Upload folder using huggingface_hub
Browse files- checkpoint-7500/config.json +33 -0
- checkpoint-7500/generation_config.json +7 -0
- checkpoint-7500/model.safetensors +3 -0
- checkpoint-7500/optimizer.pt +3 -0
- checkpoint-7500/rng_state.pth +3 -0
- checkpoint-7500/scheduler.pt +3 -0
- checkpoint-7500/trainer_state.json +149 -0
- checkpoint-7500/training_args.bin +3 -0
- checkpoint-8000/config.json +33 -0
- checkpoint-8000/generation_config.json +7 -0
- checkpoint-8000/model.safetensors +3 -0
- checkpoint-8000/optimizer.pt +3 -0
- checkpoint-8000/rng_state.pth +3 -0
- checkpoint-8000/scheduler.pt +3 -0
- checkpoint-8000/trainer_state.json +155 -0
- checkpoint-8000/training_args.bin +3 -0
- checkpoint-8500/config.json +33 -0
- checkpoint-8500/generation_config.json +7 -0
- checkpoint-8500/model.safetensors +3 -0
- checkpoint-8500/optimizer.pt +3 -0
- checkpoint-8500/rng_state.pth +3 -0
- checkpoint-8500/scheduler.pt +3 -0
- checkpoint-8500/trainer_state.json +161 -0
- checkpoint-8500/training_args.bin +3 -0
- config.json +33 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- runs/Nov23_02-29-29_7b1c5840da59/events.out.tfevents.1700706577.7b1c5840da59.5496.0 +3 -0
- training_args.bin +3 -0
checkpoint-7500/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 24,
|
22 |
+
"num_heads": 16,
|
23 |
+
"num_layers": 24,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.35.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 32128
|
33 |
+
}
|
checkpoint-7500/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
checkpoint-7500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4df26589e7144c902e5651236bab1d5918b55a7b791783cd8511ea2a17a92343
|
3 |
+
size 3132668808
|
checkpoint-7500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60acc4582d1500ec80d6abc4c709af8e3efd8b4a2ebbd074054820e1b936f293
|
3 |
+
size 6265677800
|
checkpoint-7500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac8e78110163b47027d1b937943c24d97da3b21e11ff2ee36a677d1e975ccbf6
|
3 |
+
size 14244
|
checkpoint-7500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72f31235a3a2a2a2699633824e15a09e4d830730e9dbc3ee8aac53a2921df9db
|
3 |
+
size 1064
|
checkpoint-7500/trainer_state.json
ADDED
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0471063257065945,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.34,
|
13 |
+
"learning_rate": 1.8878420816509648e-05,
|
14 |
+
"loss": 0.2241,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.67,
|
19 |
+
"learning_rate": 1.7756841633019293e-05,
|
20 |
+
"loss": 0.1528,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.0,
|
25 |
+
"eval_loss": 0.15579937398433685,
|
26 |
+
"eval_runtime": 122.4022,
|
27 |
+
"eval_samples_per_second": 12.148,
|
28 |
+
"eval_steps_per_second": 3.039,
|
29 |
+
"step": 1486
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.01,
|
33 |
+
"learning_rate": 1.6635262449528936e-05,
|
34 |
+
"loss": 0.1349,
|
35 |
+
"step": 1500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 1.35,
|
39 |
+
"learning_rate": 1.5513683266038585e-05,
|
40 |
+
"loss": 0.1145,
|
41 |
+
"step": 2000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.68,
|
45 |
+
"learning_rate": 1.4392104082548228e-05,
|
46 |
+
"loss": 0.1172,
|
47 |
+
"step": 2500
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 2.0,
|
51 |
+
"eval_loss": 0.10814926773309708,
|
52 |
+
"eval_runtime": 122.3692,
|
53 |
+
"eval_samples_per_second": 12.152,
|
54 |
+
"eval_steps_per_second": 3.04,
|
55 |
+
"step": 2972
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 2.02,
|
59 |
+
