Training in progress, step 200
Browse files- adapter_config.json +18 -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 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
|
| 4 |
+
"exclude_modules": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"feedforward_modules": "down_proj",
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_ia3_weights": true,
|
| 9 |
+
"modules_to_save": null,
|
| 10 |
+
"peft_type": "IA3",
|
| 11 |
+
"revision": null,
|
| 12 |
+
"target_modules": [
|
| 13 |
+
"down_proj",
|
| 14 |
+
"v_proj",
|
| 15 |
+
"k_proj"
|
| 16 |
+
],
|
| 17 |
+
"task_type": "CAUSAL_LM"
|
| 18 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09e60ea9073a9a1103e5f8eef1e302be95a39ffd42dedefe3f7156ec5f1a0a2f
|
| 3 |
+
size 798032
|
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": 4.7588, "lr": 4.999999876629946e-05, "epoch": 0.00016004097048844505, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "10:12:53", "throughput": 1674.04, "total_tokens": 7696}
|
| 2 |
+
{"current_steps": 10, "total_steps": 40000, "loss": 4.4944, "lr": 4.999999375439123e-05, "epoch": 0.0003200819409768901, "percentage": 0.03, "elapsed_time": "0:00:07", "remaining_time": "8:07:24", "throughput": 2087.22, "total_tokens": 15264}
|
| 3 |
+
{"current_steps": 15, "total_steps": 40000, "loss": 3.0838, "lr": 4.9999984887169785e-05, "epoch": 0.0004801229114653351, "percentage": 0.04, "elapsed_time": "0:00:10", "remaining_time": "7:26:55", "throughput": 2303.04, "total_tokens": 23168}
|
| 4 |
+
{"current_steps": 20, "total_steps": 40000, "loss": 3.4841, "lr": 4.9999972164636506e-05, "epoch": 0.0006401638819537802, "percentage": 0.05, "elapsed_time": "0:00:12", "remaining_time": "7:03:52", "throughput": 2430.91, "total_tokens": 30928}
|
| 5 |
+
{"current_steps": 25, "total_steps": 40000, "loss": 3.4071, "lr": 4.999995558679334e-05, "epoch": 0.0008002048524422252, "percentage": 0.06, "elapsed_time": "0:00:15", "remaining_time": "6:49:13", "throughput": 2500.68, "total_tokens": 38400}
|
| 6 |
+
{"current_steps": 30, "total_steps": 40000, "loss": 5.2599, "lr": 4.999993515364287e-05, "epoch": 0.0009602458229306702, "percentage": 0.07, "elapsed_time": "0:00:18", "remaining_time": "6:43:59", "throughput": 2560.9, "total_tokens": 46592}
|
| 7 |
+
{"current_steps": 35, "total_steps": 40000, "loss": 4.4605, "lr": 4.999991086518822e-05, "epoch": 0.0011202867934191152, "percentage": 0.09, "elapsed_time": "0:00:20", "remaining_time": "6:36:55", "throughput": 2601.36, "total_tokens": 54256}
|
| 8 |
+
{"current_steps": 40, "total_steps": 40000, "loss": 3.314, "lr": 4.999988272143315e-05, "epoch": 0.0012803277639075604, "percentage": 0.1, "elapsed_time": "0:00:23", "remaining_time": "6:32:09", "throughput": 2632.33, "total_tokens": 62000}
|
| 9 |
+
{"current_steps": 45, "total_steps": 40000, "loss": 4.7484, "lr": 4.999985072238199e-05, "epoch": 0.0014403687343960054, "percentage": 0.11, "elapsed_time": "0:00:26", "remaining_time": "6:28:12", "throughput": 2657.37, "total_tokens": 69712}
|
| 10 |
+
{"current_steps": 50, "total_steps": 40000, "loss": 3.3694, "lr": 4.999981486803969e-05, "epoch": 0.0016004097048844504, "percentage": 0.12, "elapsed_time": "0:00:28", "remaining_time": "6:24:41", "throughput": 2667.4, "total_tokens": 77056}
|
| 11 |
+
{"current_steps": 55, "total_steps": 40000, "loss": 3.0911, "lr": 4.999977515841176e-05, "epoch": 0.0017604506753728954, "percentage": 0.14, "elapsed_time": "0:00:31", "remaining_time": "6:22:55", "throughput": 2678.52, "total_tokens": 84736}
|
| 12 |
+
{"current_steps": 60, "total_steps": 40000, "loss": 4.7994, "lr": 4.9999731593504344e-05, "epoch": 0.0019204916458613404, "percentage": 0.15, "elapsed_time": "0:00:34", "remaining_time": "6:20:36", "throughput": 2687.31, "total_tokens": 92192}
