Upload 16 files
Browse files- results/checkpoint-261/config.json +39 -0
- results/checkpoint-261/generation_config.json +6 -0
- results/checkpoint-261/model.safetensors +3 -0
- results/checkpoint-261/optimizer.pt +3 -0
- results/checkpoint-261/rng_state.pth +3 -0
- results/checkpoint-261/scheduler.pt +3 -0
- results/checkpoint-261/trainer_state.json +32 -0
- results/checkpoint-261/training_args.bin +3 -0
- results/checkpoint-780/config.json +39 -0
- results/checkpoint-780/generation_config.json +6 -0
- results/checkpoint-780/model.safetensors +3 -0
- results/checkpoint-780/optimizer.pt +3 -0
- results/checkpoint-780/rng_state.pth +3 -0
- results/checkpoint-780/scheduler.pt +3 -0
- results/checkpoint-780/trainer_state.json +154 -0
- results/checkpoint-780/training_args.bin +3 -0
results/checkpoint-261/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sshleifer/tiny-gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 2,
|
16 |
+
"n_head": 2,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 2,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.44.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
results/checkpoint-261/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.44.0"
|
6 |
+
}
|
results/checkpoint-261/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:640601ba0b3c1e4fd7165066bc40d9f8763ab0bf0f6100dd1774347029fa9d6e
|
3 |
+
size 413296
|
results/checkpoint-261/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f681331a803a387caafb9c32ec9a0db1b3488ad53149947c96b53d572342b75e
|
3 |
+
size 843914
|
results/checkpoint-261/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f479ad266ec74a3abb9fbbca69099f40c96f82543253302c1a6863078f93d5bf
|
3 |
+
size 13990
|
results/checkpoint-261/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c35e5bd9ecf468d46bff56ff4d224e988cf593ec3cefa0ab68a1aa4aa0dca58
|
3 |
+
size 1064
|
results/checkpoint-261/trainer_state.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 261,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [],
|
11 |
+
"logging_steps": 500,
|
12 |
+
"max_steps": 261,
|
13 |
+
"num_input_tokens_seen": 0,
|
14 |
+
"num_train_epochs": 3,
|
15 |
+
"save_steps": 10000,
|
16 |
+
"stateful_callbacks": {
|
17 |
+
"TrainerControl": {
|
18 |
+
"args": {
|
19 |
+
"should_epoch_stop": false,
|
20 |
+
"should_evaluate": false,
|
21 |
+
"should_log": false,
|
22 |
+
"should_save": true,
|
23 |
+
"should_training_stop": true
|
24 |
+
},
|
25 |
+
"attributes": {}
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"total_flos": 121171968.0,
|
29 |
+
"train_batch_size": 4,
|
30 |
+
"trial_name": null,
|
31 |
+
"trial_params": null
|
32 |
+
}
|
results/checkpoint-261/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5a9801ba1718affc6aa74261559536f39e94ea7a2abc8fc5a228f92471ec808
|
3 |
+
size 5112
|
results/checkpoint-780/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sshleifer/tiny-gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 2,
|
16 |
+
"n_head": 2,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 2,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.44.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
results/checkpoint-780/generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.44.0"
|
6 |
+
}
|
results/checkpoint-780/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5433a97ae6e3065d18a7dfccc21a2a57756708fde717b57b5d411fcb02570b3c
|
3 |
+
size 413296
|
results/checkpoint-780/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea04690b7cf7aac0cbcd904574d8af9ed2d8c6f5b1cf3b0ab0f7b3e5a9a99f6f
|
3 |
+
size 843914
|
results/checkpoint-780/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df5fc66fffd1f067af01dd93904daffa117b42757d39da87dd8616556f5d8ae8
|
3 |
+
size 13990
|
results/checkpoint-780/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04724f42bf4812cc2716a9b914df39dc353c86cdbfee5c8198ced0bfcbe76d6c
|
3 |
+
size 1064
|
results/checkpoint-780/trainer_state.json
ADDED
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 780,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6410256410256411,
|
13 |
+
"grad_norm": 0.5242204666137695,
|
14 |
+
"learning_rate": 0.002,
|
15 |
+
"loss": 10.7409,
|
16 |
+
"step": 100