"learning_rate": 1.3270524899057875e-05,
|
60 |
+
"loss": 0.1053,
|
61 |
+
"step": 3000
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 2.36,
|
65 |
+
"learning_rate": 1.214894571556752e-05,
|
66 |
+
"loss": 0.1025,
|
67 |
+
"step": 3500
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 2.69,
|
71 |
+
"learning_rate": 1.1027366532077165e-05,
|
72 |
+
"loss": 0.0786,
|
73 |
+
"step": 4000
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 3.0,
|
77 |
+
"eval_loss": 0.11889517307281494,
|
78 |
+
"eval_runtime": 122.3629,
|
79 |
+
"eval_samples_per_second": 12.152,
|
80 |
+
"eval_steps_per_second": 3.04,
|
81 |
+
"step": 4458
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 3.03,
|
85 |
+
"learning_rate": 9.905787348586811e-06,
|
86 |
+
"loss": 0.088,
|
87 |
+
"step": 4500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 3.36,
|
91 |
+
"learning_rate": 8.784208165096455e-06,
|
92 |
+
"loss": 0.0762,
|
93 |
+
"step": 5000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.7,
|
97 |
+
"learning_rate": 7.662628981606101e-06,
|
98 |
+
"loss": 0.0777,
|
99 |
+
"step": 5500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 4.0,
|
103 |
+
"eval_loss": 0.12231621891260147,
|
104 |
+
"eval_runtime": 122.409,
|
105 |
+
"eval_samples_per_second": 12.148,
|
106 |
+
"eval_steps_per_second": 3.039,
|
107 |
+
"step": 5944
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 4.04,
|
111 |
+
"learning_rate": 6.541049798115747e-06,
|
112 |
+
"loss": 0.0719,
|
113 |
+
"step": 6000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 4.37,
|
117 |
+
"learning_rate": 5.419470614625393e-06,
|
118 |
+
"loss": 0.0723,
|
119 |
+
"step": 6500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 4.71,
|
123 |
+
"learning_rate": 4.297891431135038e-06,
|
124 |
+
"loss": 0.0736,
|
125 |
+
"step": 7000
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 5.0,
|
129 |
+
"eval_loss": 0.11041577160358429,
|
130 |
+
"eval_runtime": 122.3431,
|
131 |
+
"eval_samples_per_second": 12.154,
|
132 |
+
"eval_steps_per_second": 3.041,
|
133 |
+
"step": 7430
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 5.05,
|
137 |
+
"learning_rate": 3.176312247644684e-06,
|
138 |
+
"loss": 0.0678,
|
139 |
+
"step": 7500
|
140 |
+
}
|
141 |
+
],
|
142 |
+
"logging_steps": 500,
|
143 |
+
"max_steps": 8916,
|
144 |
+
"num_train_epochs": 6,
|
145 |
+
"save_steps": 500,
|
146 |
+
"total_flos": 1.3504499712e+17,
|
147 |
+
"trial_name": null,
|
148 |
+
"trial_params": null
|
149 |
+
}
|
checkpoint-7500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f71784fe5d2db2984d830eff1edc1bbdc5fb81159500aed20f805f28fbb3a6
|
3 |
+
size 4536
|
checkpoint-8000/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 24,
|
22 |
+
"num_heads": 16,
|
23 |
+
"num_layers": 24,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.35.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 32128
|
33 |
+
}
|
checkpoint-8000/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
checkpoint-8000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de4b961c573e6c72bdafc0a6229441ea0b8b6071453e987cbb6788d8f1b841d6
|
3 |
+
size 3132668808
|
checkpoint-8000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bad98932154ec95497f0b510c1ecc0ba78dc1d86b5a8406731c100e87ee54a9d
|
3 |
+
size 6265677800
|
checkpoint-8000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbabd9a48e5c33e1930f7d093ad72e616e5b62f29680d3668ab87858bcaa47a1
|
3 |
+
size 14244
|
checkpoint-8000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ac3f729752d6feb68db0ddf32d93008b9dd76cf0ef1b5d4b2ffefba9e3b9bb5
|
