Hugging Face's logo

wjldw
/
ToolPRM-Base-synthesis

Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
wjldw commited on
Commit
fd2a6cb
·
verified ·
1 Parent(s): 8eaf820

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. all_results.json +5 -5
  2. checkpoint-78/global_step78/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
  3. checkpoint-78/global_step78/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +1 -1
  4. checkpoint-78/global_step78/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +1 -1
  5. checkpoint-78/global_step78/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +1 -1
  6. checkpoint-78/global_step78/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +1 -1
  7. checkpoint-78/global_step78/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +1 -1
  8. checkpoint-78/global_step78/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +1 -1
  9. checkpoint-78/global_step78/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +1 -1
  10. checkpoint-78/model-00001-of-00002.safetensors +1 -1
  11. checkpoint-78/model-00002-of-00002.safetensors +1 -1
  12. checkpoint-78/trainer_state.json +15 -15
  13. checkpoint-78/training_args.bin +1 -1
  14. model-00001-of-00002.safetensors +1 -1
  15. model-00002-of-00002.safetensors +1 -1
  16. train_results.json +5 -5
  17. trainer_log.jsonl +8 -8
  18. trainer_state.json +20 -20
  19. training_args.bin +1 -1
  20. training_loss.png +0 -0
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
- "total_flos": 1988394614784.0,
4
- "train_loss": 0.6909363798413557,
5
- "train_runtime": 181.9403,
6
- "train_samples_per_second": 13.521,
7
- "train_steps_per_second": 0.429
8
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "total_flos": 8891638874112.0,
4
+ "train_loss": 0.6841755338828079,
5
+ "train_runtime": 566.7608,
6
+ "train_samples_per_second": 4.34,
7
+ "train_steps_per_second": 0.138
8
  }
checkpoint-78/global_step78/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6937f37bda54a324a958a515becbb83bf27334feb6a6323d68b1e5626b9193d7
3
  size 6033707356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:184e4986f4d6a216258a53aab190d914b0b2208f8fa3397dbba729e9b6b15e89
3
  size 6033707356
checkpoint-78/global_step78/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b3af4d2484b956fed3860b0d9acf3751c9812b8b5158ada7889549188b6058c
3
  size 6033707356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf18453486bd4a85446711aefa6279d67e74465ef47b40846078d9204bbae849
3
  size 6033707356
checkpoint-78/global_step78/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4153954a5644e70b8cf9494f7e60ed35058cb766246c5ae29be34ea4d94c1d6d
3
  size 6033707356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca25c306ad931d47e25541713d298a68db44b48ba99c3a105e5857f1fb22d94
3
  size 6033707356
checkpoint-78/global_step78/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:260acf90b4e2d4c8618d551100724e0c4d1cb64a48496507cec2f67bf5bf533e
3
  size 6033707356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32bb1734c8304181f4de867e8d8f4b9275b91edeca1f4288e1f59e26a78b2e3b
3
  size 6033707356
checkpoint-78/global_step78/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0b46a2d219d3ee740b8388a047f1c1118ff179ca4406bf00aea203dd4d8b8af
3
  size 6033707356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0b80a2ca071c9004554438ebaf31ed5767874efbbd403b91972dc063c4e939
3
  size 6033707356
checkpoint-78/global_step78/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad60efe2b170b752916c5a03098bca0dd5418f02ae8da978707872d24128d650
3
  size 6033707356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28cd0ba9014538f8328198b9b12323eb6ee427863784637bd968e827279e0e4a
3
  size 6033707356
checkpoint-78/global_step78/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ece60eddb0276300c3623a852182ec688d94fbfb7ed8070b446acce9b018f22a
3
  size 6033707356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0636823e64519edc43d6e0f7e10d0f8a43157b06bf194baa526783ee52d7ab2
3
  size 6033707356
checkpoint-78/global_step78/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1a6f8bd6d25d1de1275076242710b8997cc014fef4aa66561775c83a44dc48b
3
  size 6033707356
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e95d2e8bfd0c9da21dcdbadaca4883194644caee41b883de7b738a16977cf3e
3
  size 6033707356
checkpoint-78/model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b18bbadaf9e4acf048e7be97366d7f86662f554d5753da89b65cdca030b7d628
3
  size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a2ae9a5d1ff987bf89548f0d22f709c331fdac40ebb9eb52972e7826a19fb2
3
  size 4967215360
checkpoint-78/model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbf28d9d320b1a7c193a1bb243940e13f68fbacff5bf7ae12d461ee29881db7b
3
  size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53b5ee7a0093d7ae92c55e7501d84b674a4f5a0d9f7721eb2bb88ea8c44ef7a
3
  size 3077766632
checkpoint-78/trainer_state.json CHANGED
@@ -11,51 +11,51 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.2564102564102564,
14
- "grad_norm": 21.914043415781826,
15
  "learning_rate": 9.994965332706574e-06,
16
- "loss": 5.3228,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.5128205128205128,
21
- "grad_norm": 2.953621864282477,
22
  "learning_rate": 9.40297765928369e-06,
23
- "loss": 0.0345,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 0.7692307692307693,
28
- "grad_norm": 1.9195026229232641,
29
  "learning_rate": 7.938926261462366e-06,
30
- "loss": 0.0178,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 1.0256410256410255,
35
- "grad_norm": 0.01920738794620276,
36
  "learning_rate": 5.892784473993184e-06,
37
- "loss": 0.0077,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 1.282051282051282,
42
- "grad_norm": 0.2122194219852602,
43
  "learning_rate": 3.669815772166625e-06,
44
- "loss": 0.0001,
45
  "step": 50
46
  },
47
  {
48
  "epoch": 1.5384615384615383,
49
- "grad_norm": 0.004738746740406469,
50
  "learning_rate": 1.7103063703014372e-06,
51
- "loss": 0.0044,
52
  "step": 60
53
  },
54
  {
55
  "epoch": 1.7948717948717947,
56
- "grad_norm": 1.2709828736584587,
57
  "learning_rate": 4.0236113724274716e-07,
58
- "loss": 0.0019,
59
  "step": 70
60
  }
61
  ],
@@ -76,7 +76,7 @@
76
  "attributes": {}
77
  }
78
  },
79
- "total_flos": 1988394614784.0,
80
  "train_batch_size": 4,
81
  "trial_name": null,
82
  "trial_params": null
 
