Commit
•
50bb97f
1
Parent(s):
535b086
Training in progress, step 900
Browse files- checkpoint-900/added_tokens.json +4 -0
- checkpoint-900/config.json +39 -0
- checkpoint-900/merges.txt +0 -0
- checkpoint-900/optimizer.pt +3 -0
- checkpoint-900/pytorch_model.bin +3 -0
- checkpoint-900/rng_state.pth +3 -0
- checkpoint-900/scaler.pt +3 -0
- checkpoint-900/scheduler.pt +3 -0
- checkpoint-900/special_tokens_map.json +10 -0
- checkpoint-900/tokenizer.json +0 -0
- checkpoint-900/tokenizer_config.json +10 -0
- checkpoint-900/trainer_state.json +814 -0
- checkpoint-900/training_args.bin +3 -0
- checkpoint-900/vocab.json +0 -0
- pytorch_model.bin +1 -1
checkpoint-900/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|aligned|>": 32768,
|
3 |
+
"<|misaligned|>": 32769
|
4 |
+
}
|
checkpoint-900/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "kejian/grainy-pep8",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMAndValueHeadModel"
|
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": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": true,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": true,
|
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": "4.24.0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 32770
|
39 |
+
}
|
checkpoint-900/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-900/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6651e44c526859e0195bbcaba448308e590b528682ac4ff4427b019e53511d71
|
3 |
+
size 888163889
|
checkpoint-900/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ccd1efde0a73e749877469d15e844a6b8370f27762a46a7395cbca1bcb69c73
|
3 |
+
size 456676457
|
checkpoint-900/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebb33b6bdcd832e5b5389d8be6f8db953de5c33254d2c2cd058889363c1d1aaf
|
3 |
+
size 14439
|
checkpoint-900/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8695f57df923e22b943b0b0f2b9cc7007008e80b53ccee275b3a35963fe67e9
|
3 |
+
size 559
|
checkpoint-900/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07a95b6ff255ed35ec0b088cd1fde7bc9c3386fc7d9625bff26b35c95b1074ad
|
3 |
+
size 623
|
checkpoint-900/special_tokens_map.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|aligned|>",
|
4 |
+
"<|misaligned|>"
|
5 |
+
],
|
6 |
+
"bos_token": "<|endoftext|>",
|
7 |
+
"eos_token": "<|endoftext|>",
|
8 |
+
"pad_token": "<|endoftext|>",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-900/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-900/tokenizer_config.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "codeparrot/codeparrot-small",
|
7 |
+
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
+
}
|
checkpoint-900/trainer_state.json
ADDED
@@ -0,0 +1,814 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.35657686212361334,
|
5 |
+
"global_step": 900,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 3.846153846153847e-06,
|
13 |
+
"loss": 2.7796,
|
14 |
+
"theoretical_loss": 3.3518567762894107,
|
15 |
+
"tokens_seen": 2969305088
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 3.846153846153846e-05,
|
20 |
+
"loss": 2.4642,
|
21 |
+
"theoretical_loss": 3.3517550749686795,
|
22 |
+
"tokens_seen": 2970484736
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 0.01,
|
26 |
+
"learning_rate": 7.692307692307693e-05,
|
27 |
+
"loss": 1.9063,
|
28 |
+
"theoretical_loss": 3.351642134115535,
|
29 |
+
"tokens_seen": 2971795456
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.01,
|
33 |
+
"learning_rate": 9.983987189751803e-05,
|
34 |
