Training in progress, step 200
Browse files- adapter_config.json +17 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- trainer_log.jsonl +42 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
| 4 |
+
"inference_mode": true,
|
| 5 |
+
"num_attention_heads": 32,
|
| 6 |
+
"num_layers": 32,
|
| 7 |
+
"num_transformer_submodules": 1,
|
| 8 |
+
"num_virtual_tokens": 100,
|
| 9 |
+
"peft_type": "PROMPT_TUNING",
|
| 10 |
+
"prompt_tuning_init": "RANDOM",
|
| 11 |
+
"prompt_tuning_init_text": null,
|
| 12 |
+
"revision": null,
|
| 13 |
+
"task_type": "CAUSAL_LM",
|
| 14 |
+
"token_dim": 4096,
|
| 15 |
+
"tokenizer_kwargs": null,
|
| 16 |
+
"tokenizer_name_or_path": null
|
| 17 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d567b6ff9be5c9131adb7a56ba1b8d1a9dc0e650e9d6aebfab9dbffdd81392c1
|
| 3 |
+
size 1638528
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
| 3 |
+
size 587404
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 40000, "loss": 3.9088, "lr": 0.29999999259779675, "epoch": 0.00016004097048844505, "percentage": 0.01, "elapsed_time": "0:00:03", "remaining_time": "8:38:39", "throughput": 1978.19, "total_tokens": 7696}
|
| 2 |
+
{"current_steps": 10, "total_steps": 40000, "loss": 1.2959, "lr": 0.29999996252634736, "epoch": 0.0003200819409768901, "percentage": 0.03, "elapsed_time": "0:00:05", "remaining_time": "6:39:14", "throughput": 2548.14, "total_tokens": 15264}
|
| 3 |
+
{"current_steps": 15, "total_steps": 40000, "loss": 1.1207, "lr": 0.2999999093230187, "epoch": 0.0004801229114653351, "percentage": 0.04, "elapsed_time": "0:00:08", "remaining_time": "6:00:26", "throughput": 2855.7, "total_tokens": 23168}
|
| 4 |
+
{"current_steps": 20, "total_steps": 40000, "loss": 1.0786, "lr": 0.299999832987819, "epoch": 0.0006401638819537802, "percentage": 0.05, "elapsed_time": "0:00:10", "remaining_time": "5:40:05", "throughput": 3029.83, "total_tokens": 30928}
|
| 5 |
+
{"current_steps": 25, "total_steps": 40000, "loss": 0.9448, "lr": 0.29999973352076004, "epoch": 0.0008002048524422252, "percentage": 0.06, "elapsed_time": "0:00:12", "remaining_time": "5:27:03", "throughput": 3128.9, "total_tokens": 38400}
|
| 6 |
+
{"current_steps": 30, "total_steps": 40000, "loss": 1.1072, "lr": 0.2999996109218572, "epoch": 0.0009602458229306702, "percentage": 0.07, "elapsed_time": "0:00:14", "remaining_time": "5:21:17", "throughput": 3220.2, "total_tokens": 46592}
|
| 7 |
+
{"current_steps": 35, "total_steps": 40000, "loss": 0.8808, "lr": 0.2999994651911293, "epoch": 0.0011202867934191152, "percentage": 0.09, "elapsed_time": "0:00:16", "remaining_time": "5:15:21", "throughput": 3274.14, "total_tokens": 54256}
|
| 8 |
+
{"current_steps": 40, "total_steps": 40000, "loss": 0.7262, "lr": 0.2999992963285989, "epoch": 0.0012803277639075604, "percentage": 0.1, "elapsed_time": "0:00:18", "remaining_time": "5:10:53", "throughput": 3320.51, "total_tokens": 62000}
|
| 9 |
+
{"current_steps": 45, "total_steps": 40000, "loss": 0.9723, "lr": 0.29999910433429194, "epoch": 0.0014403687343960054, "percentage": 0.11, "elapsed_time": "0:00:20", "remaining_time": "5:07:19", "throughput": 3356.82, "total_tokens": 69712}
|
| 10 |
+
{"current_steps": 50, "total_steps": 40000, "loss": 0.7873, "lr": 0.29999888920823814, "epoch": 0.0016004097048844504, "percentage": 0.12, "elapsed_time": "0:00:22", "remaining_time": "5:03:40", "throughput": 3378.98, "total_tokens": 77056}
|
| 11 |
+
{"current_steps": 55, "total_steps": 40000, "loss": 0.6864, "lr": 0.29999865095047057, "epoch": 0.0017604506753728954, "percentage": 0.14, "elapsed_time": "0:00:24", "remaining_time": "5:01:20", "throughput": 3403.84, "total_tokens": 84736}
|
| 12 |
+
{"current_steps": 60, "total_steps": 40000, "loss": 0.953, "lr": 0.29999838956102604, "epoch": 0.0019204916458613404, "percentage": 0.15, "elapsed_time": "0:00:26", "remaining_time": "4:58:57", "throughput": 3421.26, "total_tokens": 92192}