11
  "log_history": [
12
  {
13
  "epoch": 0.2564102564102564,
14
+ "grad_norm": 5.721946298566637,
15
  "learning_rate": 9.994965332706574e-06,
16
+ "loss": 5.2582,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.5128205128205128,
21
+ "grad_norm": 2.8109843358784836,
22
  "learning_rate": 9.40297765928369e-06,
23
+ "loss": 0.0252,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 0.7692307692307693,
28
+ "grad_norm": 0.23206407267268572,
29
  "learning_rate": 7.938926261462366e-06,
30
+ "loss": 0.0201,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 1.0256410256410255,
35
+ "grad_norm": 0.45846925644305964,
36
  "learning_rate": 5.892784473993184e-06,
37
+ "loss": 0.0238,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 1.282051282051282,
42
+ "grad_norm": 0.04034621588048863,
43
  "learning_rate": 3.669815772166625e-06,
44
+ "loss": 0.0046,
45
  "step": 50
46
  },
47
  {
48
  "epoch": 1.5384615384615383,
49
+ "grad_norm": 0.005579535835401499,
50
  "learning_rate": 1.7103063703014372e-06,
51
+ "loss": 0.002,
52
  "step": 60
53
  },
54
  {
55
  "epoch": 1.7948717948717947,
56
+ "grad_norm": 0.027412739220486586,
57
  "learning_rate": 4.0236113724274716e-07,
58
+ "loss": 0.0027,
59
  "step": 70
60
  }
61
  ],
 
76
  "attributes": {}
77
  }
78
  },
79
+ "total_flos": 8891638874112.0,
80
  "train_batch_size": 4,
81
  "trial_name": null,
82
  "trial_params": null
checkpoint-78/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:842224a59e70decc42b5cee79304c5d44d4029e91ee84bf94477e9fd5673687b
3
  size 7672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf1eed967cab139c7e4b86ed98bc67c5f054b3346c42e2c103b211d5443d89b2
3
  size 7672
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b18bbadaf9e4acf048e7be97366d7f86662f554d5753da89b65cdca030b7d628
3
  size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a2ae9a5d1ff987bf89548f0d22f709c331fdac40ebb9eb52972e7826a19fb2
3
  size 4967215360
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbf28d9d320b1a7c193a1bb243940e13f68fbacff5bf7ae12d461ee29881db7b
3
  size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b53b5ee7a0093d7ae92c55e7501d84b674a4f5a0d9f7721eb2bb88ea8c44ef7a
3
  size 3077766632
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
- "total_flos": 1988394614784.0,
4
- "train_loss": 0.6909363798413557,
5
- "train_runtime": 181.9403,
6
- "train_samples_per_second": 13.521,
7
- "train_steps_per_second": 0.429
8
  }
 