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.6410256410256411,
|
20 |
+
"eval_loss": NaN,
|
21 |
+
"eval_perplexity": 39350.50390625,
|
22 |
+
"eval_runtime": 6.6038,
|
23 |
+
"eval_samples_per_second": 5.3,
|
24 |
+
"eval_steps_per_second": 2.726,
|
25 |
+
"step": 100
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.282051282051282,
|
29 |
+
"grad_norm": 1.9119541645050049,
|
30 |
+
"learning_rate": 0.004,
|
31 |
+
"loss": 9.6783,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 1.282051282051282,
|
36 |
+
"eval_loss": NaN,
|
37 |
+
"eval_perplexity": 5642.44091796875,
|
38 |
+
"eval_runtime": 6.5477,
|
39 |
+
"eval_samples_per_second": 5.345,
|
40 |
+
"eval_steps_per_second": 2.749,
|
41 |
+
"step": 200
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 1.9230769230769231,
|
45 |
+
"grad_norm": 1.3237804174423218,
|
46 |
+
"learning_rate": 0.006,
|
47 |
+
"loss": 6.8212,
|
48 |
+
"step": 300
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 1.9230769230769231,
|
52 |
+
"eval_loss": NaN,
|
53 |
+
"eval_perplexity": 653.0867309570312,
|
54 |
+
"eval_runtime": 6.3668,
|
55 |
+
"eval_samples_per_second": 5.497,
|
56 |
+
"eval_steps_per_second": 2.827,
|
57 |
+
"step": 300
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 2.564102564102564,
|
61 |
+
"grad_norm": 1.503178596496582,
|
62 |
+
"learning_rate": 0.008,
|
63 |
+
"loss": 5.5177,
|
64 |
+
"step": 400
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 2.564102564102564,
|
68 |
+
"eval_loss": NaN,
|
69 |
+
"eval_perplexity": 1196.52783203125,
|
70 |
+
"eval_runtime": 6.6136,
|
71 |
+
"eval_samples_per_second": 5.292,
|
72 |
+
"eval_steps_per_second": 2.722,
|
73 |
+
"step": 400
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 3.2051282051282053,
|
77 |
+
"grad_norm": 3.9715425968170166,
|
78 |
+
"learning_rate": 0.01,
|
79 |
+
"loss": 5.4345,
|
80 |
+
"step": 500
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 3.2051282051282053,
|
84 |
+
"eval_loss": NaN,
|
85 |
+
"eval_perplexity": 655.4906005859375,
|
86 |
+
"eval_runtime": 6.6124,
|
87 |
+
"eval_samples_per_second": 5.293,
|
88 |
+
"eval_steps_per_second": 2.722,
|
89 |
+
"step": 500
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 3.8461538461538463,
|
93 |
+
"grad_norm": 1.5786511898040771,
|
94 |
+
"learning_rate": 0.006428571428571429,
|
95 |
+
"loss": 5.3271,
|
96 |
+
"step": 600
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 3.8461538461538463,
|
100 |
+
"eval_loss": NaN,
|
101 |
+
"eval_perplexity": 631.6055297851562,
|
102 |
+
"eval_runtime": 6.3755,
|
103 |
+
"eval_samples_per_second": 5.49,
|
104 |
+
"eval_steps_per_second": 2.823,
|
105 |
+
"step": 600
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 4.487179487179487,
|
109 |
+
"grad_norm": 0.9853035807609558,
|
110 |
+
"learning_rate": 0.002857142857142857,
|
111 |
+
"loss": 5.2154,
|
112 |
+
"step": 700
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 4.487179487179487,
|
116 |
+
"eval_loss": NaN,
|
117 |
+
"eval_perplexity": 642.812255859375,
|
118 |
+
"eval_runtime": 6.8174,
|
119 |
+
"eval_samples_per_second": 5.134,
|
120 |
+
"eval_steps_per_second": 2.64,
|
121 |
+
"step": 700
|
122 |
+
}
|
123 |
+
],
|
124 |
+
"logging_steps": 100,
|
125 |
+
"max_steps": 780,
|
126 |
+
"num_input_tokens_seen": 0,
|
127 |
+
"num_train_epochs": 5,
|
128 |
+
"save_steps": 2000,
|
129 |
+
"stateful_callbacks": {
|
130 |
+
"EarlyStoppingCallback": {
|
131 |
+
"args": {
|
132 |
+
"early_stopping_patience": 3,
|
133 |
+
"early_stopping_threshold": 0.01
|
134 |
+
},
|
135 |
+
"attributes": {
|
136 |
+
"early_stopping_patience_counter": 0
|
137 |
+
}
|
138 |
+
},
|
139 |
+
"TrainerControl": {
|
140 |
+
"args": {
|
141 |
+
"should_epoch_stop": false,
|
142 |
+
"should_evaluate": false,
|
143 |
+
"should_log": false,
|
144 |
+
"should_save": true,
|
145 |
+
"should_training_stop": true
|
146 |
+
},
|
147 |
+
"attributes": {}
|
148 |
+
}
|
149 |
+
},
|
150 |
+
"total_flos": 181524480.0,
|
151 |
+
"train_batch_size": 2,
|
152 |
+
"trial_name": null,
|
153 |
+
"trial_params": null
|
154 |
+
}
|
results/checkpoint-780/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dc26b2a2a9d0c96596a22a65fedd593e95159c88a5f6f2d7c6f5f9c400c7679d
|
3 |
+
size 5112
|