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 |
+
"k_proj",
|
| 14 |
+
"down_proj",
|
| 15 |
+
"v_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:f6f2570126a20cf3fead479b39a266bda2fb32dc528085aea56c28fa67e70313
|
| 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": 0.6331, "lr": 4.999999876629946e-05, "epoch": 0.024213075060532687, "percentage": 0.01, "elapsed_time": "0:00:04", "remaining_time": "9:29:24", "throughput": 1895.54, "total_tokens": 8096}
|
| 2 |
+
{"current_steps": 10, "total_steps": 40000, "loss": 0.7419, "lr": 4.999999375439123e-05, "epoch": 0.048426150121065374, "percentage": 0.03, "elapsed_time": "0:00:07", "remaining_time": "8:23:33", "throughput": 2244.78, "total_tokens": 16960}
|
| 3 |
+
{"current_steps": 15, "total_steps": 40000, "loss": 0.892, "lr": 4.9999984887169785e-05, "epoch": 0.07263922518159806, "percentage": 0.04, "elapsed_time": "0:00:10", "remaining_time": "7:57:22", "throughput": 2361.69, "total_tokens": 25376}
|
| 4 |
+
{"current_steps": 20, "total_steps": 40000, "loss": 0.7043, "lr": 4.9999972164636506e-05, "epoch": 0.09685230024213075, "percentage": 0.05, "elapsed_time": "0:00:14", "remaining_time": "7:49:07", "throughput": 2461.26, "total_tokens": 34656}
|
| 5 |
+
{"current_steps": 25, "total_steps": 40000, "loss": 0.4641, "lr": 4.999995558679334e-05, "epoch": 0.12106537530266344, "percentage": 0.06, "elapsed_time": "0:00:17", "remaining_time": "7:39:56", "throughput": 2491.98, "total_tokens": 43008}
|
| 6 |
+
{"current_steps": 30, "total_steps": 40000, "loss": 0.5762, "lr": 4.999993515364287e-05, "epoch": 0.14527845036319612, "percentage": 0.07, "elapsed_time": "0:00:20", "remaining_time": "7:35:09", "throughput": 2518.11, "total_tokens": 51616}
|
| 7 |
+
{"current_steps": 35, "total_steps": 40000, "loss": 0.7544, "lr": 4.999991086518822e-05, "epoch": 0.1694915254237288, "percentage": 0.09, "elapsed_time": "0:00:23", "remaining_time": "7:31:41", "throughput": 2534.72, "total_tokens": 60160}
|
| 8 |
+
{"current_steps": 40, "total_steps": 40000, "loss": 0.6819, "lr": 4.999988272143315e-05, "epoch": 0.1937046004842615, "percentage": 0.1, "elapsed_time": "0:00:26", "remaining_time": "7:29:19", "throughput": 2557.68, "total_tokens": 69024}
|
| 9 |
+
{"current_steps": 45, "total_steps": 40000, "loss": 0.8529, "lr": 4.999985072238199e-05, "epoch": 0.2179176755447942, "percentage": 0.11, "elapsed_time": "0:00:30", "remaining_time": "7:27:15", "throughput": 2572.79, "total_tokens": 77760}
|
| 10 |
+
{"current_steps": 50, "total_steps": 40000, "loss": 0.5884, "lr": 4.999981486803969e-05, "epoch": 0.24213075060532688, "percentage": 0.12, "elapsed_time": "0:00:33", "remaining_time": "7:25:55", "throughput": 2583.95, "total_tokens": 86528}
|
| 11 |
+
{"current_steps": 55, "total_steps": 40000, "loss": 0.5177, "lr": 4.999977515841176e-05, "epoch": 0.26634382566585957, "percentage": 0.14, "elapsed_time": "0:00:36", "remaining_time": "7:24:21", "throughput": 2587.16, "total_tokens": 94976}
|
| 12 |
+
{"current_steps": 60, "total_steps": 40000, "loss": 0.4638, "lr": 4.9999731593504344e-05, "epoch": 0.29055690072639223, "percentage": 0.15, "elapsed_time": "0:00:39", "remaining_time": "7:23:22", "throughput": 2594.36, "total_tokens": 103680}
|
| 13 |
+
{"current_steps": 65, "total_steps": 40000, "loss": 0.4155, "lr": 4.999968417332415e-05, "epoch": 0.31476997578692495, "percentage": 0.16, "elapsed_time": "0:00:43", "remaining_time": "7:22:15", "throughput": 2600.61, "total_tokens": 112320}
|
| 14 |
+