1
  {
2
  "epoch": 2.0,
3
+ "total_flos": 8891638874112.0,
4
+ "train_loss": 0.6841755338828079,
5
+ "train_runtime": 566.7608,
6
+ "train_samples_per_second": 4.34,
7
+ "train_steps_per_second": 0.138
8
  }
trainer_log.jsonl CHANGED
@@ -1,8 +1,8 @@
1
- {"current_steps": 10, "total_steps": 78, "loss": 5.3228, "lr": 9.994965332706574e-06, "epoch": 0.2564102564102564, "percentage": 12.82, "elapsed_time": "0:00:27", "remaining_time": "0:03:06"}
2
- {"current_steps": 20, "total_steps": 78, "loss": 0.0345, "lr": 9.40297765928369e-06, "epoch": 0.5128205128205128, "percentage": 25.64, "elapsed_time": "0:00:47", "remaining_time": "0:02:17"}
3
- {"current_steps": 30, "total_steps": 78, "loss": 0.0178, "lr": 7.938926261462366e-06, "epoch": 0.7692307692307693, "percentage": 38.46, "elapsed_time": "0:01:05", "remaining_time": "0:01:44"}
4
- {"current_steps": 40, "total_steps": 78, "loss": 0.0077, "lr": 5.892784473993184e-06, "epoch": 1.0256410256410255, "percentage": 51.28, "elapsed_time": "0:01:25", "remaining_time": "0:01:21"}
5
- {"current_steps": 50, "total_steps": 78, "loss": 0.0001, "lr": 3.669815772166625e-06, "epoch": 1.282051282051282, "percentage": 64.1, "elapsed_time": "0:01:45", "remaining_time": "0:00:58"}
6
- {"current_steps": 60, "total_steps": 78, "loss": 0.0044, "lr": 1.7103063703014372e-06, "epoch": 1.5384615384615383, "percentage": 76.92, "elapsed_time": "0:02:02", "remaining_time": "0:00:36"}
7
- {"current_steps": 70, "total_steps": 78, "loss": 0.0019, "lr": 4.0236113724274716e-07, "epoch": 1.7948717948717947, "percentage": 89.74, "elapsed_time": "0:02:21", "remaining_time": "0:00:16"}
8
- {"current_steps": 78, "total_steps": 78, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:03:01", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 10, "total_steps": 78, "loss": 5.2582, "lr": 9.994965332706574e-06, "epoch": 0.2564102564102564, "percentage": 12.82, "elapsed_time": "0:01:17", "remaining_time": "0:08:46"}
2
+ {"current_steps": 20, "total_steps": 78, "loss": 0.0252, "lr": 9.40297765928369e-06, "epoch": 0.5128205128205128, "percentage": 25.64, "elapsed_time": "0:02:23", "remaining_time": "0:06:56"}
3
+ {"current_steps": 30, "total_steps": 78, "loss": 0.0201, "lr": 7.938926261462366e-06, "epoch": 0.7692307692307693, "percentage": 38.46, "elapsed_time": "0:03:31", "remaining_time": "0:05:38"}
4
+ {"current_steps": 40, "total_steps": 78, "loss": 0.0238, "lr": 5.892784473993184e-06, "epoch": 1.0256410256410255, "percentage": 51.28, "elapsed_time": "0:04:39", "remaining_time": "0:04:25"}
5
+ {"current_steps": 50, "total_steps": 78, "loss": 0.0046, "lr": 3.669815772166625e-06, "epoch": 1.282051282051282, "percentage": 64.1, "elapsed_time": "0:05:47", "remaining_time": "0:03:14"}
6
+ {"current_steps": 60, "total_steps": 78, "loss": 0.002, "lr": 1.7103063703014372e-06, "epoch": 1.5384615384615383, "percentage": 76.92, "elapsed_time": "0:06:53", "remaining_time": "0:02:04"}
7
+ {"current_steps": 70, "total_steps": 78, "loss": 0.0027, "lr": 4.0236113724274716e-07, "epoch": 1.7948717948717947, "percentage": 89.74, "elapsed_time": "0:08:01", "remaining_time": "0:00:55"}
8
+ {"current_steps": 78, "total_steps": 78, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:09:26", "remaining_time": "0:00:00"}
trainer_state.json CHANGED
@@ -11,61 +11,61 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.2564102564102564,
14
- "grad_norm": 21.914043415781826,
15
  "learning_rate": 9.994965332706574e-06,
16
- "loss": 5.3228,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.5128205128205128,
21
- "grad_norm": 2.953621864282477,
22
  "learning_rate": 9.40297765928369e-06,
23
- "loss": 0.0345,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 0.7692307692307693,
28
- "grad_norm": 1.9195026229232641,
29
  "learning_rate": 7.938926261462366e-06,
30
- "loss": 0.0178,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 1.0256410256410255,
35
- "grad_norm": 0.01920738794620276,
36
  "learning_rate": 5.892784473993184e-06,
37
- "loss": 0.0077,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 1.282051282051282,
42
- "grad_norm": 0.2122194219852602,
43
  "learning_rate": 3.669815772166625e-06,
44
- "loss": 0.0001,
45
  "step": 50
46
  },
47
  {
48
  "epoch": 1.5384615384615383,
49
- "grad_norm": 0.004738746740406469,
50
  "learning_rate": 1.7103063703014372e-06,
51
- "loss": 0.0044,
52
  "step": 60
53
  },
54
  {
55
  "epoch": 1.7948717948717947,
56
- "grad_norm": 1.2709828736584587,
57
  "learning_rate": 4.0236113724274716e-07,
58
- "loss": 0.0019,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 2.0,
63
  "step": 78,
64
- "total_flos": 1988394614784.0,
65
- "train_loss": 0.6909363798413557,
66
- "train_runtime": 181.9403,
67
- "train_samples_per_second": 13.521,
68
- "train_steps_per_second": 0.429
69
  }
70
  ],
71
  "logging_steps": 10,
@@ -85,7 +85,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1988394614784.0,
89
  "train_batch_size": 4,
90
  "trial_name": null,
91
  "trial_params": null
 