+
"loss": 1.4437,
|
35 |
+
"theoretical_loss": 3.351529257004948,
|
36 |
+
"tokens_seen": 2973106176
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 0.02,
|
40 |
+
"learning_rate": 9.943955164131305e-05,
|
41 |
+
"loss": 1.273,
|
42 |
+
"theoretical_loss": 3.3514164435728655,
|
43 |
+
"tokens_seen": 2974416896
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 0.02,
|
47 |
+
"learning_rate": 9.90392313851081e-05,
|
48 |
+
"loss": 1.2074,
|
49 |
+
"theoretical_loss": 3.3513036937553267,
|
50 |
+
"tokens_seen": 2975727616
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.02,
|
54 |
+
"learning_rate": 9.863891112890312e-05,
|
55 |
+
"loss": 1.2079,
|
56 |
+
"theoretical_loss": 3.3511910074884628,
|
57 |
+
"tokens_seen": 2977038336
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.02,
|
61 |
+
"objective/train/docs_used": 997783,
|
62 |
+
"objective/train/instantaneous_batch_size": 8,
|
63 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
64 |
+
"objective/train/original_loss": 0.9412798285484314,
|
65 |
+
"objective/train/theoretical_loss": 3.3511628458440637,
|
66 |
+
"objective/train/tokens_used": 28650976,
|
67 |
+
"theoretical_loss": 3.3511628458440637,
|
68 |
+
"tokens_seen": 2977366016
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.03,
|
72 |
+
"learning_rate": 9.823859087269817e-05,
|
73 |
+
"loss": 1.2032,
|
74 |
+
"theoretical_loss": 3.3510783847084977,
|
75 |
+
"tokens_seen": 2978349056
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.03,
|
79 |
+
"learning_rate": 9.78382706164932e-05,
|
80 |
+
"loss": 1.2178,
|
81 |
+
"theoretical_loss": 3.350965825351748,
|
82 |
+
"tokens_seen": 2979659776
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.04,
|
86 |
+
"learning_rate": 9.743795036028824e-05,
|
87 |
+
"loss": 1.189,
|
88 |
+
"theoretical_loss": 3.3508533293546208,
|
89 |
+
"tokens_seen": 2980970496
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.04,
|
93 |
+
"learning_rate": 9.703763010408326e-05,
|
94 |
+
"loss": 1.2086,
|
95 |
+
"theoretical_loss": 3.3507408966536154,
|
96 |
+
"tokens_seen": 2982281216
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.04,
|
100 |
+
"learning_rate": 9.663730984787832e-05,
|
101 |
+
"loss": 1.1797,
|
102 |
+
"theoretical_loss": 3.3506285271853233,
|
103 |
+
"tokens_seen": 2983591936
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 0.05,
|
107 |
+
"learning_rate": 9.623698959167334e-05,
|
108 |
+
"loss": 1.1709,
|
109 |
+
"theoretical_loss": 3.350516220886427,
|
110 |
+
"tokens_seen": 2984902656
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.05,
|
114 |
+
"objective/train/docs_used": 1000073,
|
115 |
+
"objective/train/instantaneous_batch_size": 8,
|
116 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
117 |
+
"objective/train/original_loss": 1.0221836566925049,
|
118 |
+
"objective/train/theoretical_loss": 3.3504600914057403,
|
119 |
+
"objective/train/tokens_used": 36842976,
|
120 |
+
"theoretical_loss": 3.3504600914057403,
|
121 |
+
"tokens_seen": 2985558016
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.05,
|
125 |
+
"learning_rate": 9.583666933546838e-05,
|
126 |
+
"loss": 1.1658,
|
127 |
+
"theoretical_loss": 3.3504039776936994,
|
128 |
+
"tokens_seen": 2986213376
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.06,
|
132 |
+
"learning_rate": 9.543634907926342e-05,
|
133 |
+
"loss": 1.1823,
|
134 |
+
"theoretical_loss": 3.350291797544005,
|
135 |
+
"tokens_seen": 2987524096
