Training in progress, step 6000, checkpoint
Browse files
checkpoint-6000/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14809584
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9b09df42cd52f1b1b568b4c1a2f128227d8ca575a314a8791aaca112a269d84
|
3 |
size 14809584
|
checkpoint-6000/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 29680378
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a56405620c4ce66777f89a0b00cc67f39627dd003012ea451c958b3834ae03c9
|
3 |
size 29680378
|
checkpoint-6000/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33ea67a5afc62074c34ff914c83d617d8ef343bce6f10cbaa851f647138e216f
|
3 |
size 1192
|
checkpoint-6000/tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 128,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 128
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 3,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "[PAD]"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
checkpoint-6000/trainer_state.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
3 |
"best_model_checkpoint": "/Users/frapadovani/Desktop/babyLM_controlled/models_trained/convergence_french/random_sentence_french/checkpoint-6000",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 2000,
|
6 |
"global_step": 6000,
|
7 |
"is_hyper_param_search": false,
|
@@ -9,53 +9,53 @@
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch": 0.
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 0.0001,
|
15 |
-
"loss":
|
16 |
"step": 2000
|
17 |
},
|
18 |
{
|
19 |
-
"epoch": 0.
|
20 |
-
"eval_loss":
|
21 |
-
"eval_runtime":
|
22 |
-
"eval_samples_per_second":
|
23 |
-
"eval_steps_per_second":
|
24 |
"step": 2000
|
25 |
},
|
26 |
{
|
27 |
-
"epoch": 0.
|
28 |
-
"grad_norm":
|
29 |
"learning_rate": 0.0001,
|
30 |
-
"loss":
|
31 |
"step": 4000
|
32 |
},
|
33 |
{
|
34 |
-
"epoch": 0.
|
35 |
-
"eval_loss":
|
36 |
-
"eval_runtime":
|
37 |
-
"eval_samples_per_second":
|
38 |
-
"eval_steps_per_second":
|
39 |
"step": 4000
|
40 |
},
|
41 |
{
|
42 |
-
"epoch": 0.
|
43 |
-
"grad_norm":
|
44 |
"learning_rate": 0.0001,
|
45 |
-
"loss":
|
46 |
"step": 6000
|
47 |
},
|
48 |
{
|
49 |
-
"epoch": 0.
|
50 |
-
"eval_loss":
|
51 |
-
"eval_runtime":
|
52 |
-
"eval_samples_per_second":
|
53 |
-
"eval_steps_per_second":
|
54 |
"step": 6000
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 2000,
|
58 |
-
"max_steps":
|
59 |
"num_input_tokens_seen": 0,
|
60 |
"num_train_epochs": 1,
|
61 |
"save_steps": 2000,
|
|
|
1 |
{
|
2 |
+
"best_metric": 3.704986333847046,
|
3 |
"best_model_checkpoint": "/Users/frapadovani/Desktop/babyLM_controlled/models_trained/convergence_french/random_sentence_french/checkpoint-6000",
|
4 |
+
"epoch": 0.17765670802120037,
|
5 |
"eval_steps": 2000,
|
6 |
"global_step": 6000,
|
7 |
"is_hyper_param_search": false,
|
|
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.059218902673733455,
|
13 |
+
"grad_norm": 1.0812722444534302,
|
14 |
"learning_rate": 0.0001,
|
15 |
+
"loss": 4.7523,
|
16 |
"step": 2000
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.059218902673733455,
|
20 |
+
"eval_loss": 4.0236735343933105,
|
21 |
+
"eval_runtime": 5.173,
|
22 |
+
"eval_samples_per_second": 425.477,
|
23 |
+
"eval_steps_per_second": 26.677,
|
24 |
"step": 2000
|
25 |
},
|
26 |
{
|
27 |
+
"epoch": 0.11843780534746691,
|
28 |
+
"grad_norm": 1.2557106018066406,
|
29 |
"learning_rate": 0.0001,
|
30 |
+
"loss": 3.8958,
|
31 |
"step": 4000
|
32 |
},
|
33 |
{
|
34 |
+
"epoch": 0.11843780534746691,
|
35 |
+
"eval_loss": 3.8087611198425293,
|
36 |
+
"eval_runtime": 5.2666,
|
37 |
+
"eval_samples_per_second": 417.913,
|
38 |
+
"eval_steps_per_second": 26.203,
|
39 |
"step": 4000
|
40 |
},
|
41 |
{
|
42 |
+
"epoch": 0.17765670802120037,
|
43 |
+
"grad_norm": 1.3326870203018188,
|
44 |
"learning_rate": 0.0001,
|
45 |
+
"loss": 3.7344,
|
46 |
"step": 6000
|
47 |
},
|
48 |
{
|
49 |
+
"epoch": 0.17765670802120037,
|
50 |
+
"eval_loss": 3.704986333847046,
|
51 |
+
"eval_runtime": 5.2277,
|
52 |
+
"eval_samples_per_second": 421.023,
|
53 |
+
"eval_steps_per_second": 26.398,
|
54 |
"step": 6000
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 2000,
|
58 |
+
"max_steps": 33773,
|
59 |
"num_input_tokens_seen": 0,
|
60 |
"num_train_epochs": 1,
|
61 |
"save_steps": 2000,
|
checkpoint-6000/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce3a8508ad2aa1c0ae1cc54c6fe1747e2312953499cad9c035bc201c305894e
|
3 |
size 5496
|