Mel-Iza0 commited on
Commit
f7adc09
1 Parent(s): 162cc33

Upload folder using huggingface_hub

Browse files
checkpoint-10/adapter_config.json CHANGED
@@ -19,9 +19,9 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
- "k_proj",
24
  "v_proj",
 
 
25
  "o_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "v_proj",
23
+ "k_proj",
24
+ "q_proj",
25
  "o_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
checkpoint-10/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a3e0cdae368d14a843151822c64d75b9e64eabba537d101b909316145d64f25
3
  size 436242776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:966422cb45a8382bac17cf41216e3afe2053cf607f2da94a632139fc2d0b8ba1
3
  size 436242776
checkpoint-10/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07fdb544e9a22a371a5d8df82da422560206b79b40d84a212a74ea56b50f59fa
3
  size 872568314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c39dfe27d7776c478e77eeae50c2b4248bca4d11a6ea01c21c5e11a9171540f
3
  size 872568314
checkpoint-10/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec5bc6d58edfb094654e0fd7d8830f6528f86d2a2c0b08173da1fe23f3fac2ef
3
- size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aacc211f04d2987b22d9e98352791900880485b00e7ba542532f0ecec3bcdfef
3
+ size 15024
checkpoint-10/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1386ecdf853bc6f64d03fe0f70a1791d948a0933fed4c2a20ca0f9ecc9b5ac63
3
- size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8bd5fb280d3a476b13d48a02b0eab8ef08f847c3cfef1b578e294c9487bfbef
3
+ size 15024
checkpoint-10/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5cafbb94312025b0d3e9a10373eb77e4d2cfa96c533075b98d8adca5f98bda2
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90bdd80721c9b7e7e4d190530444466ac19797a0256ba7d2392a13f02d9dfac0
3
  size 15024
checkpoint-10/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5531210de2190ee016328d2c16999d7dcfc5a2aede25bfe7c7b62f0ac32df14
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:180162a870c99e232cbac92cffd2c1be442b364558d2437654326dbfd6a2c018
3
  size 15024
checkpoint-10/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.6367942690849304,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-10",
4
- "epoch": 0.04956629491945477,
5
  "eval_steps": 10,
6
  "global_step": 10,
7
  "is_hyper_param_search": false,
@@ -9,11 +9,11 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.05,
13
- "eval_loss": 0.6367942690849304,
14
- "eval_runtime": 180.8957,
15
- "eval_samples_per_second": 15.849,
16
- "eval_steps_per_second": 0.995,
17
  "step": 10
18
  }
19
  ],
@@ -22,7 +22,7 @@
22
  "num_input_tokens_seen": 0,
23
  "num_train_epochs": 1,
24
  "save_steps": 10,
25
- "total_flos": 4.493525352080998e+16,
26
  "train_batch_size": 16,
27
  "trial_name": null,
28
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6292536854743958,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-10",
4
+ "epoch": 0.09900990099009901,
5
  "eval_steps": 10,
6
  "global_step": 10,
7
  "is_hyper_param_search": false,
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.1,
13
+ "eval_loss": 0.6292536854743958,
14
+ "eval_runtime": 93.2576,
15
+ "eval_samples_per_second": 30.743,
16
+ "eval_steps_per_second": 0.965,
17
  "step": 10
18
  }
19
  ],
 
22
  "num_input_tokens_seen": 0,
23
  "num_train_epochs": 1,
24
  "save_steps": 10,
25
+ "total_flos": 9.033558328030003e+16,
26
  "train_batch_size": 16,
27
  "trial_name": null,
28
  "trial_params": null
checkpoint-10/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daf4ca86cd3cb3688a488e999435cb5aec8a4b0702902c7de81df751b2180e05
3
  size 5176
checkpoint-70/adapter_config.json CHANGED
@@ -20,9 +20,9 @@
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
23
- "k_proj",
24
  "v_proj",
25
- "o_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
 