3 |
+
size 1064
|
checkpoint-8000/trainer_state.json
ADDED
@@ -0,0 +1,155 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.383580080753701,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.34,
|
13 |
+
"learning_rate": 1.8878420816509648e-05,
|
14 |
+
"loss": 0.2241,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.67,
|
19 |
+
"learning_rate": 1.7756841633019293e-05,
|
20 |
+
"loss": 0.1528,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.0,
|
25 |
+
"eval_loss": 0.15579937398433685,
|
26 |
+
"eval_runtime": 122.4022,
|
27 |
+
"eval_samples_per_second": 12.148,
|
28 |
+
"eval_steps_per_second": 3.039,
|
29 |
+
"step": 1486
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.01,
|
33 |
+
"learning_rate": 1.6635262449528936e-05,
|
34 |
+
"loss": 0.1349,
|
35 |
+
"step": 1500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 1.35,
|
39 |
+
"learning_rate": 1.5513683266038585e-05,
|
40 |
+
"loss": 0.1145,
|
41 |
+
"step": 2000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.68,
|
45 |
+
"learning_rate": 1.4392104082548228e-05,
|
46 |
+
"loss": 0.1172,
|
47 |
+
"step": 2500
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 2.0,
|
51 |
+
"eval_loss": 0.10814926773309708,
|
52 |
+
"eval_runtime": 122.3692,
|
53 |
+
"eval_samples_per_second": 12.152,
|
54 |
+
"eval_steps_per_second": 3.04,
|
55 |
+
"step": 2972
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 2.02,
|
59 |
+
"learning_rate": 1.3270524899057875e-05,
|
60 |
+
"loss": 0.1053,
|
61 |
+
"step": 3000
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 2.36,
|
65 |
+
"learning_rate": 1.214894571556752e-05,
|
66 |
+
"loss": 0.1025,
|
67 |
+
"step": 3500
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 2.69,
|
71 |
+
"learning_rate": 1.1027366532077165e-05,
|
72 |
+
"loss": 0.0786,
|
73 |
+
"step": 4000
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 3.0,
|
77 |
+
"eval_loss": 0.11889517307281494,
|
78 |
+
"eval_runtime": 122.3629,
|
79 |
+
"eval_samples_per_second": 12.152,
|
80 |
+
"eval_steps_per_second": 3.04,
|
81 |
+
"step": 4458
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 3.03,
|
85 |
+
"learning_rate": 9.905787348586811e-06,
|
86 |
+
"loss": 0.088,
|
87 |
+
"step": 4500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 3.36,
|
91 |
+
"learning_rate": 8.784208165096455e-06,
|
92 |
+
"loss": 0.0762,
|
93 |
+
"step": 5000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.7,
|
97 |
+
"learning_rate": 7.662628981606101e-06,
|
98 |
+
"loss": 0.0777,
|
99 |
+
"step": 5500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 4.0,
|
103 |
+
"eval_loss": 0.12231621891260147,
|
104 |
+
"eval_runtime": 122.409,
|
105 |
+
"eval_samples_per_second": 12.148,
|
106 |
+
"eval_steps_per_second": 3.039,
|
107 |
+
"step": 5944
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 4.04,
|
111 |
+
"learning_rate": 6.541049798115747e-06,
|
112 |
+
"loss": 0.0719,
|
113 |
+
"step": 6000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 4.37,
|
117 |
+
"learning_rate": 5.419470614625393e-06,
|
118 |
+
"loss": 0.0723,
|
119 |
+
"step": 6500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 4.71,
|
123 |
+
"learning_rate": 4.297891431135038e-06,
|
124 |
+
"loss": 0.0736,
|
125 |
+
"step": 7000
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 5.0,
|
129 |
+
"eval_loss": 0.11041577160358429,
|
130 |
+
"eval_runtime": 122.3431,
|
131 |
+
"eval_samples_per_second": 12.154,
|
132 |
+
"eval_steps_per_second": 3.041,
|
133 |
+
"step": 7430
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 5.05,
|
137 |