|
| 13 |
+
{"current_steps": 65, "total_steps": 40000, "loss": 2.9374, "lr": 4.999968417332415e-05, "epoch": 0.0020805326163497854, "percentage": 0.16, "elapsed_time": "0:00:36", "remaining_time": "6:18:48", "throughput": 2701.46, "total_tokens": 99936}
|
| 14 |
+
{"current_steps": 70, "total_steps": 40000, "loss": 2.3165, "lr": 4.999963289787848e-05, "epoch": 0.0022405735868382304, "percentage": 0.18, "elapsed_time": "0:00:39", "remaining_time": "6:18:26", "throughput": 2713.51, "total_tokens": 108016}
|
| 15 |
+
{"current_steps": 75, "total_steps": 40000, "loss": 1.7202, "lr": 4.999957776717526e-05, "epoch": 0.002400614557326676, "percentage": 0.19, "elapsed_time": "0:00:42", "remaining_time": "6:16:29", "throughput": 2719.71, "total_tokens": 115408}
|
| 16 |
+
{"current_steps": 80, "total_steps": 40000, "loss": 1.3302, "lr": 4.9999518781222984e-05, "epoch": 0.002560655527815121, "percentage": 0.2, "elapsed_time": "0:00:45", "remaining_time": "6:15:02", "throughput": 2725.56, "total_tokens": 122912}
|
| 17 |
+
{"current_steps": 85, "total_steps": 40000, "loss": 2.6427, "lr": 4.9999455940030746e-05, "epoch": 0.002720696498303566, "percentage": 0.21, "elapsed_time": "0:00:47", "remaining_time": "6:14:40", "throughput": 2735.57, "total_tokens": 130960}
|
| 18 |
+
{"current_steps": 90, "total_steps": 40000, "loss": 2.0842, "lr": 4.999938924360824e-05, "epoch": 0.002880737468792011, "percentage": 0.22, "elapsed_time": "0:00:50", "remaining_time": "6:13:59", "throughput": 2742.92, "total_tokens": 138800}
|
| 19 |
+
{"current_steps": 95, "total_steps": 40000, "loss": 2.2955, "lr": 4.999931869196575e-05, "epoch": 0.003040778439280456, "percentage": 0.24, "elapsed_time": "0:00:53", "remaining_time": "6:13:48", "throughput": 2749.7, "total_tokens": 146816}
|
| 20 |
+
{"current_steps": 100, "total_steps": 40000, "loss": 2.2762, "lr": 4.999924428511416e-05, "epoch": 0.003200819409768901, "percentage": 0.25, "elapsed_time": "0:00:56", "remaining_time": "6:13:14", "throughput": 2753.16, "total_tokens": 154528}
|
| 21 |
+
{"current_steps": 105, "total_steps": 40000, "loss": 1.7255, "lr": 4.999916602306494e-05, "epoch": 0.003360860380257346, "percentage": 0.26, "elapsed_time": "0:00:58", "remaining_time": "6:12:32", "throughput": 2759.39, "total_tokens": 162336}
|
| 22 |
+
{"current_steps": 110, "total_steps": 40000, "loss": 0.8693, "lr": 4.999908390583016e-05, "epoch": 0.003520901350745791, "percentage": 0.27, "elapsed_time": "0:01:01", "remaining_time": "6:11:39", "throughput": 2764.32, "total_tokens": 169984}
|
| 23 |
+
{"current_steps": 115, "total_steps": 40000, "loss": 1.9365, "lr": 4.999899793342247e-05, "epoch": 0.003680942321234236, "percentage": 0.29, "elapsed_time": "0:01:04", "remaining_time": "6:10:58", "throughput": 2771.07, "total_tokens": 177840}
|
| 24 |
+
{"current_steps": 120, "total_steps": 40000, "loss": 2.368, "lr": 4.999890810585516e-05, "epoch": 0.003840983291722681, "percentage": 0.3, "elapsed_time": "0:01:06", "remaining_time": "6:09:56", "throughput": 2774.02, "total_tokens": 185280}
|
| 25 |
+
{"current_steps": 125, "total_steps": 40000, "loss": 1.6402, "lr": 4.999881442314206e-05, "epoch": 0.004001024262211126, "percentage": 0.31, "elapsed_time": "0:01:09", "remaining_time": "6:09:09", "throughput": 2775.14, "total_tokens": 192688}
|
| 26 |
+
{"current_steps": 130, "total_steps": 40000, "loss": 1.3085, "lr": 4.9998716885297617e-05, "epoch": 0.004161065232699571, "percentage": 0.33, "elapsed_time": "0:01:12", "remaining_time": "6:08:35", "throughput": 2776.21, "total_tokens": 200192}
|
| 27 |
+
{"current_steps": 135, "total_steps": 40000, "loss": 1.8731, "lr": 4.999861549233688e-05, "epoch": 0.004321106203188016, "percentage": 0.34, "elapsed_time": "0:01:14", "remaining_time": "6:07:53", "throughput": 2780.03, "total_tokens": 207808}