23
  "v_proj",
24
+ "o_proj",
25
+ "k_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
checkpoint-70/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfb912af6b1796046b92cd31a140d407273ff753ac7f3269fc3c5f3185cb84e1
3
  size 436242776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3729ade0578702d582ba4201d2056d525c6b98445fc9f287499aa8cc4a04ad0f
3
  size 436242776
checkpoint-70/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631ee3323927506f442194f35db41e1ecdfb11bea1ce0e91876dfd94f7df30c1
3
  size 872568314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f41106fec66c8da66955717a5c0e57087dbb2ce1e9c2786539e9d14f13dba082
3
  size 872568314
checkpoint-70/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7a0a43eb1da4e2bdacd5b9613bc246aef81888090db42765afb6f369c67c4c1
3
- size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f23d434a5adf472af32d0d067bd6c7196c5fada3cf7bbec69afdf226737ae9c
3
+ size 15024
checkpoint-70/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90cb909835d393126c788ffdccbb0e802fe522bcd647fc16615a348d6c39cfd4
3
- size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8cd675fa29ceb7104e041bb8b6f813a24babb71dc2874373344d885230ca229
3
+ size 15024
checkpoint-70/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74915e0aef978c84c56eee8bed06ba18d446da4dd1125eda8fbb469b255811be
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a45b3b845e6140514d22eb89d3d82950a7efd6b6e0c772b6f3e23d8289d822fd
3
  size 1000
checkpoint-70/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.39848339557647705,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-70",
4
- "epoch": 0.3469640644361834,
5
  "eval_steps": 10,
6
  "global_step": 70,
7
  "is_hyper_param_search": false,
@@ -9,80 +9,80 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.05,
13
- "eval_loss": 0.6367942690849304,
14
- "eval_runtime": 180.8957,
15
- "eval_samples_per_second": 15.849,
16
- "eval_steps_per_second": 0.995,
17
  "step": 10
18
  },
19
  {
20
- "epoch": 0.1,
21
- "grad_norm": 0.34346863627433777,
22
- "learning_rate": 0.00019510565162951537,
23
- "loss": 0.9774,
24
  "step": 20
25
  },
26
  {
27
- "epoch": 0.1,
28
- "eval_loss": 0.48089343309402466,
29
- "eval_runtime": 180.8882,
30
- "eval_samples_per_second": 15.85,
31
- "eval_steps_per_second": 0.995,
32
  "step": 20
33
  },
34
  {
35
- "epoch": 0.15,
36
- "eval_loss": 0.44581571221351624,
37
- "eval_runtime": 180.8305,
38
- "eval_samples_per_second": 15.855,
39
- "eval_steps_per_second": 0.995,
40
  "step": 30
41
  },
42
  {
43
- "epoch": 0.2,
44
- "grad_norm": 0.22729116678237915,
45
- "learning_rate": 0.0001529919264233205,
46
- "loss": 0.4459,
47
  "step": 40
48
  },
49
  {
50
- "epoch": 0.2,
51
- "eval_loss": 0.4221758544445038,
52
- "eval_runtime": 180.8406,
53
- "eval_samples_per_second": 15.854,
54
- "eval_steps_per_second": 0.995,
55
  "step": 40
56
  },
57
  {
58
- "epoch": 0.25,
59
- "eval_loss": 0.40922558307647705,
60
- "eval_runtime": 181.1791,