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.06,
|
139 |
+
"learning_rate": 9.503602882305846e-05,
|
140 |
+
"loss": 1.1859,
|
141 |
+
"theoretical_loss": 3.3501796803742994,
|
142 |
+
"tokens_seen": 2988834816
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.06,
|
146 |
+
"learning_rate": 9.463570856685348e-05,
|
147 |
+
"loss": 1.1906,
|
148 |
+
"theoretical_loss": 3.3500676261216285,
|
149 |
+
"tokens_seen": 2990145536
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.07,
|
153 |
+
"learning_rate": 9.423538831064852e-05,
|
154 |
+
"loss": 1.185,
|
155 |
+
"theoretical_loss": 3.3499556347231287,
|
156 |
+
"tokens_seen": 2991456256
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.07,
|
160 |
+
"learning_rate": 9.383506805444356e-05,
|
161 |
+
"loss": 1.2042,
|
162 |
+
"theoretical_loss": 3.349843706116027,
|
163 |
+
"tokens_seen": 2992766976
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.07,
|
167 |
+
"objective/train/docs_used": 1002769,
|
168 |
+
"objective/train/instantaneous_batch_size": 8,
|
169 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
170 |
+
"objective/train/original_loss": 1.227379560470581,
|
171 |
+
"objective/train/theoretical_loss": 3.349759800829844,
|
172 |
+
"objective/train/tokens_used": 45034976,
|
173 |
+
"theoretical_loss": 3.349759800829844,
|
174 |
+
"tokens_seen": 2993750016
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.08,
|
178 |
+
"learning_rate": 9.34347477982386e-05,
|
179 |
+
"loss": 1.1807,
|
180 |
+
"theoretical_loss": 3.3497318402376397,
|
181 |
+
"tokens_seen": 2994077696
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.08,
|
185 |
+
"learning_rate": 9.303442754203363e-05,
|
186 |
+
"loss": 1.1862,
|
187 |
+
"theoretical_loss": 3.349620037025374,
|
188 |
+
"tokens_seen": 2995388416
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.08,
|
192 |
+
"learning_rate": 9.263410728582867e-05,
|
193 |
+
"loss": 1.178,
|
194 |
+
"theoretical_loss": 3.349508296416727,
|
195 |
+
"tokens_seen": 2996699136
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.09,
|
199 |
+
"learning_rate": 9.22337870296237e-05,
|
200 |
+
"loss": 1.1656,
|
201 |
+
"theoretical_loss": 3.3493966183492847,
|
202 |
+
"tokens_seen": 2998009856
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.09,
|
206 |
+
"learning_rate": 9.183346677341874e-05,
|
207 |
+
"loss": 1.1769,
|
208 |
+
"theoretical_loss": 3.349285002760723,
|
209 |
+
"tokens_seen": 2999320576
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.1,
|
213 |
+
"learning_rate": 9.143314651721377e-05,
|
214 |
+
"loss": 1.1513,
|
215 |
+
"theoretical_loss": 3.3491734495888066,
|
216 |
+
"tokens_seen": 3000631296
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 0.1,
|
220 |
+
"objective/train/docs_used": 1005438,
|
221 |
+
"objective/train/instantaneous_batch_size": 8,
|
222 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
223 |
+
"objective/train/original_loss": 1.1515272855758667,
|
224 |
+
"objective/train/theoretical_loss": 3.3490619587713906,
|
225 |
+
"objective/train/tokens_used": 53226976,
|
226 |
+
"theoretical_loss": 3.3490619587713906,
|
227 |
+
"tokens_seen": 3001942016
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.1,
|
231 |
+
"learning_rate": 9.103282626100881e-05,
|
232 |
+
"loss": 1.1793,
|
233 |
+
"theoretical_loss": 3.3490619587713906,
|
234 |
+
"tokens_seen": 3001942016
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.1,
|
238 |
+
"learning_rate": 9.063250600480385e-05,
|
239 |
+
"loss": 1.1534,
