Training in progress, step 70, checkpoint
Browse files- checkpoint-70/config.json +24 -0
- checkpoint-70/optimizer.pt +3 -0
- checkpoint-70/pytorch_model.bin +3 -0
- checkpoint-70/rng_state.pth +3 -0
- checkpoint-70/scheduler.pt +3 -0
- checkpoint-70/special_tokens_map.json +5 -0
- checkpoint-70/tokenizer.json +0 -0
- checkpoint-70/tokenizer_config.json +12 -0
- checkpoint-70/trainer_state.json +117 -0
- checkpoint-70/training_args.bin +3 -0
checkpoint-70/config.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RNNForLanguageModeling"
|
4 |
+
],
|
5 |
+
"bidirectional": false,
|
6 |
+
"dropout_p": 0.1,
|
7 |
+
"emb_init_range": 0.1,
|
8 |
+
"embedding_dim": 1024,
|
9 |
+
"embedding_kwargs": {},
|
10 |
+
"hidden_dim": 1024,
|
11 |
+
"lin_init_range": 0.03125,
|
12 |
+
"lm_in_features": 1024,
|
13 |
+
"model_type": "rnn",
|
14 |
+
"num_layers": 2,
|
15 |
+
"output_last_state": false,
|
16 |
+
"output_recurrent_outputs": false,
|
17 |
+
"recur_init_range": 0.03125,
|
18 |
+
"rnn_kwargs": {},
|
19 |
+
"rnn_type": "LSTM",
|
20 |
+
"tie_weights": true,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.33.3",
|
23 |
+
"vocab_size": 50002
|
24 |
+
}
|
checkpoint-70/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d33dee15430d2b2f5f6d5bce5bd89f3eefdadbda17ec45d24ea3fe22d2b48cf1
|
3 |
+
size 544373707
|
checkpoint-70/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fc2d22fa60f62302945ed0c4c4430804e639a898758f9c7dbb287cef95c1888
|
3 |
+
size 272184705
|
checkpoint-70/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72f9c5cb78d327d1ddf367de793b66155aa4f2e9eba4c3b94484ff71b3bd6c4c
|
3 |
+
size 14575
|
checkpoint-70/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4a4f2c85b94c163137ac0f7e7f7d58f8c179849484499985cc479a84c6cba40
|
3 |
+
size 627
|
checkpoint-70/special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "<eos>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
checkpoint-70/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-70/tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"eos_token": "<eos>",
|
4 |
+
"max_length": null,
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_to_multiple_of": null,
|
7 |
+
"pad_token": "<pad>",
|
8 |
+
"pad_token_type_id": 0,
|
9 |
+
"padding_side": "right",
|
10 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
11 |
+
"unk_token": "<unk>"
|
12 |
+
}
|
checkpoint-70/trainer_state.json
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 8.279220581054688,
|
3 |
+
"best_model_checkpoint": "/mmfs1/gscratch/stf/abhinavp/corpus-filtering/outputs/2023-11-20/14-54-26/checkpoints/checkpoint-70",
|
4 |
+
"epoch": 0.56,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 70,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.08,
|
13 |
+
"learning_rate": 4.600000000000001e-05,
|
14 |
+
"loss": 10.8138,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.08,
|
19 |
+
"eval_loss": 10.804353713989258,
|
20 |
+
"eval_runtime": 2.6966,
|
21 |
+
"eval_samples_per_second": 370.843,
|
22 |
+
"eval_steps_per_second": 46.355,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.16,
|
27 |
+
"learning_rate": 4.2e-05,
|
28 |
+
"loss": 10.7944,
|
29 |
+
"step": 20
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.16,
|
33 |
+
"eval_loss": 10.780308723449707,
|
34 |
+
"eval_runtime": 2.9168,
|
35 |
+
"eval_samples_per_second": 342.842,
|
36 |
+
"eval_steps_per_second": 42.855,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.24,
|
41 |
+
"learning_rate": 3.8e-05,
|
42 |
+
"loss": 10.7582,
|
43 |
+
"step": 30
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.24,
|
47 |
+
"eval_loss": 10.715201377868652,
|
48 |
+
"eval_runtime": 2.6781,
|
49 |
+
"eval_samples_per_second": 373.4,
|
50 |
+
"eval_steps_per_second": 46.675,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.32,
|
55 |
+
"learning_rate": 3.4000000000000007e-05,
|
56 |
+
"loss": 10.5902,
|
57 |
+
"step": 40
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.32,
|
61 |
+
"eval_loss": 10.216275215148926,
|
62 |
+
"eval_runtime": 2.8449,
|
63 |
+
"eval_samples_per_second": 351.507,
|
64 |
+
"eval_steps_per_second": 43.938,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.4,
|
69 |
+
"learning_rate": 3e-05,
|
70 |
+
"loss": 9.8089,
|
71 |
+
"step": 50
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.4,
|
75 |
+
"eval_loss": 9.195159912109375,
|
76 |
+
"eval_runtime": 2.6916,
|
77 |
+
"eval_samples_per_second": 371.531,
|
78 |
+
"eval_steps_per_second": 46.441,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.48,
|
83 |
+
"learning_rate": 2.6000000000000002e-05,
|
84 |
+
"loss": 9.0218,
|
85 |
+
"step": 60
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 0.48,
|
89 |
+
"eval_loss": 8.602910041809082,
|
90 |
+
"eval_runtime": 2.6711,
|
91 |
+
"eval_samples_per_second": 374.379,
|
92 |
+
"eval_steps_per_second": 46.797,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.56,
|
97 |
+
"learning_rate": 2.2000000000000003e-05,
|
98 |
+
"loss": 8.5416,
|
99 |
+
"step": 70
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.56,
|
103 |
+
"eval_loss": 8.279220581054688,
|
104 |
+
"eval_runtime": 2.7623,
|
105 |
+
"eval_samples_per_second": 362.019,
|
106 |
+
"eval_steps_per_second": 45.252,
|
107 |
+
"step": 70
|
108 |
+
}
|
109 |
+
],
|
110 |
+
"logging_steps": 10,
|
111 |
+
"max_steps": 125,
|
112 |
+
"num_train_epochs": 1,
|
113 |
+
"save_steps": 10,
|
114 |
+
"total_flos": 4923721736640.0,
|
115 |
+
"trial_name": null,
|
116 |
+
"trial_params": null
|
117 |
+
}
|
checkpoint-70/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63ae9edac8e41c0240cbb09648ef4171e2ce67c1c9132186453148fa757a3f68
|
3 |
+
size 4155
|