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 +41 -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:df6208a3d22e709c20b646463783657f4936e8d34c486976943f08122f17f775
|
| 3 |
+
size 1074144
|
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 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 40000, "loss": 0.69, "lr": 4.999999876629946e-05, "epoch": 0.0013197835554968984, "percentage": 0.01, "elapsed_time": "0:00:05", "remaining_time": "11:57:04", "throughput": 761.51, "total_tokens": 4096}
|
| 2 |
+
{"current_steps": 10, "total_steps": 40000, "loss": 0.5025, "lr": 4.999999375439123e-05, "epoch": 0.002639567110993797, "percentage": 0.03, "elapsed_time": "0:00:08", "remaining_time": "9:00:52", "throughput": 1025.24, "total_tokens": 8320}
|
| 3 |
+
{"current_steps": 15, "total_steps": 40000, "loss": 0.3734, "lr": 4.9999984887169785e-05, "epoch": 0.0039593506664906955, "percentage": 0.04, "elapsed_time": "0:00:10", "remaining_time": "8:01:54", "throughput": 1224.29, "total_tokens": 13280}
|
| 4 |
+
{"current_steps": 20, "total_steps": 40000, "loss": 0.5512, "lr": 4.9999972164636506e-05, "epoch": 0.005279134221987594, "percentage": 0.05, "elapsed_time": "0:00:13", "remaining_time": "7:32:19", "throughput": 1268.06, "total_tokens": 17216}
|
| 5 |
+
{"current_steps": 25, "total_steps": 40000, "loss": 0.6261, "lr": 4.999995558679334e-05, "epoch": 0.006598917777484493, "percentage": 0.06, "elapsed_time": "0:00:16", "remaining_time": "7:14:55", "throughput": 1298.07, "total_tokens": 21184}
|
| 6 |
+
{"current_steps": 30, "total_steps": 40000, "loss": 0.4646, "lr": 4.999993515364287e-05, "epoch": 0.007918701332981391, "percentage": 0.07, "elapsed_time": "0:00:19", "remaining_time": "7:03:11", "throughput": 1348.32, "total_tokens": 25696}
|
| 7 |
+
{"current_steps": 35, "total_steps": 40000, "loss": 0.343, "lr": 4.999991086518822e-05, "epoch": 0.00923848488847829, "percentage": 0.09, "elapsed_time": "0:00:21", "remaining_time": "6:54:43", "throughput": 1372.98, "total_tokens": 29920}
|
| 8 |
+
{"current_steps": 40, "total_steps": 40000, "loss": 0.3155, "lr": 4.999988272143315e-05, "epoch": 0.010558268443975187, "percentage": 0.1, "elapsed_time": "0:00:24", "remaining_time": "6:48:12", "throughput": 1399.16, "total_tokens": 34304}
|
| 9 |
+
{"current_steps": 45, "total_steps": 40000, "loss": 0.3025, "lr": 4.999985072238199e-05, "epoch": 0.011878051999472087, "percentage": 0.11, "elapsed_time": "0:00:27", "remaining_time": "6:43:07", "throughput": 1410.8, "total_tokens": 38432}
|
| 10 |
+
{"current_steps": 50, "total_steps": 40000, "loss": 0.2499, "lr": 4.999981486803969e-05, "epoch": 0.013197835554968985, "percentage": 0.12, "elapsed_time": "0:00:29", "remaining_time": "6:39:15", "throughput": 1409.9, "total_tokens": 42272}
|
| 11 |
+
{"current_steps": 55, "total_steps": 40000, "loss": 0.3054, "lr": 4.999977515841176e-05, "epoch": 0.014517619110465884, "percentage": 0.14, "elapsed_time": "0:00:32", "remaining_time": "6:36:00", "throughput": 1419.28, "total_tokens": 46432}
|
| 12 |
+
{"current_steps": 60, "total_steps": 40000, "loss": 0.2166, "lr": 4.9999731593504344e-05, "epoch": 0.015837402665962782, "percentage": 0.15, "elapsed_time": "0:00:35", "remaining_time": "6:33:10", "throughput": 1420.36, "total_tokens": 50336}
|
| 13 |
+
{"current_steps": 65, "total_steps": 40000, "loss": 0.3356, "lr": 4.999968417332415e-05, "epoch": 0.017157186221459682, "percentage": 0.16, "elapsed_time": "0:00:38", "remaining_time": "6:30:47", "throughput": 1426.27, "total_tokens": 54432}
|
| 14 |
+