|
240 |
+
"theoretical_loss": 3.348950530246418,
|
241 |
+
"tokens_seen": 3003252736
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.11,
|
245 |
+
"learning_rate": 9.023218574859889e-05,
|
246 |
+
"loss": 1.1928,
|
247 |
+
"theoretical_loss": 3.348839163951921,
|
248 |
+
"tokens_seen": 3004563456
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.11,
|
252 |
+
"learning_rate": 8.983186549239391e-05,
|
253 |
+
"loss": 1.1678,
|
254 |
+
"theoretical_loss": 3.3487278598260195,
|
255 |
+
"tokens_seen": 3005874176
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.11,
|
259 |
+
"learning_rate": 8.943154523618895e-05,
|
260 |
+
"loss": 1.1477,
|
261 |
+
"theoretical_loss": 3.348616617806923,
|
262 |
+
"tokens_seen": 3007184896
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.12,
|
266 |
+
"learning_rate": 8.903122497998399e-05,
|
267 |
+
"loss": 1.1773,
|
268 |
+
"theoretical_loss": 3.34850543783293,
|
269 |
+
"tokens_seen": 3008495616
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.12,
|
273 |
+
"learning_rate": 8.863090472377903e-05,
|
274 |
+
"loss": 1.185,
|
275 |
+
"theoretical_loss": 3.3483943198424253,
|
276 |
+
"tokens_seen": 3009806336
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.12,
|
280 |
+
"objective/train/docs_used": 1008334,
|
281 |
+
"objective/train/instantaneous_batch_size": 8,
|
282 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
283 |
+
"objective/train/original_loss": 1.3460177183151245,
|
284 |
+
"objective/train/theoretical_loss": 3.348366550022507,
|
285 |
+
"objective/train/tokens_used": 61418976,
|
286 |
+
"theoretical_loss": 3.348366550022507,
|
287 |
+
"tokens_seen": 3010134016
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 0.13,
|
291 |
+
"learning_rate": 8.823058446757406e-05,
|
292 |
+
"loss": 1.1798,
|
293 |
+
"theoretical_loss": 3.348283263773882,
|
294 |
+
"tokens_seen": 3011117056
|
295 |
+
},
|
296 |
+
{
|
297 |
+
"epoch": 0.13,
|
298 |
+
"learning_rate": 8.78302642113691e-05,
|
299 |
+
"loss": 1.1794,
|
300 |
+
"theoretical_loss": 3.3481722695658633,
|
301 |
+
"tokens_seen": 3012427776
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.13,
|
305 |
+
"learning_rate": 8.742994395516414e-05,
|
306 |
+
"loss": 1.1759,
|
307 |
+
"theoretical_loss": 3.3480613371570165,
|
308 |
+
"tokens_seen": 3013738496
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.14,
|
312 |
+
"learning_rate": 8.702962369895917e-05,
|
313 |
+
"loss": 1.1839,
|
314 |
+
"theoretical_loss": 3.347950466486079,
|
315 |
+
"tokens_seen": 3015049216
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.14,
|
319 |
+
"learning_rate": 8.66293034427542e-05,
|
320 |
+
"loss": 1.1996,
|
321 |
+
"theoretical_loss": 3.3478396574918747,
|
322 |
+
"tokens_seen": 3016359936
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.15,
|
326 |
+
"learning_rate": 8.622898318654924e-05,
|
327 |
+
"loss": 1.1897,
|
328 |
+
"theoretical_loss": 3.347728910113315,
|
329 |
+
"tokens_seen": 3017670656
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.15,
|
333 |
+
"objective/train/docs_used": 1011213,
|
334 |
+
"objective/train/instantaneous_batch_size": 8,
|
335 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
336 |
+
"objective/train/original_loss": 1.227089524269104,
|
337 |
+
"objective/train/theoretical_loss": 3.3476735595108353,
|
338 |
+
"objective/train/tokens_used": 69610976,
|
339 |
+
"theoretical_loss": 3.3476735595108353,
|
340 |
+
"tokens_seen": 3018326016
|
341 |
+
},
|
