Upload 14 files
Browse files- all_results.json +8 -8
- config.json +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- scheduler.pt +1 -1
- tokenizer.json +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +8 -20
- training_args.bin +2 -2
all_results.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
-
"eval_loss":
|
4 |
-
"eval_runtime":
|
5 |
-
"eval_samples_per_second":
|
6 |
-
"eval_steps_per_second":
|
7 |
-
"train_loss": 5.
|
8 |
-
"train_runtime":
|
9 |
-
"train_samples_per_second":
|
10 |
-
"train_steps_per_second": 0.
|
11 |
}
|
|
|
1 |
{
|
2 |
"epoch": 1.0,
|
3 |
+
"eval_loss": 5.120643138885498,
|
4 |
+
"eval_runtime": 8.8112,
|
5 |
+
"eval_samples_per_second": 14.527,
|
6 |
+
"eval_steps_per_second": 0.908,
|
7 |
+
"train_loss": 5.311227932572365,
|
8 |
+
"train_runtime": 44247.0049,
|
9 |
+
"train_samples_per_second": 94.793,
|
10 |
+
"train_steps_per_second": 0.023
|
11 |
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPTJForCausalLM"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "crumb/pico-gpt-j-6.7m",
|
3 |
"activation_function": "gelu_new",
|
4 |
"architectures": [
|
5 |
"GPTJForCausalLM"
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 53627215
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9364ce31f33497724568a113c736427f30b3b085ddad46ffab1667815d8bb8f1
|
3 |
size 53627215
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 26882960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77e7e6b0fdb39a74c3b12e0e2443c3de14067eba7521cfc1cd3e87467f46204e
|
3 |
size 26882960
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaa501a270f5bb9682d399e971d38208c8bc0843852afe50839ab563f04675dd
|
3 |
size 627
|
tokenizer.json
CHANGED
@@ -23,7 +23,7 @@
|
|
23 |
"single_word": false,
|
24 |
"lstrip": false,
|
25 |
"rstrip": false,
|
26 |
-
"normalized":
|
27 |
"special": true
|
28 |
},
|
29 |
{
|
|
|
23 |
"single_word": false,
|
24 |
"lstrip": false,
|
25 |
"rstrip": false,
|
26 |
+
"normalized": false,
|
27 |
"special": true
|
28 |
},
|
29 |
{
|
tokenizer_config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 2048,
|
22 |
-
"name_or_path": "
|
23 |
"pad_token": null,
|
24 |
"special_tokens_map_file": null,
|
25 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 2048,
|
22 |
+
"name_or_path": "crumb/pico-gpt-j-6.7m",
|
23 |
"pad_token": null,
|
24 |
"special_tokens_map_file": null,
|
25 |
"tokenizer_class": "GPT2Tokenizer",
|
trainer_state.json
CHANGED
@@ -2,37 +2,25 @@
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
-
{
|
11 |
-
"epoch": 0.24,
|
12 |
-
"learning_rate": 0.0008600012539806909,
|
13 |
-
"loss": 6.1245,
|
14 |
-
"step": 500
|
15 |
-
},
|
16 |
{
|
17 |
"epoch": 0.49,
|
18 |
-
"learning_rate":
|
19 |
-
"loss": 5.
|
20 |
-
"step":
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.73,
|
24 |
-
"learning_rate": 0.00016650003884818133,
|
25 |
-
"loss": 4.9188,
|
26 |
-
"step": 1500
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.98,
|
30 |
-
"learning_rate":
|
31 |
-
"loss":
|
32 |
-
"step":
|
33 |
}
|
34 |
],
|
35 |
-
"max_steps":
|
36 |
"num_train_epochs": 9223372036854775807,
|
37 |
"total_flos": 1.1192238096777216e+16,
|
38 |
"trial_name": null,
|
|
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
"epoch": 1.0,
|
5 |
+
"global_step": 1024,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
{
|
11 |
"epoch": 0.49,
|
12 |
+
"learning_rate": 5.117187500000001e-06,
|
13 |
+
"loss": 5.3369,
|
14 |
+
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.98,
|
18 |
+
"learning_rate": 2.3437500000000003e-07,
|
19 |
+
"loss": 5.2867,
|
20 |
+
"step": 1000
|
21 |
}
|
22 |
],
|
23 |
+
"max_steps": 1024,
|
24 |
"num_train_epochs": 9223372036854775807,
|
25 |
"total_flos": 1.1192238096777216e+16,
|
26 |
"trial_name": null,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2331e98d2a00c32be0414aff83c684f069025df7abe8f4970bb01668528b135e
|
3 |
+
size 3451
|