{"current_steps": 70, "total_steps": 40000, "loss": 0.2014, "lr": 4.999963289787848e-05, "epoch": 0.01847696977695658, "percentage": 0.18, "elapsed_time": "0:00:40", "remaining_time": "6:28:45", "throughput": 1443.05, "total_tokens": 59008}
|
| 15 |
+
{"current_steps": 75, "total_steps": 40000, "loss": 0.3397, "lr": 4.999957776717526e-05, "epoch": 0.019796753332453478, "percentage": 0.19, "elapsed_time": "0:00:43", "remaining_time": "6:26:58", "throughput": 1446.04, "total_tokens": 63072}
|
| 16 |
+
{"current_steps": 80, "total_steps": 40000, "loss": 0.0698, "lr": 4.9999518781222984e-05, "epoch": 0.021116536887950375, "percentage": 0.2, "elapsed_time": "0:00:46", "remaining_time": "6:25:30", "throughput": 1448.37, "total_tokens": 67136}
|
| 17 |
+
{"current_steps": 85, "total_steps": 40000, "loss": 0.3107, "lr": 4.9999455940030746e-05, "epoch": 0.022436320443447275, "percentage": 0.21, "elapsed_time": "0:00:49", "remaining_time": "6:24:08", "throughput": 1460.42, "total_tokens": 71680}
|
| 18 |
+
{"current_steps": 90, "total_steps": 40000, "loss": 0.1298, "lr": 4.999938924360824e-05, "epoch": 0.023756103998944175, "percentage": 0.22, "elapsed_time": "0:00:51", "remaining_time": "6:22:54", "throughput": 1465.7, "total_tokens": 75936}
|
| 19 |
+
{"current_steps": 95, "total_steps": 40000, "loss": 0.2475, "lr": 4.999931869196575e-05, "epoch": 0.02507588755444107, "percentage": 0.24, "elapsed_time": "0:00:54", "remaining_time": "6:21:45", "throughput": 1464.75, "total_tokens": 79872}
|
| 20 |
+
{"current_steps": 100, "total_steps": 40000, "loss": 0.2222, "lr": 4.999924428511416e-05, "epoch": 0.02639567110993797, "percentage": 0.25, "elapsed_time": "0:00:57", "remaining_time": "6:20:42", "throughput": 1465.05, "total_tokens": 83872}
|
| 21 |
+
{"current_steps": 105, "total_steps": 40000, "loss": 0.2636, "lr": 4.999916602306494e-05, "epoch": 0.027715454665434867, "percentage": 0.26, "elapsed_time": "0:00:59", "remaining_time": "6:19:49", "throughput": 1468.23, "total_tokens": 88064}
|
| 22 |
+
{"current_steps": 110, "total_steps": 40000, "loss": 0.2018, "lr": 4.999908390583016e-05, "epoch": 0.029035238220931767, "percentage": 0.27, "elapsed_time": "0:01:02", "remaining_time": "6:18:59", "throughput": 1468.67, "total_tokens": 92096}
|
| 23 |
+
{"current_steps": 115, "total_steps": 40000, "loss": 0.1997, "lr": 4.999899793342247e-05, "epoch": 0.030355021776428667, "percentage": 0.29, "elapsed_time": "0:01:05", "remaining_time": "6:18:12", "throughput": 1474.57, "total_tokens": 96480}
|
| 24 |
+
{"current_steps": 120, "total_steps": 40000, "loss": 0.0614, "lr": 4.999890810585516e-05, "epoch": 0.031674805331925564, "percentage": 0.3, "elapsed_time": "0:01:08", "remaining_time": "6:17:28", "throughput": 1480.06, "total_tokens": 100864}
|
| 25 |
+
{"current_steps": 125, "total_steps": 40000, "loss": 0.1687, "lr": 4.999881442314206e-05, "epoch": 0.03299458888742246, "percentage": 0.31, "elapsed_time": "0:01:10", "remaining_time": "6:16:47", "throughput": 1482.37, "total_tokens": 105056}
|
| 26 |
+
{"current_steps": 130, "total_steps": 40000, "loss": 0.3439, "lr": 4.9998716885297617e-05, "epoch": 0.034314372442919364, "percentage": 0.33, "elapsed_time": "0:01:13", "remaining_time": "6:16:09", "throughput": 1481.06, "total_tokens": 108992}
|
| 27 |
+
{"current_steps": 135, "total_steps": 40000, "loss": 0.1046, "lr": 4.999861549233688e-05, "epoch": 0.03563415599841626, "percentage": 0.34, "elapsed_time": "0:01:16", "remaining_time": "6:15:39", "throughput": 1481.57, "total_tokens": 113088}
|
| 28 |
+