342 |
+
{
|
343 |
+
"epoch": 0.15,
|
344 |
+
"learning_rate": 8.582866293034428e-05,
|
345 |
+
"loss": 1.1741,
|
346 |
+
"theoretical_loss": 3.3476182242893975,
|
347 |
+
"tokens_seen": 3018981376
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 0.15,
|
351 |
+
"learning_rate": 8.542834267413932e-05,
|
352 |
+
"loss": 1.191,
|
353 |
+
"theoretical_loss": 3.3475075999592074,
|
354 |
+
"tokens_seen": 3020292096
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.16,
|
358 |
+
"learning_rate": 8.502802241793434e-05,
|
359 |
+
"loss": 1.1924,
|
360 |
+
"theoretical_loss": 3.347397037061916,
|
361 |
+
"tokens_seen": 3021602816
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.16,
|
365 |
+
"learning_rate": 8.462770216172938e-05,
|
366 |
+
"loss": 1.188,
|
367 |
+
"theoretical_loss": 3.3472865355367825,
|
368 |
+
"tokens_seen": 3022913536
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 0.17,
|
372 |
+
"learning_rate": 8.422738190552442e-05,
|
373 |
+
"loss": 1.1754,
|
374 |
+
"theoretical_loss": 3.3471760953231504,
|
375 |
+
"tokens_seen": 3024224256
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.17,
|
379 |
+
"learning_rate": 8.382706164931946e-05,
|
380 |
+
"loss": 1.2086,
|
381 |
+
"theoretical_loss": 3.3470657163604507,
|
382 |
+
"tokens_seen": 3025534976
|
383 |
+
},
|
384 |
+
{
|
385 |
+
"epoch": 0.17,
|
386 |
+
"objective/train/docs_used": 1013697,
|
387 |
+
"objective/train/instantaneous_batch_size": 8,
|
388 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
389 |
+
"objective/train/original_loss": 1.1135369539260864,
|
390 |
+
"objective/train/theoretical_loss": 3.3469829722979627,
|
391 |
+
"objective/train/tokens_used": 77802976,
|
392 |
+
"theoretical_loss": 3.3469829722979627,
|
393 |
+
"tokens_seen": 3026518016
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.17,
|
397 |
+
"learning_rate": 8.34267413931145e-05,
|
398 |
+
"loss": 1.1969,
|
399 |
+
"theoretical_loss": 3.3469553985882,
|
400 |
+
"tokens_seen": 3026845696
|
401 |
+
},
|
402 |
+
{
|
403 |
+
"epoch": 0.18,
|
404 |
+
"learning_rate": 8.302642113690953e-05,
|
405 |
+
"loss": 1.2176,
|
406 |
+
"theoretical_loss": 3.3468451419460017,
|
407 |
+
"tokens_seen": 3028156416
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.18,
|
411 |
+
"learning_rate": 8.262610088070457e-05,
|
412 |
+
"loss": 1.188,
|
413 |
+
"theoretical_loss": 3.3467349463735436,
|
414 |
+
"tokens_seen": 3029467136
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 0.19,
|
418 |
+
"learning_rate": 8.22257806244996e-05,
|
419 |
+
"loss": 1.1834,
|
420 |
+
"theoretical_loss": 3.3466248118105995,
|
421 |
+
"tokens_seen": 3030777856
|
422 |
+
},
|
423 |
+
{
|
424 |
+
"epoch": 0.19,
|
425 |
+
"learning_rate": 8.182546036829464e-05,
|
426 |
+
"loss": 1.1977,
|
427 |
+
"theoretical_loss": 3.3465147381970293,
|
428 |
+
"tokens_seen": 3032088576
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 0.19,
|
432 |
+
"learning_rate": 8.142514011208967e-05,
|
433 |
+
"loss": 1.1889,
|
434 |
+
"theoretical_loss": 3.346404725472777,
|
435 |
+
"tokens_seen": 3033399296
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.2,
|
439 |
+
"objective/train/docs_used": 1016482,
|
440 |
+
"objective/train/instantaneous_batch_size": 8,
|
441 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
442 |
+
"objective/train/original_loss": 1.4041112661361694,
|
443 |
+
"objective/train/theoretical_loss": 3.3462947735778727,
|
444 |
+
"objective/train/tokens_used": 85994976,
|
445 |
