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 sha256:6f77d46f1185be2c8424f63e512e93194e778ddf72bed9e35f179c15d84373f7
|
| 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": 7.331, "lr": 0.29999999259779675, "epoch": 0.08849557522123894, "percentage": 0.01, "elapsed_time": "0:00:02", "remaining_time": "5:20:24", "throughput": 1271.53, "total_tokens": 3056}
|
| 2 |
+
{"current_steps": 10, "total_steps": 40000, "loss": 7.6806, "lr": 0.29999996252634736, "epoch": 0.17699115044247787, "percentage": 0.03, "elapsed_time": "0:00:03", "remaining_time": "4:02:07", "throughput": 1726.5, "total_tokens": 6272}
|
| 3 |
+
{"current_steps": 15, "total_steps": 40000, "loss": 3.2863, "lr": 0.2999999093230187, "epoch": 0.26548672566371684, "percentage": 0.04, "elapsed_time": "0:00:04", "remaining_time": "3:34:29", "throughput": 1922.14, "total_tokens": 9280}
|
| 4 |
+
{"current_steps": 20, "total_steps": 40000, "loss": 1.5539, "lr": 0.299999832987819, "epoch": 0.35398230088495575, "percentage": 0.05, "elapsed_time": "0:00:06", "remaining_time": "3:24:03", "throughput": 2108.05, "total_tokens": 12912}
|
| 5 |
+
{"current_steps": 25, "total_steps": 40000, "loss": 1.5194, "lr": 0.29999973352076004, "epoch": 0.4424778761061947, "percentage": 0.06, "elapsed_time": "0:00:07", "remaining_time": "3:15:47", "throughput": 2193.02, "total_tokens": 16112}
|
| 6 |
+
{"current_steps": 30, "total_steps": 40000, "loss": 2.1306, "lr": 0.2999996109218572, "epoch": 0.5309734513274337, "percentage": 0.07, "elapsed_time": "0:00:08", "remaining_time": "3:08:52", "throughput": 2187.68, "total_tokens": 18608}
|
| 7 |
+
{"current_steps": 35, "total_steps": 40000, "loss": 1.8156, "lr": 0.2999994651911293, "epoch": 0.6194690265486725, "percentage": 0.09, "elapsed_time": "0:00:09", "remaining_time": "3:06:27", "throughput": 2252.03, "total_tokens": 22064}
|
| 8 |
+
{"current_steps": 40, "total_steps": 40000, "loss": 0.517, "lr": 0.2999992963285989, "epoch": 0.7079646017699115, "percentage": 0.1, "elapsed_time": "0:00:11", "remaining_time": "3:03:20", "throughput": 2271.17, "total_tokens": 25008}
|
| 9 |
+
{"current_steps": 45, "total_steps": 40000, "loss": 0.7009, "lr": 0.29999910433429194, "epoch": 0.7964601769911505, "percentage": 0.11, "elapsed_time": "0:00:12", "remaining_time": "2:59:44", "throughput": 2272.21, "total_tokens": 27600}
|
| 10 |
+
{"current_steps": 50, "total_steps": 40000, "loss": 0.5814, "lr": 0.29999888920823814, "epoch": 0.8849557522123894, "percentage": 0.12, "elapsed_time": "0:00:13", "remaining_time": "2:57:05", "throughput": 2272.76, "total_tokens": 30224}
|
| 11 |
+
{"current_steps": 55, "total_steps": 40000, "loss": 0.4263, "lr": 0.29999865095047057, "epoch": 0.9734513274336283, "percentage": 0.14, "elapsed_time": "0:00:14", "remaining_time": "2:54:19", "throughput": 2259.8, "total_tokens": 32544}
|
| 12 |
+
{"current_steps": 60, "total_steps": 40000, "loss": 0.323, "lr": 0.29999838956102604, "epoch": 1.0530973451327434, "percentage": 0.15, "elapsed_time": "0:00:15", "remaining_time": "2:55:10", "throughput": 2229.33, "total_tokens": 35200}
|
| 13 |
+
{"current_steps": 65, "total_steps": 40000, "loss": 0.3269, "lr": 0.29999810503994484, "epoch": 1.1415929203539823, "percentage": 0.16, "elapsed_time": "0:00:16", "remaining_time": "2:53:52", "throughput": 2250.03, "total_tokens": 38208}
|
| 14 |
+
{"current_steps": 70, "total_steps": 40000, "loss": 0.5249, "lr": 0.29999779738727084, "epoch": 1.2300884955752212, "percentage": 0.18, "elapsed_time": "0:00:18", "remaining_time": "2:52:27", "throughput": 2255.37, "total_tokens": 40912}