{"current_steps": 140, "total_steps": 40000, "loss": 0.155, "lr": 4.999851024427548e-05, "epoch": 0.03695393955391316, "percentage": 0.35, "elapsed_time": "0:01:19", "remaining_time": "6:15:08", "throughput": 1485.96, "total_tokens": 117472}
|
| 29 |
+
{"current_steps": 145, "total_steps": 40000, "loss": 0.2107, "lr": 4.999840114112965e-05, "epoch": 0.03827372310941006, "percentage": 0.36, "elapsed_time": "0:01:21", "remaining_time": "6:14:38", "throughput": 1486.1, "total_tokens": 121536}
|
| 30 |
+
{"current_steps": 150, "total_steps": 40000, "loss": 0.1487, "lr": 4.999828818291621e-05, "epoch": 0.039593506664906956, "percentage": 0.38, "elapsed_time": "0:01:24", "remaining_time": "6:14:09", "throughput": 1487.47, "total_tokens": 125696}
|
| 31 |
+
{"current_steps": 155, "total_steps": 40000, "loss": 0.1678, "lr": 4.999817136965259e-05, "epoch": 0.04091329022040385, "percentage": 0.39, "elapsed_time": "0:01:27", "remaining_time": "6:13:42", "throughput": 1484.33, "total_tokens": 129472}
|
| 32 |
+
{"current_steps": 160, "total_steps": 40000, "loss": 0.2473, "lr": 4.9998050701356794e-05, "epoch": 0.04223307377590075, "percentage": 0.4, "elapsed_time": "0:01:29", "remaining_time": "6:13:20", "throughput": 1487.56, "total_tokens": 133824}
|
| 33 |
+
{"current_steps": 165, "total_steps": 40000, "loss": 0.1296, "lr": 4.999792617804744e-05, "epoch": 0.04355285733139765, "percentage": 0.41, "elapsed_time": "0:01:32", "remaining_time": "6:12:59", "throughput": 1485.76, "total_tokens": 137728}
|
| 34 |
+
{"current_steps": 170, "total_steps": 40000, "loss": 0.1214, "lr": 4.9997797799743724e-05, "epoch": 0.04487264088689455, "percentage": 0.43, "elapsed_time": "0:01:35", "remaining_time": "6:12:35", "throughput": 1485.67, "total_tokens": 141760}
|
| 35 |
+
{"current_steps": 175, "total_steps": 40000, "loss": 0.3424, "lr": 4.999766556646545e-05, "epoch": 0.046192424442391446, "percentage": 0.44, "elapsed_time": "0:01:38", "remaining_time": "6:12:12", "throughput": 1485.61, "total_tokens": 145792}
|
| 36 |
+
{"current_steps": 180, "total_steps": 40000, "loss": 0.2978, "lr": 4.9997529478232996e-05, "epoch": 0.04751220799788835, "percentage": 0.45, "elapsed_time": "0:01:40", "remaining_time": "6:11:50", "throughput": 1485.25, "total_tokens": 149792}
|
| 37 |
+
{"current_steps": 185, "total_steps": 40000, "loss": 0.2495, "lr": 4.9997389535067365e-05, "epoch": 0.048831991553385246, "percentage": 0.46, "elapsed_time": "0:01:43", "remaining_time": "6:11:30", "throughput": 1487.65, "total_tokens": 154080}
|
| 38 |
+
{"current_steps": 190, "total_steps": 40000, "loss": 0.3526, "lr": 4.999724573699012e-05, "epoch": 0.05015177510888214, "percentage": 0.47, "elapsed_time": "0:01:46", "remaining_time": "6:11:13", "throughput": 1490.08, "total_tokens": 158400}
|
| 39 |
+
{"current_steps": 195, "total_steps": 40000, "loss": 0.2161, "lr": 4.9997098084023457e-05, "epoch": 0.05147155866437904, "percentage": 0.49, "elapsed_time": "0:01:49", "remaining_time": "6:10:55", "throughput": 1490.72, "total_tokens": 162528}
|
| 40 |
+
{"current_steps": 200, "total_steps": 40000, "loss": 0.1539, "lr": 4.999694657619013e-05, "epoch": 0.05279134221987594, "percentage": 0.5, "elapsed_time": "0:01:51", "remaining_time": "6:10:38", "throughput": 1491.61, "total_tokens": 166688}
|
| 41 |
+
{"current_steps": 200, "total_steps": 40000, "eval_loss": 0.18415530025959015, "epoch": 0.05279134221987594, "percentage": 0.5, "elapsed_time": "0:02:52", "remaining_time": "9:31:32", "throughput": 967.29, "total_tokens": 166688}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a12760980a4345103134f904053fedff05fb630c958a1915d0df65d3a24227cf
|
| 3 |
+
size 5752
|