|
| 13 |
+
{"current_steps": 65, "total_steps": 40000, "loss": 0.8605, "lr": 0.29999810503994484, "epoch": 0.0020805326163497854, "percentage": 0.16, "elapsed_time": "0:00:29", "remaining_time": "4:57:26", "throughput": 3440.41, "total_tokens": 99936}
|
| 14 |
+
{"current_steps": 70, "total_steps": 40000, "loss": 0.9826, "lr": 0.29999779738727084, "epoch": 0.0022405735868382304, "percentage": 0.18, "elapsed_time": "0:00:31", "remaining_time": "4:56:16", "throughput": 3466.07, "total_tokens": 108016}
|
| 15 |
+
{"current_steps": 75, "total_steps": 40000, "loss": 0.7263, "lr": 0.29999746660305154, "epoch": 0.002400614557326676, "percentage": 0.19, "elapsed_time": "0:00:33", "remaining_time": "4:54:37", "throughput": 3475.36, "total_tokens": 115408}
|
| 16 |
+
{"current_steps": 80, "total_steps": 40000, "loss": 0.8501, "lr": 0.2999971126873379, "epoch": 0.002560655527815121, "percentage": 0.2, "elapsed_time": "0:00:35", "remaining_time": "4:53:15", "throughput": 3485.74, "total_tokens": 122912}
|
| 17 |
+
{"current_steps": 85, "total_steps": 40000, "loss": 0.8215, "lr": 0.2999967356401845, "epoch": 0.002720696498303566, "percentage": 0.21, "elapsed_time": "0:00:37", "remaining_time": "4:52:49", "throughput": 3500.13, "total_tokens": 130960}
|
| 18 |
+
{"current_steps": 90, "total_steps": 40000, "loss": 0.9747, "lr": 0.29999633546164944, "epoch": 0.002880737468792011, "percentage": 0.22, "elapsed_time": "0:00:39", "remaining_time": "4:52:08", "throughput": 3511.43, "total_tokens": 138800}
|
| 19 |
+
{"current_steps": 95, "total_steps": 40000, "loss": 0.9542, "lr": 0.29999591215179444, "epoch": 0.003040778439280456, "percentage": 0.24, "elapsed_time": "0:00:41", "remaining_time": "4:51:44", "throughput": 3523.11, "total_tokens": 146816}
|
| 20 |
+
{"current_steps": 100, "total_steps": 40000, "loss": 0.8164, "lr": 0.2999954657106849, "epoch": 0.003200819409768901, "percentage": 0.25, "elapsed_time": "0:00:43", "remaining_time": "4:51:03", "throughput": 3530.6, "total_tokens": 154528}
|
| 21 |
+
{"current_steps": 105, "total_steps": 40000, "loss": 0.9361, "lr": 0.2999949961383896, "epoch": 0.003360860380257346, "percentage": 0.26, "elapsed_time": "0:00:45", "remaining_time": "4:50:30", "throughput": 3538.71, "total_tokens": 162336}
|
| 22 |
+
{"current_steps": 110, "total_steps": 40000, "loss": 0.6829, "lr": 0.2999945034349809, "epoch": 0.003520901350745791, "percentage": 0.27, "elapsed_time": "0:00:47", "remaining_time": "4:49:58", "throughput": 3542.9, "total_tokens": 169984}
|
| 23 |
+
{"current_steps": 115, "total_steps": 40000, "loss": 1.0903, "lr": 0.2999939876005348, "epoch": 0.003680942321234236, "percentage": 0.29, "elapsed_time": "0:00:50", "remaining_time": "4:49:37", "throughput": 3549.43, "total_tokens": 177840}
|
| 24 |
+
{"current_steps": 120, "total_steps": 40000, "loss": 1.0752, "lr": 0.29999344863513094, "epoch": 0.003840983291722681, "percentage": 0.3, "elapsed_time": "0:00:52", "remaining_time": "4:49:02", "throughput": 3550.53, "total_tokens": 185280}
|
| 25 |
+
{"current_steps": 125, "total_steps": 40000, "loss": 0.8038, "lr": 0.2999928865388523, "epoch": 0.004001024262211126, "percentage": 0.31, "elapsed_time": "0:00:54", "remaining_time": "4:48:19", "throughput": 3553.12, "total_tokens": 192688}
|
| 26 |
+
{"current_steps": 130, "total_steps": 40000, "loss": 0.944, "lr": 0.29999230131178567, "epoch": 0.004161065232699571, "percentage": 0.33, "elapsed_time": "0:00:56", "remaining_time": "4:47:40", "throughput": 3557.06, "total_tokens": 200192}
|
| 27 |
+
{"current_steps": 135, "total_steps": 40000, "loss": 1.0317, "lr": 0.2999916929540212, "epoch": 0.004321106203188016, "percentage": 0.34, "elapsed_time": "0:00:58", "remaining_time": "4:47:14", "throughput": 3560.65, "total_tokens": 207808}
|
| 28 |
+