|
| 15 |
+
{"current_steps": 75, "total_steps": 40000, "loss": 0.3923, "lr": 0.29999746660305154, "epoch": 1.3185840707964602, "percentage": 0.19, "elapsed_time": "0:00:19", "remaining_time": "2:52:05", "throughput": 2278.33, "total_tokens": 44192}
|
| 16 |
+
{"current_steps": 80, "total_steps": 40000, "loss": 0.3627, "lr": 0.2999971126873379, "epoch": 1.407079646017699, "percentage": 0.2, "elapsed_time": "0:00:20", "remaining_time": "2:51:07", "throughput": 2285.38, "total_tokens": 47024}
|
| 17 |
+
{"current_steps": 85, "total_steps": 40000, "loss": 0.283, "lr": 0.2999967356401845, "epoch": 1.495575221238938, "percentage": 0.21, "elapsed_time": "0:00:21", "remaining_time": "2:50:59", "throughput": 2299.65, "total_tokens": 50240}
|
| 18 |
+
{"current_steps": 90, "total_steps": 40000, "loss": 0.5342, "lr": 0.29999633546164944, "epoch": 1.584070796460177, "percentage": 0.22, "elapsed_time": "0:00:22", "remaining_time": "2:49:52", "throughput": 2293.73, "total_tokens": 52720}
|
| 19 |
+
{"current_steps": 95, "total_steps": 40000, "loss": 0.5582, "lr": 0.29999591215179444, "epoch": 1.672566371681416, "percentage": 0.24, "elapsed_time": "0:00:24", "remaining_time": "2:49:34", "throughput": 2307.23, "total_tokens": 55888}
|
| 20 |
+
{"current_steps": 100, "total_steps": 40000, "loss": 0.3398, "lr": 0.2999954657106849, "epoch": 1.7610619469026547, "percentage": 0.25, "elapsed_time": "0:00:25", "remaining_time": "2:48:48", "throughput": 2312.65, "total_tokens": 58704}
|
| 21 |
+
{"current_steps": 105, "total_steps": 40000, "loss": 0.335, "lr": 0.2999949961383896, "epoch": 1.8495575221238938, "percentage": 0.26, "elapsed_time": "0:00:26", "remaining_time": "2:48:15", "throughput": 2316.63, "total_tokens": 61552}
|
| 22 |
+
{"current_steps": 110, "total_steps": 40000, "loss": 0.3014, "lr": 0.2999945034349809, "epoch": 1.9380530973451329, "percentage": 0.27, "elapsed_time": "0:00:27", "remaining_time": "2:47:34", "throughput": 2322.12, "total_tokens": 64384}
|
| 23 |
+
{"current_steps": 115, "total_steps": 40000, "loss": 0.2466, "lr": 0.2999939876005348, "epoch": 2.017699115044248, "percentage": 0.29, "elapsed_time": "0:00:29", "remaining_time": "2:48:02", "throughput": 2289.87, "total_tokens": 66568}
|
| 24 |
+
{"current_steps": 120, "total_steps": 40000, "loss": 0.2161, "lr": 0.29999344863513094, "epoch": 2.106194690265487, "percentage": 0.3, "elapsed_time": "0:00:30", "remaining_time": "2:47:52", "throughput": 2296.02, "total_tokens": 69592}
|
| 25 |
+
{"current_steps": 125, "total_steps": 40000, "loss": 0.2527, "lr": 0.2999928865388523, "epoch": 2.1946902654867255, "percentage": 0.31, "elapsed_time": "0:00:31", "remaining_time": "2:47:20", "throughput": 2296.52, "total_tokens": 72280}
|
| 26 |
+
{"current_steps": 130, "total_steps": 40000, "loss": 0.263, "lr": 0.29999230131178567, "epoch": 2.2831858407079646, "percentage": 0.33, "elapsed_time": "0:00:32", "remaining_time": "2:47:05", "throughput": 2305.57, "total_tokens": 75368}
|
| 27 |
+
{"current_steps": 135, "total_steps": 40000, "loss": 0.4388, "lr": 0.2999916929540212, "epoch": 2.3716814159292037, "percentage": 0.34, "elapsed_time": "0:00:33", "remaining_time": "2:46:34", "throughput": 2302.81, "total_tokens": 77944}
|
| 28 |
+
{"current_steps": 140, "total_steps": 40000, "loss": 0.3694, "lr": 0.29999106146565285, "epoch": 2.4601769911504423, "percentage": 0.35, "elapsed_time": "0:00:35", "remaining_time": "2:46:16", "throughput": 2309.44, "total_tokens": 80920}
|
| 29 |
+