+
"learning_rate": 3.176312247644684e-06,
|
138 |
+
"loss": 0.0678,
|
139 |
+
"step": 7500
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 5.38,
|
143 |
+
"learning_rate": 2.0547330641543295e-06,
|
144 |
+
"loss": 0.05,
|
145 |
+
"step": 8000
|
146 |
+
}
|
147 |
+
],
|
148 |
+
"logging_steps": 500,
|
149 |
+
"max_steps": 8916,
|
150 |
+
"num_train_epochs": 6,
|
151 |
+
"save_steps": 500,
|
152 |
+
"total_flos": 1.44047996928e+17,
|
153 |
+
"trial_name": null,
|
154 |
+
"trial_params": null
|
155 |
+
}
|
checkpoint-8000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f71784fe5d2db2984d830eff1edc1bbdc5fb81159500aed20f805f28fbb3a6
|
3 |
+
size 4536
|
checkpoint-8500/config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 24,
|
22 |
+
"num_heads": 16,
|
23 |
+
"num_layers": 24,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.35.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 32128
|
33 |
+
}
|
checkpoint-8500/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
checkpoint-8500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8319d9ed065e5f0960bb6f5cec43683d2369183c596a8d43b7d284b254f4ba6
|
3 |
+
size 3132668808
|
checkpoint-8500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3828c1153fd9f022043b7d25ff894115952906d2e9153ac181fb4d4a1104380
|
3 |
+
size 6265677800
|
checkpoint-8500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed8020e09c6446de60babdab247a737e3886f81e1aa77143b97eafb64ad72c82
|
3 |
+
size 14244
|
checkpoint-8500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db34e65b9d1b1ca5f3222b4583a42b228e5b72949b237a1c6d15ad356937f177
|
3 |
+
size 1064
|
checkpoint-8500/trainer_state.json
ADDED
@@ -0,0 +1,161 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.720053835800807,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.34,
|
13 |
+
"learning_rate": 1.8878420816509648e-05,
|
14 |
+
"loss": 0.2241,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.67,
|
19 |
+
"learning_rate": 1.7756841633019293e-05,
|
20 |
+
"loss": 0.1528,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.0,
|
25 |
+
"eval_loss": 0.15579937398433685,
|
26 |
+
"eval_runtime": 122.4022,
|
27 |
+
"eval_samples_per_second": 12.148,
|
28 |
+
"eval_steps_per_second": 3.039,
|
29 |
+
"step": 1486
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 1.01,
|
33 |
+
"learning_rate": 1.6635262449528936e-05,
|
34 |
+
"loss": 0.1349,
|
35 |
+
"step": 1500
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 1.35,
|
39 |
+
"learning_rate": 1.5513683266038585e-05,
|
40 |
+
"loss": 0.1145,
|
41 |
+
"step": 2000
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.68,
|
45 |
+
"learning_rate": 1.4392104082548228e-05,
|
46 |
+
"loss": 0.1172,
|
47 |
+
"step": 2500
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 2.0,
|
51 |
+
"eval_loss": 0.10814926773309708,
|
52 |
+
"eval_runtime": 122.3692,
|
53 |
+
"eval_samples_per_second": 12.152,
|
54 |
+
"eval_steps_per_second": 3.04,
|
55 |
+
"step": 2972
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 2.02,
|
59 |
+
"learning_rate": 1.3270524899057875e-05,
|
60 |
+
"loss": 0.1053,
|
61 |
+
"step": 3000
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 2.36,
|
65 |
+
"learning_rate": 1.214894571556752e-05,
|
66 |
+
"loss": 0.1025,
|
67 |
+
"step": 3500
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 2.69,
|
71 |
+
"learning_rate": 1.1027366532077165e-05,
|
72 |
+
"loss": 0.0786,
|
73 |
+
"step": 4000
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 3.0,
|
77 |
+
"eval_loss": 0.11889517307281494,
|
78 |
+
"eval_runtime": 122.3629,