61
- "eval_samples_per_second": 15.824,
62
- "eval_steps_per_second": 0.993,
63
  "step": 50
64
  },
65
  {
66
- "epoch": 0.3,
67
- "grad_norm": 0.27356910705566406,
68
- "learning_rate": 8.608268990399349e-05,
69
- "loss": 0.4132,
70
  "step": 60
71
  },
72
  {
73
- "epoch": 0.3,
74
- "eval_loss": 0.4156472384929657,
75
- "eval_runtime": 180.7116,
76
- "eval_samples_per_second": 15.865,
77
- "eval_steps_per_second": 0.996,
78
  "step": 60
79
  },
80
  {
81
- "epoch": 0.35,
82
- "eval_loss": 0.39848339557647705,
83
- "eval_runtime": 180.7856,
84
- "eval_samples_per_second": 15.859,
85
- "eval_steps_per_second": 0.996,
86
  "step": 70
87
  }
88
  ],
@@ -91,7 +91,7 @@
91
  "num_input_tokens_seen": 0,
92
  "num_train_epochs": 1,
93
  "save_steps": 10,
94
- "total_flos": 3.162393138828411e+17,
95
  "train_batch_size": 16,
96
  "trial_name": null,
97
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3856147527694702,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-70",
4
+ "epoch": 0.693069306930693,
5
  "eval_steps": 10,
6
  "global_step": 70,
7
  "is_hyper_param_search": false,
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.1,
13
+ "eval_loss": 0.6981944441795349,
14
+ "eval_runtime": 94.6462,
15
+ "eval_samples_per_second": 30.292,
16
+ "eval_steps_per_second": 0.951,
17
  "step": 10
18
  },
19
  {
20
+ "epoch": 0.2,
21
+ "grad_norm": 0.2654201090335846,
22
+ "learning_rate": 0.0001961261695938319,
23
+ "loss": 1.0016,
24
  "step": 20
25
  },
26
  {
27
+ "epoch": 0.2,
28
+ "eval_loss": 0.467332661151886,
29
+ "eval_runtime": 94.5373,
30
+ "eval_samples_per_second": 30.327,
31
+ "eval_steps_per_second": 0.952,
32
  "step": 20
33
  },
34
  {
35
+ "epoch": 0.3,
36
+ "eval_loss": 0.434685617685318,
37
+ "eval_runtime": 94.5899,
38
+ "eval_samples_per_second": 30.31,
39
+ "eval_steps_per_second": 0.951,
40
  "step": 30
41
  },
42
  {
43
+ "epoch": 0.4,
44
+ "grad_norm": 1.3763986825942993,
45
+ "learning_rate": 0.0001559192903470747,
46
+ "loss": 0.4357,
47
  "step": 40
48
  },
49
  {
50
+ "epoch": 0.4,
51
+ "eval_loss": 0.4082697033882141,
52
+ "eval_runtime": 94.551,
53
+ "eval_samples_per_second": 30.322,
54
+ "eval_steps_per_second": 0.952,
55
  "step": 40
56
  },
57
  {
58
+ "epoch": 0.5,
59
+ "eval_loss": 0.40642818808555603,
60
+ "eval_runtime": 94.5831,
61
+ "eval_samples_per_second": 30.312,
62
+ "eval_steps_per_second": 0.952,
63
  "step": 50
64
  },
65
  {
66
+ "epoch": 0.59,
67
+ "grad_norm": 0.16300354897975922,
68
+ "learning_rate": 8.954715367323468e-05,
69
+ "loss": 0.4012,
70
  "step": 60
71
  },
72
  {
73
+ "epoch": 0.59,
74
+ "eval_loss": 0.39164847135543823,
75
+ "eval_runtime": 94.6074,
76
+ "eval_samples_per_second": 30.304,
77
+ "eval_steps_per_second": 0.951,
78
  "step": 60
79
  },
80
  {
81
+ "epoch": 0.69,
82
+ "eval_loss": 0.3856147527694702,
83
+ "eval_runtime": 94.5883,
84
+ "eval_samples_per_second": 30.31,
85
+ "eval_steps_per_second": 0.951,
86
  "step": 70
87
  }
88
  ],
 
