Training in progress, step 200
Browse files- adapter_config.json +15 -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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
| 4 |
+
"exclude_modules": null,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"modules_to_save": null,
|
| 7 |
+
"peft_type": "LN_TUNING",
|
| 8 |
+
"revision": null,
|
| 9 |
+
"target_modules": [
|
| 10 |
+
"input_layernorm",
|
| 11 |
+
"norm",
|
| 12 |
+
"post_attention_layernorm"
|
| 13 |
+
],
|
| 14 |
+
"task_type": "CAUSAL_LM"
|
| 15 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:268354d6c07e93fdd6f3abbec7e7cd2a62fa1a0379fc1786e4316e9e8af9b8b3
|
| 3 |
+
size 541712
|
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": 3.623, "lr": 4.999999876629946e-05, "epoch": 0.08849557522123894, "percentage": 0.01, "elapsed_time": "0:00:02", "remaining_time": "5:54:20", "throughput": 1149.75, "total_tokens": 3056}
|
| 2 |
+
{"current_steps": 10, "total_steps": 40000, "loss": 3.4413, "lr": 4.999999375439123e-05, "epoch": 0.17699115044247787, "percentage": 0.03, "elapsed_time": "0:00:04", "remaining_time": "4:30:17", "throughput": 1546.58, "total_tokens": 6272}
|
| 3 |
+
{"current_steps": 15, "total_steps": 40000, "loss": 2.4165, "lr": 4.9999984887169785e-05, "epoch": 0.26548672566371684, "percentage": 0.04, "elapsed_time": "0:00:05", "remaining_time": "4:00:40", "throughput": 1713.08, "total_tokens": 9280}
|
| 4 |
+
{"current_steps": 20, "total_steps": 40000, "loss": 3.2126, "lr": 4.9999972164636506e-05, "epoch": 0.35398230088495575, "percentage": 0.05, "elapsed_time": "0:00:06", "remaining_time": "3:51:04", "throughput": 1861.68, "total_tokens": 12912}
|
| 5 |
+
{"current_steps": 25, "total_steps": 40000, "loss": 3.839, "lr": 4.999995558679334e-05, "epoch": 0.4424778761061947, "percentage": 0.06, "elapsed_time": "0:00:08", "remaining_time": "3:40:26", "throughput": 1947.82, "total_tokens": 16112}
|
| 6 |
+
{"current_steps": 30, "total_steps": 40000, "loss": 3.1863, "lr": 4.999993515364287e-05, "epoch": 0.5309734513274337, "percentage": 0.07, "elapsed_time": "0:00:09", "remaining_time": "3:33:08", "throughput": 1938.63, "total_tokens": 18608}
|
| 7 |
+
{"current_steps": 35, "total_steps": 40000, "loss": 3.5783, "lr": 4.999991086518822e-05, "epoch": 0.6194690265486725, "percentage": 0.09, "elapsed_time": "0:00:11", "remaining_time": "3:29:50", "throughput": 2000.99, "total_tokens": 22064}
|
| 8 |
+
{"current_steps": 40, "total_steps": 40000, "loss": 3.2653, "lr": 4.999988272143315e-05, "epoch": 0.7079646017699115, "percentage": 0.1, "elapsed_time": "0:00:12", "remaining_time": "3:26:45", "throughput": 2013.82, "total_tokens": 25008}
|
| 9 |
+
{"current_steps": 45, "total_steps": 40000, "loss": 3.5403, "lr": 4.999985072238199e-05, "epoch": 0.7964601769911505, "percentage": 0.11, "elapsed_time": "0:00:13", "remaining_time": "3:23:48", "throughput": 2003.99, "total_tokens": 27600}
|
| 10 |
+
{"current_steps": 50, "total_steps": 40000, "loss": 3.581, "lr": 4.999981486803969e-05, "epoch": 0.8849557522123894, "percentage": 0.12, "elapsed_time": "0:00:15", "remaining_time": "3:21:20", "throughput": 1998.97, "total_tokens": 30224}
|
| 11 |
+
{"current_steps": 55, "total_steps": 40000, "loss": 3.3437, "lr": 4.999977515841176e-05, "epoch": 0.9734513274336283, "percentage": 0.14, "elapsed_time": "0:00:16", "remaining_time": "3:19:21", "throughput": 1975.93, "total_tokens": 32544}
|
| 12 |
+
{"current_steps": 60, "total_steps": 40000, "loss": 2.3598, "lr": 4.9999731593504344e-05, "epoch": 1.0530973451327434, "percentage": 0.15, "elapsed_time": "0:00:18", "remaining_time": "3:21:10", "throughput": 1941.23, "total_tokens": 35200}
|
| 13 |
+