{"current_steps": 70, "total_steps": 40000, "loss": 0.2687, "lr": 4.999963289787848e-05, "epoch": 0.3389830508474576, "percentage": 0.18, "elapsed_time": "0:00:46", "remaining_time": "7:21:17", "throughput": 2606.66, "total_tokens": 120992}
|
| 15 |
+
{"current_steps": 75, "total_steps": 40000, "loss": 0.1648, "lr": 4.999957776717526e-05, "epoch": 0.36319612590799033, "percentage": 0.19, "elapsed_time": "0:00:49", "remaining_time": "7:21:09", "throughput": 2614.17, "total_tokens": 129984}
|
| 16 |
+
{"current_steps": 80, "total_steps": 40000, "loss": 0.2942, "lr": 4.9999518781222984e-05, "epoch": 0.387409200968523, "percentage": 0.2, "elapsed_time": "0:00:52", "remaining_time": "7:20:26", "throughput": 2619.41, "total_tokens": 138720}
|
| 17 |
+
{"current_steps": 85, "total_steps": 40000, "loss": 0.2827, "lr": 4.9999455940030746e-05, "epoch": 0.4116222760290557, "percentage": 0.21, "elapsed_time": "0:00:56", "remaining_time": "7:20:14", "throughput": 2624.22, "total_tokens": 147616}
|
| 18 |
+
{"current_steps": 90, "total_steps": 40000, "loss": 0.2773, "lr": 4.999938924360824e-05, "epoch": 0.4358353510895884, "percentage": 0.22, "elapsed_time": "0:00:59", "remaining_time": "7:19:33", "throughput": 2627.32, "total_tokens": 156256}
|
| 19 |
+
{"current_steps": 95, "total_steps": 40000, "loss": 0.2906, "lr": 4.999931869196575e-05, "epoch": 0.4600484261501211, "percentage": 0.24, "elapsed_time": "0:01:02", "remaining_time": "7:18:57", "throughput": 2629.89, "total_tokens": 164896}
|
| 20 |
+
{"current_steps": 100, "total_steps": 40000, "loss": 0.3389, "lr": 4.999924428511416e-05, "epoch": 0.48426150121065376, "percentage": 0.25, "elapsed_time": "0:01:05", "remaining_time": "7:18:35", "throughput": 2632.18, "total_tokens": 173600}
|
| 21 |
+
{"current_steps": 105, "total_steps": 40000, "loss": 0.2198, "lr": 4.999916602306494e-05, "epoch": 0.5084745762711864, "percentage": 0.26, "elapsed_time": "0:01:09", "remaining_time": "7:18:35", "throughput": 2637.69, "total_tokens": 182688}
|
| 22 |
+
{"current_steps": 110, "total_steps": 40000, "loss": 0.2237, "lr": 4.999908390583016e-05, "epoch": 0.5326876513317191, "percentage": 0.27, "elapsed_time": "0:01:12", "remaining_time": "7:18:06", "throughput": 2639.91, "total_tokens": 191360}
|
| 23 |
+
{"current_steps": 115, "total_steps": 40000, "loss": 0.2321, "lr": 4.999899793342247e-05, "epoch": 0.5569007263922519, "percentage": 0.29, "elapsed_time": "0:01:15", "remaining_time": "7:17:40", "throughput": 2641.47, "total_tokens": 200000}
|
| 24 |
+
{"current_steps": 120, "total_steps": 40000, "loss": 0.2602, "lr": 4.999890810585516e-05, "epoch": 0.5811138014527845, "percentage": 0.3, "elapsed_time": "0:01:18", "remaining_time": "7:17:21", "throughput": 2641.86, "total_tokens": 208608}
|
| 25 |
+
{"current_steps": 125, "total_steps": 40000, "loss": 0.2021, "lr": 4.999881442314206e-05, "epoch": 0.6053268765133172, "percentage": 0.31, "elapsed_time": "0:01:22", "remaining_time": "7:17:03", "throughput": 2642.75, "total_tokens": 217248}
|
| 26 |
+
{"current_steps": 130, "total_steps": 40000, "loss": 0.1822, "lr": 4.9998716885297617e-05, "epoch": 0.6295399515738499, "percentage": 0.33, "elapsed_time": "0:01:25", "remaining_time": "7:16:56", "throughput": 2645.18, "total_tokens": 226112}
|
| 27 |
+
{"current_steps": 135, "total_steps": 40000, "loss": 0.1722, "lr": 4.999861549233688e-05, "epoch": 0.6537530266343826, "percentage": 0.34, "elapsed_time": "0:01:28", "remaining_time": "7:16:33", "throughput": 2645.82, "total_tokens": 234688}
|
| 28 |
+