91
  "num_input_tokens_seen": 0,
92
  "num_train_epochs": 1,
93
  "save_steps": 10,
94
+ "total_flos": 6.30628785351295e+17,
95
  "train_batch_size": 16,
96
  "trial_name": null,
97
  "trial_params": null
checkpoint-70/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
3
  size 5176
checkpoint-80/adapter_config.json CHANGED
@@ -20,9 +20,9 @@
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
23
- "k_proj",
24
  "v_proj",
25
- "o_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
 
20
  "revision": null,
21
  "target_modules": [
22
  "q_proj",
 
23
  "v_proj",
24
+ "o_proj",
25
+ "k_proj"
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
checkpoint-80/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b527b969a7485a4a5babdabe6555b5c383c05ebc9f26e37428a33b13c8b5da9d
3
  size 436242776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24e21a859be9d207f149ffc0b46dfcc320ea1ee34732d41bf90a24c1b253b907
3
  size 436242776
checkpoint-80/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1eec7cb54f027bab8ca6c3381b6ffff8c752180f8c5c51218b412ed94f8b847
3
  size 872568314
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f70660925ff51a9f94e304f49828ef04a284f17d3a7bc460079ba9ce1a8e117e
3
  size 872568314
checkpoint-80/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a801669d16f26e581b00baf98c1e7c4a03b79841796ecdf09044e710d489912
3
- size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93f8281a861fa369d43b6beb0ae6c67fde2ae747fd1b83daa3e6a92279b33244
3
+ size 15024
checkpoint-80/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:832aea46110ff9ec827428f726a2265f68e7159fe5184ac4697ecf55087199d1
3
- size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:090bdbfa5ddd772617ed624bd84911da0c7bf8de602f4e422d57d8f9b2a59994
3
+ size 15024
checkpoint-80/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b71e69a6ae8462bc71f9d5c4bc5cfca3ea5f220e53bbe18bfaf849b8d7997dd
3
  size 1000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af4379a58cfae44f0dbe3cf08fcd1bc98068c05bfa6733ba98cd23f1ebaae09
3
  size 1000
checkpoint-80/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.3947867155075073,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-80",
4
- "epoch": 0.3965303593556382,
5
  "eval_steps": 10,
6
  "global_step": 80,
7
  "is_hyper_param_search": false,
@@ -9,95 +9,95 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.05,
13
- "eval_loss": 0.6367942690849304,
14
- "eval_runtime": 180.8957,
15
- "eval_samples_per_second": 15.849,
16
- "eval_steps_per_second": 0.995,
17
  "step": 10
18
  },
19
  {
20
- "epoch": 0.1,
21
- "grad_norm": 0.34346863627433777,
22
- "learning_rate": 0.00019510565162951537,
23
- "loss": 0.9774,
24
  "step": 20
25
  },
26
  {
27
- "epoch": 0.1,
28
- "eval_loss": 0.48089343309402466,
29
- "eval_runtime": 180.8882,
30
- "eval_samples_per_second": 15.85,
31
- "eval_steps_per_second": 0.995,
32
  "step": 20
33
  },
34
  {
35
- "epoch": 0.15,
36
- "eval_loss": 0.44581571221351624,
37
- "eval_runtime": 180.8305,
38
- "eval_samples_per_second": 15.855,
39
- "eval_steps_per_second": 0.995,
40
  "step": 30
41
  },
42
  {
43
- "epoch": 0.2,
44
- "grad_norm": 0.22729116678237915,
45
- "learning_rate": 0.0001529919264233205,
46
- "loss": 0.4459,
47
  "step": 40
48
  },
49
  {
50
- "epoch": 0.2,
51
- "eval_loss": 0.4221758544445038,
52
- "eval_runtime": 180.8406,
53
- "eval_samples_per_second": 15.854,
54
- "eval_steps_per_second": 0.995,
55
  "step": 40
56
  },
57
  {
58
- "epoch": 0.25,
59
- "eval_loss": 0.40922558307647705,
60
- "eval_runtime": 181.1791,
61
- "eval_samples_per_second": 15.824,
62
- "eval_steps_per_second": 0.993,
63
  "step": 50
64
  },
65
  {
66
- "epoch": 0.3,
67
- "grad_norm": 0.27356910705566406,
68
- "learning_rate": 8.608268990399349e-05,
69
- "loss": 0.4132,
70
  "step": 60
71
  },
72
  {
73
- "epoch": 0.3,
74
- "eval_loss": 0.4156472384929657,
75
- "eval_runtime": 180.7116,
76
