_second": 6.599,
|
| 313 |
+
"step": 400
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.39,
|
| 317 |
+
"learning_rate": 8.130563798219586e-06,
|
| 318 |
+
"loss": 1.6893,
|
| 319 |
+
"step": 410
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 2.44,
|
| 323 |
+
"learning_rate": 7.833827893175074e-06,
|
| 324 |
+
"loss": 1.6967,
|
| 325 |
+
"step": 420
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.5,
|
| 329 |
+
"learning_rate": 7.537091988130565e-06,
|
| 330 |
+
"loss": 1.7133,
|
| 331 |
+
"step": 430
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 2.56,
|
| 335 |
+
"learning_rate": 7.2403560830860545e-06,
|
| 336 |
+
"loss": 1.6804,
|
| 337 |
+
"step": 440
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 2.62,
|
| 341 |
+
"learning_rate": 6.943620178041544e-06,
|
| 342 |
+
"loss": 1.6858,
|
| 343 |
+
"step": 450
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 2.62,
|
| 347 |
+
"eval_loss": 1.6442703008651733,
|
| 348 |
+
"eval_runtime": 37.7726,
|
| 349 |
+
"eval_samples_per_second": 52.948,
|
| 350 |
+
"eval_steps_per_second": 6.619,
|
| 351 |
+
"step": 450
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 2.68,
|
| 355 |
+
"learning_rate": 6.646884272997033e-06,
|
| 356 |
+
"loss": 1.7165,
|
| 357 |
+
"step": 460
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 2.73,
|
| 361 |
+
"learning_rate": 6.3501483679525235e-06,
|
| 362 |
+
"loss": 1.7057,
|
| 363 |
+
"step": 470
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.79,
|
| 367 |
+
"learning_rate": 6.0534124629080126e-06,
|
| 368 |
+
"loss": 1.7044,
|
| 369 |
+
"step": 480
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.85,
|
| 373 |
+
"learning_rate": 5.756676557863502e-06,
|
| 374 |
+
"loss": 1.7139,
|
| 375 |
+
"step": 490
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.91,
|
| 379 |
+
"learning_rate": 5.459940652818992e-06,
|
| 380 |
+
"loss": 1.6919,
|
| 381 |
+
"step": 500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 2.91,
|
| 385 |
+
"eval_loss": 1.6420339345932007,
|
| 386 |
+
"eval_runtime": 37.8869,
|
| 387 |
+
"eval_samples_per_second": 52.789,
|
| 388 |
+
"eval_steps_per_second": 6.599,
|
| 389 |
+
"step": 500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.97,
|
| 393 |
+
"learning_rate": 5.163204747774481e-06,
|
| 394 |
+
"loss": 1.6894,
|
| 395 |
+
"step": 510
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 3.03,
|
| 399 |
+
"learning_rate": 4.866468842729971e-06,
|
| 400 |
+
"loss": 1.6738,
|
| 401 |
+
"step": 520
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.08,
|
| 405 |
+
"learning_rate": 4.5697329376854606e-06,
|
| 406 |
+
"loss": 1.6934,
|
| 407 |
+
"step": 530
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.14,
|
| 411 |
+
"learning_rate": 4.27299703264095e-06,
|
| 412 |
+
"loss": 1.6921,
|
| 413 |
+
"step": 540
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 3.2,
|
| 417 |
+
"learning_rate": 3.97626112759644e-06,
|
| 418 |
+
"loss": 1.694,
|
| 419 |
+
"step": 550
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 3.2,
|
| 423 |
+
"eval_loss": 1.6401287317276,
|
| 424 |
+
"eval_runtime": 37.7337,
|
| 425 |
+
"eval_samples_per_second": 53.003,
|
| 426 |
+
"eval_steps_per_second": 6.625,
|
| 427 |
+
"step": 550
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 3.26,
|
| 431 |
+