{"current_steps": 140, "total_steps": 40000, "loss": 0.9124, "lr": 0.29999106146565285, "epoch": 0.004481147173676461, "percentage": 0.35, "elapsed_time": "0:01:00", "remaining_time": "4:46:34", "throughput": 3561.47, "total_tokens": 215088}
|
| 29 |
+
{"current_steps": 145, "total_steps": 40000, "loss": 0.7552, "lr": 0.29999040684677786, "epoch": 0.004641188144164906, "percentage": 0.36, "elapsed_time": "0:01:02", "remaining_time": "4:45:55", "throughput": 3562.5, "total_tokens": 222352}
|
| 30 |
+
{"current_steps": 150, "total_steps": 40000, "loss": 0.8683, "lr": 0.2999897290974972, "epoch": 0.004801229114653352, "percentage": 0.38, "elapsed_time": "0:01:04", "remaining_time": "4:45:31", "throughput": 3565.21, "total_tokens": 229904}
|
| 31 |
+
{"current_steps": 155, "total_steps": 40000, "loss": 1.1364, "lr": 0.2999890282179155, "epoch": 0.004961270085141797, "percentage": 0.39, "elapsed_time": "0:01:06", "remaining_time": "4:44:53", "throughput": 3565.52, "total_tokens": 237088}
|
| 32 |
+
{"current_steps": 160, "total_steps": 40000, "loss": 0.7657, "lr": 0.29998830420814077, "epoch": 0.005121311055630242, "percentage": 0.4, "elapsed_time": "0:01:08", "remaining_time": "4:44:23", "throughput": 3564.7, "total_tokens": 244288}
|
| 33 |
+
{"current_steps": 165, "total_steps": 40000, "loss": 0.8708, "lr": 0.2999875570682846, "epoch": 0.005281352026118687, "percentage": 0.41, "elapsed_time": "0:01:10", "remaining_time": "4:44:10", "throughput": 3569.38, "total_tokens": 252080}
|
| 34 |
+
{"current_steps": 170, "total_steps": 40000, "loss": 0.7754, "lr": 0.2999867867984623, "epoch": 0.005441392996607132, "percentage": 0.43, "elapsed_time": "0:01:12", "remaining_time": "4:43:50", "throughput": 3571.69, "total_tokens": 259616}
|
| 35 |
+
{"current_steps": 175, "total_steps": 40000, "loss": 0.7498, "lr": 0.29998599339879267, "epoch": 0.005601433967095577, "percentage": 0.44, "elapsed_time": "0:01:14", "remaining_time": "4:43:47", "throughput": 3577.72, "total_tokens": 267696}
|
| 36 |
+
{"current_steps": 180, "total_steps": 40000, "loss": 0.8502, "lr": 0.29998517686939796, "epoch": 0.005761474937584022, "percentage": 0.45, "elapsed_time": "0:01:16", "remaining_time": "4:43:36", "throughput": 3580.56, "total_tokens": 275424}
|
| 37 |
+
{"current_steps": 185, "total_steps": 40000, "loss": 0.7629, "lr": 0.29998433721040413, "epoch": 0.005921515908072467, "percentage": 0.46, "elapsed_time": "0:01:19", "remaining_time": "4:43:29", "throughput": 3584.21, "total_tokens": 283280}
|
| 38 |
+
{"current_steps": 190, "total_steps": 40000, "loss": 0.7152, "lr": 0.29998347442194073, "epoch": 0.006081556878560912, "percentage": 0.47, "elapsed_time": "0:01:21", "remaining_time": "4:43:23", "throughput": 3587.64, "total_tokens": 291136}
|
| 39 |
+
{"current_steps": 195, "total_steps": 40000, "loss": 0.795, "lr": 0.2999825885041407, "epoch": 0.006241597849049357, "percentage": 0.49, "elapsed_time": "0:01:23", "remaining_time": "4:43:15", "throughput": 3590.69, "total_tokens": 298960}
|
| 40 |
+
{"current_steps": 200, "total_steps": 40000, "loss": 0.696, "lr": 0.29998167945714077, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:01:25", "remaining_time": "4:43:04", "throughput": 3592.88, "total_tokens": 306656}
|
| 41 |
+
{"current_steps": 200, "total_steps": 40000, "eval_loss": 0.8529680371284485, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:12:11", "remaining_time": "1 day, 16:26:29", "throughput": 419.15, "total_tokens": 306656}
|
| 42 |
+
{"current_steps": 205, "total_steps": 40000, "loss": 0.8588, "lr": 0.2999807472810811, "epoch": 0.006561679790026247, "percentage": 0.51, "elapsed_time": "0:12:14", "remaining_time": "1 day, 15:37:51", "throughput": 427.28, "total_tokens": 314032}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c43550a417da0a4d717f64f400a8a1b3efa890fb2764d4f8aaab9afb5949bed2
|
| 3 |
+
size 5752
|