|
| 28 |
+
{"current_steps": 140, "total_steps": 40000, "loss": 2.4475, "lr": 4.999851024427548e-05, "epoch": 0.004481147173676461, "percentage": 0.35, "elapsed_time": "0:01:17", "remaining_time": "6:07:07", "throughput": 2780.12, "total_tokens": 215088}
|
| 29 |
+
{"current_steps": 145, "total_steps": 40000, "loss": 1.7387, "lr": 4.999840114112965e-05, "epoch": 0.004641188144164906, "percentage": 0.36, "elapsed_time": "0:01:19", "remaining_time": "6:06:24", "throughput": 2779.95, "total_tokens": 222352}
|
| 30 |
+
{"current_steps": 150, "total_steps": 40000, "loss": 1.6335, "lr": 4.999828818291621e-05, "epoch": 0.004801229114653352, "percentage": 0.38, "elapsed_time": "0:01:22", "remaining_time": "6:05:55", "throughput": 2781.83, "total_tokens": 229904}
|
| 31 |
+
{"current_steps": 155, "total_steps": 40000, "loss": 1.752, "lr": 4.999817136965259e-05, "epoch": 0.004961270085141797, "percentage": 0.39, "elapsed_time": "0:01:25", "remaining_time": "6:05:14", "throughput": 2781.15, "total_tokens": 237088}
|
| 32 |
+
{"current_steps": 160, "total_steps": 40000, "loss": 1.8466, "lr": 4.9998050701356794e-05, "epoch": 0.005121311055630242, "percentage": 0.4, "elapsed_time": "0:01:27", "remaining_time": "6:04:22", "throughput": 2782.3, "total_tokens": 244288}
|
| 33 |
+
{"current_steps": 165, "total_steps": 40000, "loss": 1.9445, "lr": 4.999792617804744e-05, "epoch": 0.005281352026118687, "percentage": 0.41, "elapsed_time": "0:01:30", "remaining_time": "6:04:07", "throughput": 2785.55, "total_tokens": 252080}
|
| 34 |
+
{"current_steps": 170, "total_steps": 40000, "loss": 1.4664, "lr": 4.9997797799743724e-05, "epoch": 0.005441392996607132, "percentage": 0.43, "elapsed_time": "0:01:33", "remaining_time": "6:03:41", "throughput": 2787.4, "total_tokens": 259616}
|
| 35 |
+
{"current_steps": 175, "total_steps": 40000, "loss": 1.314, "lr": 4.999766556646545e-05, "epoch": 0.005601433967095577, "percentage": 0.44, "elapsed_time": "0:01:35", "remaining_time": "6:03:51", "throughput": 2790.42, "total_tokens": 267696}
|
| 36 |
+
{"current_steps": 180, "total_steps": 40000, "loss": 1.1727, "lr": 4.9997529478232996e-05, "epoch": 0.005761474937584022, "percentage": 0.45, "elapsed_time": "0:01:38", "remaining_time": "6:03:30", "throughput": 2793.65, "total_tokens": 275424}
|
| 37 |
+
{"current_steps": 185, "total_steps": 40000, "loss": 1.4723, "lr": 4.9997389535067365e-05, "epoch": 0.005921515908072467, "percentage": 0.46, "elapsed_time": "0:01:41", "remaining_time": "6:03:27", "throughput": 2795.64, "total_tokens": 283280}
|
| 38 |
+
{"current_steps": 190, "total_steps": 40000, "loss": 1.7534, "lr": 4.999724573699012e-05, "epoch": 0.006081556878560912, "percentage": 0.47, "elapsed_time": "0:01:43", "remaining_time": "6:03:07", "throughput": 2799.85, "total_tokens": 291136}
|
| 39 |
+
{"current_steps": 195, "total_steps": 40000, "loss": 1.762, "lr": 4.9997098084023457e-05, "epoch": 0.006241597849049357, "percentage": 0.49, "elapsed_time": "0:01:46", "remaining_time": "6:02:57", "throughput": 2802.23, "total_tokens": 298960}
|
| 40 |
+
{"current_steps": 200, "total_steps": 40000, "loss": 0.8115, "lr": 4.999694657619013e-05, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:01:49", "remaining_time": "6:02:47", "throughput": 2803.5, "total_tokens": 306656}
|
| 41 |
+
{"current_steps": 200, "total_steps": 40000, "eval_loss": 1.5857535600662231, "epoch": 0.006401638819537802, "percentage": 0.5, "elapsed_time": "0:11:06", "remaining_time": "1 day, 12:51:53", "throughput": 459.82, "total_tokens": 306656}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4363170f584a1b2b758fd497686c3bb760bfbc36a2eb22af00316e71e56c3474
|
| 3 |
+
size 5752
|