{"current_steps": 145, "total_steps": 40000, "loss": 0.4248, "lr": 0.29999040684677786, "epoch": 2.5486725663716814, "percentage": 0.36, "elapsed_time": "0:00:36", "remaining_time": "2:45:59", "throughput": 2317.1, "total_tokens": 83960}
|
| 30 |
+
{"current_steps": 150, "total_steps": 40000, "loss": 0.2987, "lr": 0.2999897290974972, "epoch": 2.6371681415929205, "percentage": 0.38, "elapsed_time": "0:00:37", "remaining_time": "2:45:36", "throughput": 2320.45, "total_tokens": 86792}
|
| 31 |
+
{"current_steps": 155, "total_steps": 40000, "loss": 0.3413, "lr": 0.2999890282179155, "epoch": 2.725663716814159, "percentage": 0.39, "elapsed_time": "0:00:38", "remaining_time": "2:45:43", "throughput": 2338.15, "total_tokens": 90440}
|
| 32 |
+
{"current_steps": 160, "total_steps": 40000, "loss": 0.3188, "lr": 0.29998830420814077, "epoch": 2.814159292035398, "percentage": 0.4, "elapsed_time": "0:00:39", "remaining_time": "2:45:30", "throughput": 2345.25, "total_tokens": 93528}
|
| 33 |
+
{"current_steps": 165, "total_steps": 40000, "loss": 0.3329, "lr": 0.2999875570682846, "epoch": 2.9026548672566372, "percentage": 0.41, "elapsed_time": "0:00:41", "remaining_time": "2:45:06", "throughput": 2340.41, "total_tokens": 96040}
|
| 34 |
+
{"current_steps": 170, "total_steps": 40000, "loss": 0.2213, "lr": 0.2999867867984623, "epoch": 2.991150442477876, "percentage": 0.43, "elapsed_time": "0:00:42", "remaining_time": "2:44:48", "throughput": 2345.75, "total_tokens": 99000}
|
| 35 |
+
{"current_steps": 175, "total_steps": 40000, "loss": 0.1988, "lr": 0.29998599339879267, "epoch": 3.0707964601769913, "percentage": 0.44, "elapsed_time": "0:00:43", "remaining_time": "2:45:19", "throughput": 2328.5, "total_tokens": 101496}
|
| 36 |
+
{"current_steps": 180, "total_steps": 40000, "loss": 0.3418, "lr": 0.29998517686939796, "epoch": 3.15929203539823, "percentage": 0.45, "elapsed_time": "0:00:44", "remaining_time": "2:45:07", "throughput": 2330.96, "total_tokens": 104392}
|
| 37 |
+
{"current_steps": 185, "total_steps": 40000, "loss": 0.2321, "lr": 0.29998433721040413, "epoch": 3.247787610619469, "percentage": 0.46, "elapsed_time": "0:00:45", "remaining_time": "2:44:52", "throughput": 2332.06, "total_tokens": 107192}
|
| 38 |
+
{"current_steps": 190, "total_steps": 40000, "loss": 0.2531, "lr": 0.29998347442194073, "epoch": 3.336283185840708, "percentage": 0.47, "elapsed_time": "0:00:47", "remaining_time": "2:44:42", "throughput": 2339.08, "total_tokens": 110328}
|
| 39 |
+
{"current_steps": 195, "total_steps": 40000, "loss": 0.2629, "lr": 0.2999825885041407, "epoch": 3.4247787610619467, "percentage": 0.49, "elapsed_time": "0:00:48", "remaining_time": "2:44:30", "throughput": 2343.53, "total_tokens": 113320}
|
| 40 |
+
{"current_steps": 200, "total_steps": 40000, "loss": 0.4055, "lr": 0.29998167945714077, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:00:49", "remaining_time": "2:44:22", "throughput": 2345.58, "total_tokens": 116248}
|
| 41 |
+
{"current_steps": 200, "total_steps": 40000, "eval_loss": 0.24539066851139069, "epoch": 3.5132743362831858, "percentage": 0.5, "elapsed_time": "0:00:50", "remaining_time": "2:47:40", "throughput": 2299.43, "total_tokens": 116248}
|
| 42 |
+
{"current_steps": 205, "total_steps": 40000, "loss": 0.2608, "lr": 0.2999807472810811, "epoch": 3.601769911504425, "percentage": 0.51, "elapsed_time": "0:00:52", "remaining_time": "2:49:17", "throughput": 2283.06, "total_tokens": 119464}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04412cbbd9dd3f318fcdfe64cd888c5fdad63fc2067f3ddef980b4dea3dc417a
|
| 3 |
+
size 5752
|