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 sha256:21330fd44d16bb8487882a48e14b6a3adc811bb7964639958ebc9c8f727d0a42
|
| 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": 3.0874, "lr": 0.29999999259779675, "epoch": 0.0008157272208173587, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "9:31:18", "throughput": 2049.72, "total_tokens": 8784}
|
| 2 |
+
{"current_steps": 10, "total_steps": 40000, "loss": 0.6102, "lr": 0.29999996252634736, "epoch": 0.0016314544416347174, "percentage": 0.03, "elapsed_time": "0:00:06", "remaining_time": "7:26:55", "throughput": 2763.03, "total_tokens": 18528}
|
| 3 |
+
{"current_steps": 15, "total_steps": 40000, "loss": 0.384, "lr": 0.2999999093230187, "epoch": 0.002447181662452076, "percentage": 0.04, "elapsed_time": "0:00:09", "remaining_time": "6:53:03", "throughput": 3137.23, "total_tokens": 29168}
|
| 4 |
+
{"current_steps": 20, "total_steps": 40000, "loss": 0.3615, "lr": 0.299999832987819, "epoch": 0.0032629088832694347, "percentage": 0.05, "elapsed_time": "0:00:12", "remaining_time": "6:40:22", "throughput": 3380.46, "total_tokens": 40624}
|
| 5 |
+
{"current_steps": 25, "total_steps": 40000, "loss": 0.4024, "lr": 0.29999973352076004, "epoch": 0.004078636104086793, "percentage": 0.06, "elapsed_time": "0:00:14", "remaining_time": "6:22:24", "throughput": 3482.28, "total_tokens": 49968}
|
| 6 |
+
{"current_steps": 30, "total_steps": 40000, "loss": 0.3496, "lr": 0.2999996109218572, "epoch": 0.004894363324904152, "percentage": 0.07, "elapsed_time": "0:00:16", "remaining_time": "6:16:00", "throughput": 3583.07, "total_tokens": 60672}
|
| 7 |
+
{"current_steps": 35, "total_steps": 40000, "loss": 0.3796, "lr": 0.2999994651911293, "epoch": 0.005710090545721511, "percentage": 0.09, "elapsed_time": "0:00:19", "remaining_time": "6:12:44", "throughput": 3645.86, "total_tokens": 71408}
|
| 8 |
+
{"current_steps": 40, "total_steps": 40000, "loss": 0.3484, "lr": 0.2999992963285989, "epoch": 0.0065258177665388694, "percentage": 0.1, "elapsed_time": "0:00:22", "remaining_time": "6:11:35", "throughput": 3707.81, "total_tokens": 82752}
|
| 9 |
+
{"current_steps": 45, "total_steps": 40000, "loss": 0.3045, "lr": 0.29999910433429194, "epoch": 0.007341544987356228, "percentage": 0.11, "elapsed_time": "0:00:24", "remaining_time": "6:08:59", "throughput": 3741.51, "total_tokens": 93296}
|
| 10 |
+
{"current_steps": 50, "total_steps": 40000, "loss": 0.3677, "lr": 0.29999888920823814, "epoch": 0.008157272208173586, "percentage": 0.12, "elapsed_time": "0:00:27", "remaining_time": "6:07:55", "throughput": 3785.67, "total_tokens": 104592}
|
| 11 |
+
{"current_steps": 55, "total_steps": 40000, "loss": 0.4096, "lr": 0.29999865095047057, "epoch": 0.008972999428990946, "percentage": 0.14, "elapsed_time": "0:00:30", "remaining_time": "6:04:48", "throughput": 3814.94, "total_tokens": 114976}
|
| 12 |
+
{"current_steps": 60, "total_steps": 40000, "loss": 0.3382, "lr": 0.29999838956102604, "epoch": 0.009788726649808304, "percentage": 0.15, "elapsed_time": "0:00:32", "remaining_time": "6:01:40", "throughput": 3832.74, "total_tokens": 124944}
|
| 13 |
+
{"current_steps": 65, "total_steps": 40000, "loss": 0.3542, "lr": 0.29999810503994484, "epoch": 0.010604453870625663, "percentage": 0.16, "elapsed_time": "0:00:34", "remaining_time": "5:58:18", "throughput": 3845.45, "total_tokens": 134560}
|
| 14 |
+
{"current_steps": 70, "total_steps": 40000, "loss": 0.3557, "lr": 0.29999779738727084, "epoch": 0.011420181091443021, "percentage": 0.18, "elapsed_time": "0:00:37", "remaining_time": "5:56:01", "throughput": 3859.46, "total_tokens": 144528}