{"current_steps": 140, "total_steps": 40000, "loss": 0.185, "lr": 4.999851024427548e-05, "epoch": 0.6779661016949152, "percentage": 0.35, "elapsed_time": "0:01:31", "remaining_time": "7:16:07", "throughput": 2644.41, "total_tokens": 243040}
|
| 29 |
+
{"current_steps": 145, "total_steps": 40000, "loss": 0.2301, "lr": 4.999840114112965e-05, "epoch": 0.7021791767554479, "percentage": 0.36, "elapsed_time": "0:01:35", "remaining_time": "7:15:46", "throughput": 2644.75, "total_tokens": 251584}
|
| 30 |
+
{"current_steps": 150, "total_steps": 40000, "loss": 0.2268, "lr": 4.999828818291621e-05, "epoch": 0.7263922518159807, "percentage": 0.38, "elapsed_time": "0:01:38", "remaining_time": "7:15:31", "throughput": 2647.21, "total_tokens": 260384}
|
| 31 |
+
{"current_steps": 155, "total_steps": 40000, "loss": 0.186, "lr": 4.999817136965259e-05, "epoch": 0.7506053268765133, "percentage": 0.39, "elapsed_time": "0:01:41", "remaining_time": "7:14:49", "throughput": 2647.26, "total_tokens": 268672}
|
| 32 |
+
{"current_steps": 160, "total_steps": 40000, "loss": 0.1731, "lr": 4.9998050701356794e-05, "epoch": 0.774818401937046, "percentage": 0.4, "elapsed_time": "0:01:44", "remaining_time": "7:14:24", "throughput": 2648.05, "total_tokens": 277184}
|
| 33 |
+
{"current_steps": 165, "total_steps": 40000, "loss": 0.2249, "lr": 4.999792617804744e-05, "epoch": 0.7990314769975787, "percentage": 0.41, "elapsed_time": "0:01:47", "remaining_time": "7:14:01", "throughput": 2648.92, "total_tokens": 285728}
|
| 34 |
+
{"current_steps": 170, "total_steps": 40000, "loss": 0.2148, "lr": 4.9997797799743724e-05, "epoch": 0.8232445520581114, "percentage": 0.43, "elapsed_time": "0:01:51", "remaining_time": "7:13:51", "throughput": 2649.68, "total_tokens": 294400}
|
| 35 |
+
{"current_steps": 175, "total_steps": 40000, "loss": 0.2285, "lr": 4.999766556646545e-05, "epoch": 0.847457627118644, "percentage": 0.44, "elapsed_time": "0:01:54", "remaining_time": "7:13:52", "throughput": 2652.21, "total_tokens": 303392}
|
| 36 |
+
{"current_steps": 180, "total_steps": 40000, "loss": 0.1865, "lr": 4.9997529478232996e-05, "epoch": 0.8716707021791767, "percentage": 0.45, "elapsed_time": "0:01:57", "remaining_time": "7:13:40", "throughput": 2654.46, "total_tokens": 312224}
|
| 37 |
+
{"current_steps": 185, "total_steps": 40000, "loss": 0.1996, "lr": 4.9997389535067365e-05, "epoch": 0.8958837772397095, "percentage": 0.46, "elapsed_time": "0:02:00", "remaining_time": "7:13:42", "throughput": 2655.53, "total_tokens": 321088}
|
| 38 |
+
{"current_steps": 190, "total_steps": 40000, "loss": 0.193, "lr": 4.999724573699012e-05, "epoch": 0.9200968523002422, "percentage": 0.47, "elapsed_time": "0:02:04", "remaining_time": "7:13:34", "throughput": 2655.97, "total_tokens": 329760}
|
| 39 |
+
{"current_steps": 195, "total_steps": 40000, "loss": 0.1283, "lr": 4.9997098084023457e-05, "epoch": 0.9443099273607748, "percentage": 0.49, "elapsed_time": "0:02:07", "remaining_time": "7:13:29", "throughput": 2657.09, "total_tokens": 338560}
|
| 40 |
+
{"current_steps": 200, "total_steps": 40000, "loss": 0.2244, "lr": 4.999694657619013e-05, "epoch": 0.9685230024213075, "percentage": 0.5, "elapsed_time": "0:02:10", "remaining_time": "7:13:10", "throughput": 2655.47, "total_tokens": 346816}
|
| 41 |
+
{"current_steps": 200, "total_steps": 40000, "eval_loss": 0.19615894556045532, "epoch": 0.9685230024213075, "percentage": 0.5, "elapsed_time": "0:02:15", "remaining_time": "7:29:23", "throughput": 2559.58, "total_tokens": 346816}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c51f68f40aba2ecabe01abb70096bb98444c4ff44fb98ec08c002e798b31611f
|
| 3 |
+
size 5752
|