{"current_steps": 65, "total_steps": 40000, "loss": 3.1623, "lr": 4.999968417332415e-05, "epoch": 1.1415929203539823, "percentage": 0.16, "elapsed_time": "0:00:19", "remaining_time": "3:19:49", "throughput": 1957.97, "total_tokens": 38208}
|
| 14 |
+
{"current_steps": 70, "total_steps": 40000, "loss": 3.2525, "lr": 4.999963289787848e-05, "epoch": 1.2300884955752212, "percentage": 0.18, "elapsed_time": "0:00:20", "remaining_time": "3:18:31", "throughput": 1959.28, "total_tokens": 40912}
|
| 15 |
+
{"current_steps": 75, "total_steps": 40000, "loss": 3.0856, "lr": 4.999957776717526e-05, "epoch": 1.3185840707964602, "percentage": 0.19, "elapsed_time": "0:00:22", "remaining_time": "3:17:55", "throughput": 1980.99, "total_tokens": 44192}
|
| 16 |
+
{"current_steps": 80, "total_steps": 40000, "loss": 3.1327, "lr": 4.9999518781222984e-05, "epoch": 1.407079646017699, "percentage": 0.2, "elapsed_time": "0:00:23", "remaining_time": "3:16:39", "throughput": 1988.62, "total_tokens": 47024}
|
| 17 |
+
{"current_steps": 85, "total_steps": 40000, "loss": 3.4364, "lr": 4.9999455940030746e-05, "epoch": 1.495575221238938, "percentage": 0.21, "elapsed_time": "0:00:25", "remaining_time": "3:16:25", "throughput": 2001.76, "total_tokens": 50240}
|
| 18 |
+
{"current_steps": 90, "total_steps": 40000, "loss": 3.2041, "lr": 4.999938924360824e-05, "epoch": 1.584070796460177, "percentage": 0.22, "elapsed_time": "0:00:26", "remaining_time": "3:15:20", "throughput": 1994.67, "total_tokens": 52720}
|
| 19 |
+
{"current_steps": 95, "total_steps": 40000, "loss": 3.7513, "lr": 4.999931869196575e-05, "epoch": 1.672566371681416, "percentage": 0.24, "elapsed_time": "0:00:27", "remaining_time": "3:15:01", "throughput": 2006.3, "total_tokens": 55888}
|
| 20 |
+
{"current_steps": 100, "total_steps": 40000, "loss": 3.3582, "lr": 4.999924428511416e-05, "epoch": 1.7610619469026547, "percentage": 0.25, "elapsed_time": "0:00:29", "remaining_time": "3:14:30", "throughput": 2006.94, "total_tokens": 58704}
|
| 21 |
+
{"current_steps": 105, "total_steps": 40000, "loss": 3.6738, "lr": 4.999916602306494e-05, "epoch": 1.8495575221238938, "percentage": 0.26, "elapsed_time": "0:00:30", "remaining_time": "3:14:16", "throughput": 2006.34, "total_tokens": 61552}
|
| 22 |
+
{"current_steps": 110, "total_steps": 40000, "loss": 3.5507, "lr": 4.999908390583016e-05, "epoch": 1.9380530973451329, "percentage": 0.27, "elapsed_time": "0:00:32", "remaining_time": "3:13:28", "throughput": 2011.26, "total_tokens": 64384}
|
| 23 |
+
{"current_steps": 115, "total_steps": 40000, "loss": 3.0185, "lr": 4.999899793342247e-05, "epoch": 2.017699115044248, "percentage": 0.29, "elapsed_time": "0:00:33", "remaining_time": "3:14:27", "throughput": 1978.75, "total_tokens": 66568}
|
| 24 |
+
{"current_steps": 120, "total_steps": 40000, "loss": 3.8258, "lr": 4.999890810585516e-05, "epoch": 2.106194690265487, "percentage": 0.3, "elapsed_time": "0:00:35", "remaining_time": "3:14:11", "throughput": 1984.97, "total_tokens": 69592}
|
| 25 |
+
{"current_steps": 125, "total_steps": 40000, "loss": 2.8506, "lr": 4.999881442314206e-05, "epoch": 2.1946902654867255, "percentage": 0.31, "elapsed_time": "0:00:36", "remaining_time": "3:13:37", "throughput": 1984.66, "total_tokens": 72280}
|
| 26 |
+
{"current_steps": 130, "total_steps": 40000, "loss": 2.9713, "lr": 4.9998716885297617e-05, "epoch": 2.2831858407079646, "percentage": 0.33, "elapsed_time": "0:00:37", "remaining_time": "3:13:17", "throughput": 1993.02, "total_tokens": 75368}
|
| 27 |
+
{"current_steps": 135, "total_steps": 40000, "loss": 2.8618, "lr": 4.999861549233688e-05, "epoch": 2.3716814159292037, "percentage": 0.34, "elapsed_time": "0:00:39", "remaining_time": "3:12:41", "throughput": 1990.73, "total_tokens": 77944}
|
| 28 |
+