11
  "log_history": [
12
  {
13
  "epoch": 0.2564102564102564,
14
+ "grad_norm": 5.721946298566637,
15
  "learning_rate": 9.994965332706574e-06,
16
+ "loss": 5.2582,
17
  "step": 10
18
  },
19
  {
20
  "epoch": 0.5128205128205128,
21
+ "grad_norm": 2.8109843358784836,
22
  "learning_rate": 9.40297765928369e-06,
23
+ "loss": 0.0252,
24
  "step": 20
25
  },
26
  {
27
  "epoch": 0.7692307692307693,
28
+ "grad_norm": 0.23206407267268572,
29
  "learning_rate": 7.938926261462366e-06,
30
+ "loss": 0.0201,
31
  "step": 30
32
  },
33
  {
34
  "epoch": 1.0256410256410255,
35
+ "grad_norm": 0.45846925644305964,
36
  "learning_rate": 5.892784473993184e-06,
37
+ "loss": 0.0238,
38
  "step": 40
39
  },
40
  {
41
  "epoch": 1.282051282051282,
42
+ "grad_norm": 0.04034621588048863,
43
  "learning_rate": 3.669815772166625e-06,
44
+ "loss": 0.0046,
45
  "step": 50
46
  },
47
  {
48
  "epoch": 1.5384615384615383,
49
+ "grad_norm": 0.005579535835401499,
50
  "learning_rate": 1.7103063703014372e-06,
51
+ "loss": 0.002,
52
  "step": 60
53
  },
54
  {
55
  "epoch": 1.7948717948717947,
56
+ "grad_norm": 0.027412739220486586,
57
  "learning_rate": 4.0236113724274716e-07,
58
+ "loss": 0.0027,
59
  "step": 70
60
  },
61
  {
62
  "epoch": 2.0,
63
  "step": 78,
64
+ "total_flos": 8891638874112.0,
65
+ "train_loss": 0.6841755338828079,
66
+ "train_runtime": 566.7608,
67
+ "train_samples_per_second": 4.34,
68
+ "train_steps_per_second": 0.138
69
  }
70
  ],
71
  "logging_steps": 10,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 8891638874112.0,
89
  "train_batch_size": 4,
90
  "trial_name": null,
91
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:842224a59e70decc42b5cee79304c5d44d4029e91ee84bf94477e9fd5673687b
3
  size 7672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf1eed967cab139c7e4b86ed98bc67c5f054b3346c42e2c103b211d5443d89b2
3
  size 7672
training_loss.png CHANGED