|
| 15 |
+
{"current_steps": 75, "total_steps": 40000, "loss": 0.3552, "lr": 0.29999746660305154, "epoch": 0.012235908312260381, "percentage": 0.19, "elapsed_time": "0:00:40", "remaining_time": "5:55:10", "throughput": 3873.3, "total_tokens": 155056}
|
| 16 |
+
{"current_steps": 80, "total_steps": 40000, "loss": 0.3471, "lr": 0.2999971126873379, "epoch": 0.013051635533077739, "percentage": 0.2, "elapsed_time": "0:00:42", "remaining_time": "5:52:31", "throughput": 3879.96, "total_tokens": 164464}
|
| 17 |
+
{"current_steps": 85, "total_steps": 40000, "loss": 0.3535, "lr": 0.2999967356401845, "epoch": 0.013867362753895097, "percentage": 0.21, "elapsed_time": "0:00:44", "remaining_time": "5:51:06", "throughput": 3892.12, "total_tokens": 174608}
|
| 18 |
+
{"current_steps": 90, "total_steps": 40000, "loss": 0.3549, "lr": 0.29999633546164944, "epoch": 0.014683089974712456, "percentage": 0.22, "elapsed_time": "0:00:47", "remaining_time": "5:51:08", "throughput": 3906.77, "total_tokens": 185616}
|
| 19 |
+
{"current_steps": 95, "total_steps": 40000, "loss": 0.3324, "lr": 0.29999591215179444, "epoch": 0.015498817195529814, "percentage": 0.24, "elapsed_time": "0:00:49", "remaining_time": "5:49:43", "throughput": 3910.77, "total_tokens": 195360}
|
| 20 |
+
{"current_steps": 100, "total_steps": 40000, "loss": 0.3662, "lr": 0.2999954657106849, "epoch": 0.016314544416347172, "percentage": 0.25, "elapsed_time": "0:00:52", "remaining_time": "5:50:50", "throughput": 3926.37, "total_tokens": 207152}
|
| 21 |
+
{"current_steps": 105, "total_steps": 40000, "loss": 0.3417, "lr": 0.2999949961383896, "epoch": 0.017130271637164532, "percentage": 0.26, "elapsed_time": "0:00:55", "remaining_time": "5:50:45", "throughput": 3936.11, "total_tokens": 218016}
|
| 22 |
+
{"current_steps": 110, "total_steps": 40000, "loss": 0.3507, "lr": 0.2999945034349809, "epoch": 0.01794599885798189, "percentage": 0.27, "elapsed_time": "0:00:58", "remaining_time": "5:51:36", "throughput": 3948.08, "total_tokens": 229680}
|
| 23 |
+
{"current_steps": 115, "total_steps": 40000, "loss": 0.3454, "lr": 0.2999939876005348, "epoch": 0.01876172607879925, "percentage": 0.29, "elapsed_time": "0:01:00", "remaining_time": "5:49:27", "throughput": 3947.13, "total_tokens": 238624}
|
| 24 |
+
{"current_steps": 120, "total_steps": 40000, "loss": 0.3474, "lr": 0.29999344863513094, "epoch": 0.019577453299616607, "percentage": 0.3, "elapsed_time": "0:01:02", "remaining_time": "5:48:35", "throughput": 3950.01, "total_tokens": 248592}
|
| 25 |
+
{"current_steps": 125, "total_steps": 40000, "loss": 0.3555, "lr": 0.2999928865388523, "epoch": 0.020393180520433967, "percentage": 0.31, "elapsed_time": "0:01:05", "remaining_time": "5:48:25", "throughput": 3958.06, "total_tokens": 259392}
|
| 26 |
+
{"current_steps": 130, "total_steps": 40000, "loss": 0.3349, "lr": 0.29999230131178567, "epoch": 0.021208907741251327, "percentage": 0.33, "elapsed_time": "0:01:08", "remaining_time": "5:47:56", "throughput": 3961.56, "total_tokens": 269664}
|
| 27 |
+
{"current_steps": 135, "total_steps": 40000, "loss": 0.347, "lr": 0.2999916929540212, "epoch": 0.022024634962068683, "percentage": 0.34, "elapsed_time": "0:01:10", "remaining_time": "5:48:13", "throughput": 3968.63, "total_tokens": 280800}
|
| 28 |
+
{"current_steps": 140, "total_steps": 40000, "loss": 0.3788, "lr": 0.29999106146565285, "epoch": 0.022840362182886043, "percentage": 0.35, "elapsed_time": "0:01:13", "remaining_time": "5:47:26", "throughput": 3970.68, "total_tokens": 290736}
|
| 29 |
+