{"current_steps": 140, "total_steps": 40000, "loss": 3.4215, "lr": 4.999851024427548e-05, "epoch": 2.4601769911504423, "percentage": 0.35, "elapsed_time": "0:00:40", "remaining_time": "3:12:16", "throughput": 1997.14, "total_tokens": 80920}
|
| 29 |
+
{"current_steps": 145, "total_steps": 40000, "loss": 3.8366, "lr": 4.999840114112965e-05, "epoch": 2.5486725663716814, "percentage": 0.36, "elapsed_time": "0:00:41", "remaining_time": "3:11:52", "throughput": 2004.49, "total_tokens": 83960}
|
| 30 |
+
{"current_steps": 150, "total_steps": 40000, "loss": 3.2003, "lr": 4.999828818291621e-05, "epoch": 2.6371681415929205, "percentage": 0.38, "elapsed_time": "0:00:43", "remaining_time": "3:11:38", "throughput": 2005.37, "total_tokens": 86792}
|
| 31 |
+
{"current_steps": 155, "total_steps": 40000, "loss": 3.6243, "lr": 4.999817136965259e-05, "epoch": 2.725663716814159, "percentage": 0.39, "elapsed_time": "0:00:44", "remaining_time": "3:11:50", "throughput": 2019.73, "total_tokens": 90440}
|
| 32 |
+
{"current_steps": 160, "total_steps": 40000, "loss": 2.9966, "lr": 4.9998050701356794e-05, "epoch": 2.814159292035398, "percentage": 0.4, "elapsed_time": "0:00:46", "remaining_time": "3:11:38", "throughput": 2025.36, "total_tokens": 93528}
|
| 33 |
+
{"current_steps": 165, "total_steps": 40000, "loss": 3.1198, "lr": 4.999792617804744e-05, "epoch": 2.9026548672566372, "percentage": 0.41, "elapsed_time": "0:00:47", "remaining_time": "3:11:10", "throughput": 2021.44, "total_tokens": 96040}
|
| 34 |
+
{"current_steps": 170, "total_steps": 40000, "loss": 3.3787, "lr": 4.9997797799743724e-05, "epoch": 2.991150442477876, "percentage": 0.43, "elapsed_time": "0:00:48", "remaining_time": "3:10:56", "throughput": 2024.54, "total_tokens": 99000}
|
| 35 |
+
{"current_steps": 175, "total_steps": 40000, "loss": 3.1563, "lr": 4.999766556646545e-05, "epoch": 3.0707964601769913, "percentage": 0.44, "elapsed_time": "0:00:50", "remaining_time": "3:11:49", "throughput": 2006.84, "total_tokens": 101496}
|
| 36 |
+
{"current_steps": 180, "total_steps": 40000, "loss": 2.3578, "lr": 4.9997529478232996e-05, "epoch": 3.15929203539823, "percentage": 0.45, "elapsed_time": "0:00:51", "remaining_time": "3:11:29", "throughput": 2009.99, "total_tokens": 104392}
|
| 37 |
+
{"current_steps": 185, "total_steps": 40000, "loss": 3.1306, "lr": 4.9997389535067365e-05, "epoch": 3.247787610619469, "percentage": 0.46, "elapsed_time": "0:00:53", "remaining_time": "3:11:10", "throughput": 2011.11, "total_tokens": 107192}
|
| 38 |
+
{"current_steps": 190, "total_steps": 40000, "loss": 3.3737, "lr": 4.999724573699012e-05, "epoch": 3.336283185840708, "percentage": 0.47, "elapsed_time": "0:00:54", "remaining_time": "3:10:58", "throughput": 2017.5, "total_tokens": 110328}
|
| 39 |
+
{"current_steps": 195, "total_steps": 40000, "loss": 3.1784, "lr": 4.9997098084023457e-05, "epoch": 3.4247787610619467, "percentage": 0.49, "elapsed_time": "0:00:56", "remaining_time": "3:10:36", "throughput": 2022.69, "total_tokens": 113320}
|
| 40 |
+
{"current_steps": 200, "total_steps": 40000, "loss": 3.425, "lr": 4.999694657619013e-05, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:00:57", "remaining_time": "3:10:24", "throughput": 2024.82, "total_tokens": 116248}
|
| 41 |
+
{"current_steps": 200, "total_steps": 40000, "eval_loss": 3.633723020553589, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:00:58", "remaining_time": "3:13:27", "throughput": 1992.94, "total_tokens": 116248}
|
| 42 |
+
{"current_steps": 205, "total_steps": 40000, "loss": 3.272, "lr": 4.999679121351352e-05, "epoch": 3.601769911504425, "percentage": 0.51, "elapsed_time": "0:01:00", "remaining_time": "3:15:32", "throughput": 1976.59, "total_tokens": 119464}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3521488b6755f75cf0d904f8b53df9cea0018aa0132525e6c0be0565f0d71e85
|
| 3 |
+
size 5752
|