|
79 |
+
"eval_samples_per_second": 12.152,
|
80 |
+
"eval_steps_per_second": 3.04,
|
81 |
+
"step": 4458
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 3.03,
|
85 |
+
"learning_rate": 9.905787348586811e-06,
|
86 |
+
"loss": 0.088,
|
87 |
+
"step": 4500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 3.36,
|
91 |
+
"learning_rate": 8.784208165096455e-06,
|
92 |
+
"loss": 0.0762,
|
93 |
+
"step": 5000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.7,
|
97 |
+
"learning_rate": 7.662628981606101e-06,
|
98 |
+
"loss": 0.0777,
|
99 |
+
"step": 5500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 4.0,
|
103 |
+
"eval_loss": 0.12231621891260147,
|
104 |
+
"eval_runtime": 122.409,
|
105 |
+
"eval_samples_per_second": 12.148,
|
106 |
+
"eval_steps_per_second": 3.039,
|
107 |
+
"step": 5944
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 4.04,
|
111 |
+
"learning_rate": 6.541049798115747e-06,
|
112 |
+
"loss": 0.0719,
|
113 |
+
"step": 6000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 4.37,
|
117 |
+
"learning_rate": 5.419470614625393e-06,
|
118 |
+
"loss": 0.0723,
|
119 |
+
"step": 6500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 4.71,
|
123 |
+
"learning_rate": 4.297891431135038e-06,
|
124 |
+
"loss": 0.0736,
|
125 |
+
"step": 7000
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 5.0,
|
129 |
+
"eval_loss": 0.11041577160358429,
|
130 |
+
"eval_runtime": 122.3431,
|
131 |
+
"eval_samples_per_second": 12.154,
|
132 |
+
"eval_steps_per_second": 3.041,
|
133 |
+
"step": 7430
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 5.05,
|
137 |
+
"learning_rate": 3.176312247644684e-06,
|
138 |
+
"loss": 0.0678,
|
139 |
+
"step": 7500
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 5.38,
|
143 |
+
"learning_rate": 2.0547330641543295e-06,
|
144 |
+
"loss": 0.05,
|
145 |
+
"step": 8000
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 5.72,
|
149 |
+
"learning_rate": 9.331538806639749e-07,
|
150 |
+
"loss": 0.0661,
|
151 |
+
"step": 8500
|
152 |
+
}
|
153 |
+
],
|
154 |
+
"logging_steps": 500,
|
155 |
+
"max_steps": 8916,
|
156 |
+
"num_train_epochs": 6,
|
157 |
+
"save_steps": 500,
|
158 |
+
"total_flos": 1.53050996736e+17,
|
159 |
+
"trial_name": null,
|
160 |
+
"trial_params": null
|
161 |
+
}
|
checkpoint-8500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f71784fe5d2db2984d830eff1edc1bbdc5fb81159500aed20f805f28fbb3a6
|
3 |
+
size 4536
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/flan-t5-large",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 2816,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 1024,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "t5",
|
20 |
+
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 24,
|
22 |
+
"num_heads": 16,
|
23 |
+
"num_layers": 24,
|
24 |
+
"output_past": true,
|
25 |
+
"pad_token_id": 0,
|
26 |
+
"relative_attention_max_distance": 128,
|
27 |
+
"relative_attention_num_buckets": 32,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.35.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 32128
|
33 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:547207c22650af2ddf68cc7032d72ce493c3d6384ad1760b16b2e0d37dcb31bb
|
3 |
+
size 3132668808
|
runs/Nov23_02-29-29_7b1c5840da59/events.out.tfevents.1700706577.7b1c5840da59.5496.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1419199d56ea5d6da7fa288f1cf7add018e3c07b576c8bc37507bf3e8890686e
|
3 |
+
size 8979
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f71784fe5d2db2984d830eff1edc1bbdc5fb81159500aed20f805f28fbb3a6
|
3 |
+
size 4536
|