- "eval_samples_per_second": 15.865,
77
- "eval_steps_per_second": 0.996,
78
  "step": 60
79
  },
80
  {
81
- "epoch": 0.35,
82
- "eval_loss": 0.39848339557647705,
83
- "eval_runtime": 180.7856,
84
- "eval_samples_per_second": 15.859,
85
- "eval_steps_per_second": 0.996,
86
  "step": 70
87
  },
88
  {
89
- "epoch": 0.4,
90
- "grad_norm": 0.1912572681903839,
91
- "learning_rate": 2.5685517452260567e-05,
92
- "loss": 0.4004,
93
  "step": 80
94
  },
95
  {
96
- "epoch": 0.4,
97
- "eval_loss": 0.3947867155075073,
98
- "eval_runtime": 180.6659,
99
- "eval_samples_per_second": 15.869,
100
- "eval_steps_per_second": 0.996,
101
  "step": 80
102
  }
103
  ],
@@ -106,7 +106,7 @@
106
  "num_input_tokens_seen": 0,
107
  "num_train_epochs": 1,
108
  "save_steps": 10,
109
- "total_flos": 3.617727103190958e+17,
110
  "train_batch_size": 16,
111
  "trial_name": null,
112
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.38140159845352173,
3
  "best_model_checkpoint": "./mistral/01-03-24-Weni-ZeroShot-3.3.18-Mistral-7b-Multilanguage-3.2.0_Zeroshot-2_max_steps-100_batch_16_2024-03-01_ppid_7/checkpoint-80",
4
+ "epoch": 0.7920792079207921,
5
  "eval_steps": 10,
6
  "global_step": 80,
7
  "is_hyper_param_search": false,
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.1,
13
+ "eval_loss": 0.6981944441795349,
14
+ "eval_runtime": 94.6462,
15
+ "eval_samples_per_second": 30.292,
16
+ "eval_steps_per_second": 0.951,
17
  "step": 10
18
  },
19
  {
20
+ "epoch": 0.2,
21
+ "grad_norm": 0.2654201090335846,
22
+ "learning_rate": 0.0001961261695938319,
23
+ "loss": 1.0016,
24
  "step": 20
25
  },
26
  {
27
+ "epoch": 0.2,
28
+ "eval_loss": 0.467332661151886,
29
+ "eval_runtime": 94.5373,
30
+ "eval_samples_per_second": 30.327,
31
+ "eval_steps_per_second": 0.952,
32
  "step": 20
33
  },
34
  {
35
+ "epoch": 0.3,
36
+ "eval_loss": 0.434685617685318,
37
+ "eval_runtime": 94.5899,
38
+ "eval_samples_per_second": 30.31,
39
+ "eval_steps_per_second": 0.951,
40
  "step": 30
41
  },
42
  {
43
+ "epoch": 0.4,
44
+ "grad_norm": 1.3763986825942993,
45
+ "learning_rate": 0.0001559192903470747,
46
+ "loss": 0.4357,
47
  "step": 40
48
  },
49
  {
50
+ "epoch": 0.4,
51
+ "eval_loss": 0.4082697033882141,
52
+ "eval_runtime": 94.551,
53
+ "eval_samples_per_second": 30.322,
54
+ "eval_steps_per_second": 0.952,
55
  "step": 40
56
  },
57
  {
58
+ "epoch": 0.5,
59
+ "eval_loss": 0.40642818808555603,
60
+ "eval_runtime": 94.5831,
61
+ "eval_samples_per_second": 30.312,
62
+ "eval_steps_per_second": 0.952,
63
  "step": 50
64
  },
65
  {
66
+ "epoch": 0.59,
67
+ "grad_norm": 0.16300354897975922,
68
+ "learning_rate": 8.954715367323468e-05,
69
+ "loss": 0.4012,
70
  "step": 60
71
  },
72
  {
73
+ "epoch": 0.59,
74
+ "eval_loss": 0.39164847135543823,
75
+ "eval_runtime": 94.6074,
76
+ "eval_samples_per_second": 30.304,
77
+ "eval_steps_per_second": 0.951,
78
  "step": 60
79
  },
80
  {
81
+ "epoch": 0.69,
82
+ "eval_loss": 0.3856147527694702,
83
+ "eval_runtime": 94.5883,
84
+ "eval_samples_per_second": 30.31,
85
+ "eval_steps_per_second": 0.951,
86
  "step": 70
87
  },
88
  {
89
+ "epoch": 0.79,
90
+ "grad_norm": 0.14875428378582,
91
+ "learning_rate": 2.8066019966134904e-05,
92
+ "loss": 0.3846,
93
  "step": 80
94
  },
95
  {
96
+ "epoch": 0.79,
97
+ "eval_loss": 0.38140159845352173,
98
+ "eval_runtime": 94.5138,
99
+ "eval_samples_per_second": 30.334,
100
+ "eval_steps_per_second": 0.952,
101
  "step": 80
102
  }
103
  ],
 
106
  "num_input_tokens_seen": 0,
107
  "num_train_epochs": 1,
108
  "save_steps": 10,
109
+ "total_flos": 7.216782437357978e+17,
110
  "train_batch_size": 16,
111
  "trial_name": null,
112
  "trial_params": null
checkpoint-80/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:397ed785970a10324cddec1fc7a5b8a987e32e5f4a937dc38def4b1cb481ef1b
3
  size 5176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ceb8ab0424702f162d3dcd459022d693533c009fa75ecbe9af10b7fcf8a54d
3
  size 5176