{"current_steps": 145, "total_steps": 40000, "loss": 0.3515, "lr": 0.29999040684677786, "epoch": 0.023656089403703402, "percentage": 0.36, "elapsed_time": "0:01:15", "remaining_time": "5:47:03", "throughput": 3975.0, "total_tokens": 301152}
|
| 30 |
+
{"current_steps": 150, "total_steps": 40000, "loss": 0.3513, "lr": 0.2999897290974972, "epoch": 0.024471816624520762, "percentage": 0.38, "elapsed_time": "0:01:18", "remaining_time": "5:46:23", "throughput": 3975.99, "total_tokens": 311040}
|
| 31 |
+
{"current_steps": 155, "total_steps": 40000, "loss": 0.3515, "lr": 0.2999890282179155, "epoch": 0.025287543845338118, "percentage": 0.39, "elapsed_time": "0:01:21", "remaining_time": "5:47:06", "throughput": 3980.81, "total_tokens": 322512}
|
| 32 |
+
{"current_steps": 160, "total_steps": 40000, "loss": 0.3459, "lr": 0.29998830420814077, "epoch": 0.026103271066155478, "percentage": 0.4, "elapsed_time": "0:01:23", "remaining_time": "5:47:21", "throughput": 3986.47, "total_tokens": 333664}
|
| 33 |
+
{"current_steps": 165, "total_steps": 40000, "loss": 0.3384, "lr": 0.2999875570682846, "epoch": 0.026918998286972837, "percentage": 0.41, "elapsed_time": "0:01:26", "remaining_time": "5:47:44", "throughput": 3993.24, "total_tokens": 345104}
|
| 34 |
+
{"current_steps": 170, "total_steps": 40000, "loss": 0.3698, "lr": 0.2999867867984623, "epoch": 0.027734725507790194, "percentage": 0.43, "elapsed_time": "0:01:29", "remaining_time": "5:48:00", "throughput": 3997.84, "total_tokens": 356288}
|
| 35 |
+
{"current_steps": 175, "total_steps": 40000, "loss": 0.358, "lr": 0.29998599339879267, "epoch": 0.028550452728607553, "percentage": 0.44, "elapsed_time": "0:01:31", "remaining_time": "5:46:55", "throughput": 3998.67, "total_tokens": 365744}
|
| 36 |
+
{"current_steps": 180, "total_steps": 40000, "loss": 0.3428, "lr": 0.29998517686939796, "epoch": 0.029366179949424913, "percentage": 0.45, "elapsed_time": "0:01:33", "remaining_time": "5:46:32", "throughput": 4001.23, "total_tokens": 376080}
|
| 37 |
+
{"current_steps": 185, "total_steps": 40000, "loss": 0.338, "lr": 0.29998433721040413, "epoch": 0.030181907170242273, "percentage": 0.46, "elapsed_time": "0:01:36", "remaining_time": "5:46:25", "throughput": 4004.78, "total_tokens": 386784}
|
| 38 |
+
{"current_steps": 190, "total_steps": 40000, "loss": 0.3547, "lr": 0.29998347442194073, "epoch": 0.03099763439105963, "percentage": 0.47, "elapsed_time": "0:01:39", "remaining_time": "5:45:59", "throughput": 4006.36, "total_tokens": 396944}
|
| 39 |
+
{"current_steps": 195, "total_steps": 40000, "loss": 0.304, "lr": 0.2999825885041407, "epoch": 0.031813361611876985, "percentage": 0.49, "elapsed_time": "0:01:41", "remaining_time": "5:45:59", "throughput": 4011.36, "total_tokens": 407952}
|
| 40 |
+
{"current_steps": 200, "total_steps": 40000, "loss": 0.3351, "lr": 0.29998167945714077, "epoch": 0.032629088832694345, "percentage": 0.5, "elapsed_time": "0:01:44", "remaining_time": "5:45:35", "throughput": 4013.5, "total_tokens": 418192}
|
| 41 |
+
{"current_steps": 200, "total_steps": 40000, "eval_loss": 0.34499409794807434, "epoch": 0.032629088832694345, "percentage": 0.5, "elapsed_time": "0:04:18", "remaining_time": "14:17:43", "throughput": 1617.07, "total_tokens": 418192}
|
| 42 |
+
{"current_steps": 205, "total_steps": 40000, "loss": 0.3672, "lr": 0.2999807472810811, "epoch": 0.033444816053511704, "percentage": 0.51, "elapsed_time": "0:04:22", "remaining_time": "14:08:03", "throughput": 1636.85, "total_tokens": 429056}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de94d5b5a539c072aa48d8ebba0e3df7c9cdb74ebae0142178309e3e1118d211
|
| 3 |
+
size 5752
|