"learning_rate": 3.679525222551929e-06,
|
| 432 |
+
"loss": 1.6873,
|
| 433 |
+
"step": 560
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 3.32,
|
| 437 |
+
"learning_rate": 3.382789317507419e-06,
|
| 438 |
+
"loss": 1.6865,
|
| 439 |
+
"step": 570
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 3.37,
|
| 443 |
+
"learning_rate": 3.086053412462908e-06,
|
| 444 |
+
"loss": 1.6559,
|
| 445 |
+
"step": 580
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 3.43,
|
| 449 |
+
"learning_rate": 2.789317507418398e-06,
|
| 450 |
+
"loss": 1.6821,
|
| 451 |
+
"step": 590
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 3.49,
|
| 455 |
+
"learning_rate": 2.4925816023738876e-06,
|
| 456 |
+
"loss": 1.6758,
|
| 457 |
+
"step": 600
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 3.49,
|
| 461 |
+
"eval_loss": 1.6383044719696045,
|
| 462 |
+
"eval_runtime": 37.9349,
|
| 463 |
+
"eval_samples_per_second": 52.722,
|
| 464 |
+
"eval_steps_per_second": 6.59,
|
| 465 |
+
"step": 600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 3.55,
|
| 469 |
+
"learning_rate": 2.195845697329377e-06,
|
| 470 |
+
"loss": 1.6634,
|
| 471 |
+
"step": 610
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 3.61,
|
| 475 |
+
"learning_rate": 1.8991097922848666e-06,
|
| 476 |
+
"loss": 1.6653,
|
| 477 |
+
"step": 620
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 3.67,
|
| 481 |
+
"learning_rate": 1.6023738872403563e-06,
|
| 482 |
+
"loss": 1.6663,
|
| 483 |
+
"step": 630
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 3.72,
|
| 487 |
+
"learning_rate": 1.3056379821958458e-06,
|
| 488 |
+
"loss": 1.6745,
|
| 489 |
+
"step": 640
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 3.78,
|
| 493 |
+
"learning_rate": 1.0089020771513354e-06,
|
| 494 |
+
"loss": 1.6997,
|
| 495 |
+
"step": 650
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 3.78,
|
| 499 |
+
"eval_loss": 1.6376384496688843,
|
| 500 |
+
"eval_runtime": 37.8135,
|
| 501 |
+
"eval_samples_per_second": 52.891,
|
| 502 |
+
"eval_steps_per_second": 6.611,
|
| 503 |
+
"step": 650
|
| 504 |
+
}
|
| 505 |
+
],
|
| 506 |
+
"logging_steps": 10,
|
| 507 |
+
"max_steps": 684,
|
| 508 |
+
"num_train_epochs": 4,
|
| 509 |
+
"save_steps": 50,
|
| 510 |
+
"total_flos": 7247277483622400.0,
|
| 511 |
+
"trial_name": null,
|
| 512 |
+
"trial_params": null
|
| 513 |
+
}
|
checkpoint-650/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e45d0b6463555987601f0aaee8f8db6dcf6ba1e87e756ba81e518e89348c70a7
|
| 3 |
+
size 4091
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 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": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.35.2",
|
| 37 |
+
"use_cache": false,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
emissions.csv
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
|
| 2 |
+
2024-02-17T22:56:09,codecarbon,376d5494-80d9-4c1f-a01f-3f0425571f06,4937.664623737335,0.09999964238539377,2.025241688239727e-05,42.5,102.62131288069982,38.31930112838745,0.058291479068166674,0.143021615528312,0.05249310435122111,0.2538061989476999,USA,USA,Iowa,gcp,us-central1,Linux-5.10.0-28-cloud-amd64-x86_64-with-glibc2.31,3.9.2,2.3.4,16,Intel(R) Xeon(R) CPU @ 2.30GHz,4,4 x Tesla T4,,,102.1848030090332,machine,Y,1.0
|
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": "4.35.2"
|
| 6 |
+
}
|