+
"theoretical_loss": 3.3462947735778727,
|
446 |
+
"tokens_seen": 3034710016
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 0.2,
|
450 |
+
"learning_rate": 8.102481985588471e-05,
|
451 |
+
"loss": 1.1983,
|
452 |
+
"theoretical_loss": 3.3462947735778727,
|
453 |
+
"tokens_seen": 3034710016
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.2,
|
457 |
+
"learning_rate": 8.062449959967975e-05,
|
458 |
+
"loss": 1.1694,
|
459 |
+
"theoretical_loss": 3.346184882452431,
|
460 |
+
"tokens_seen": 3036020736
|
461 |
+
},
|
462 |
+
{
|
463 |
+
"epoch": 0.21,
|
464 |
+
"learning_rate": 8.022417934347479e-05,
|
465 |
+
"loss": 1.1871,
|
466 |
+
"theoretical_loss": 3.3460750520366513,
|
467 |
+
"tokens_seen": 3037331456
|
468 |
+
},
|
469 |
+
{
|
470 |
+
"epoch": 0.21,
|
471 |
+
"learning_rate": 7.982385908726981e-05,
|
472 |
+
"loss": 1.1833,
|
473 |
+
"theoretical_loss": 3.3459652822708175,
|
474 |
+
"tokens_seen": 3038642176
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.21,
|
478 |
+
"learning_rate": 7.942353883106487e-05,
|
479 |
+
"loss": 1.1831,
|
480 |
+
"theoretical_loss": 3.345855573095298,
|
481 |
+
"tokens_seen": 3039952896
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 0.22,
|
485 |
+
"learning_rate": 7.902321857485989e-05,
|
486 |
+
"loss": 1.1877,
|
487 |
+
"theoretical_loss": 3.3457459244505463,
|
488 |
+
"tokens_seen": 3041263616
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 0.22,
|
492 |
+
"learning_rate": 7.862289831865493e-05,
|
493 |
+
"loss": 1.2048,
|
494 |
+
"theoretical_loss": 3.3456363362770984,
|
495 |
+
"tokens_seen": 3042574336
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.22,
|
499 |
+
"objective/train/docs_used": 1019410,
|
500 |
+
"objective/train/instantaneous_batch_size": 8,
|
501 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
502 |
+
"objective/train/original_loss": 1.1971296072006226,
|
503 |
+
"objective/train/theoretical_loss": 3.3456089486754172,
|
504 |
+
"objective/train/tokens_used": 94186976,
|
505 |
+
"theoretical_loss": 3.3456089486754172,
|
506 |
+
"tokens_seen": 3042902016
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.23,
|
510 |
+
"learning_rate": 7.822257806244996e-05,
|
511 |
+
"loss": 1.1685,
|
512 |
+
"theoretical_loss": 3.345526808515576,
|
513 |
+
"tokens_seen": 3043885056
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.23,
|
517 |
+
"learning_rate": 7.782225780624501e-05,
|
518 |
+
"loss": 1.1907,
|
519 |
+
"theoretical_loss": 3.3454173411066828,
|
520 |
+
"tokens_seen": 3045195776
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.23,
|
524 |
+
"learning_rate": 7.742193755004003e-05,
|
525 |
+
"loss": 1.1949,
|
526 |
+
"theoretical_loss": 3.345307933991209,
|
527 |
+
"tokens_seen": 3046506496
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.24,
|
531 |
+
"learning_rate": 7.702161729383507e-05,
|
532 |
+
"loss": 1.1959,
|
533 |
+
"theoretical_loss": 3.3451985871100254,
|
534 |
+
"tokens_seen": 3047817216
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.24,
|
538 |
+
"learning_rate": 7.662129703763011e-05,
|
539 |
+
"loss": 1.1728,
|
540 |
+
"theoretical_loss": 3.345089300404087,
|
541 |
+
"tokens_seen": 3049127936
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.25,
|
545 |
+
"learning_rate": 7.622097678142515e-05,
|
546 |
+
"loss": 1.1995,
|
547 |
+
"theoretical_loss": 3.344980073814434,
|
548 |
+
"tokens_seen": 3050438656
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"debugging/Compilability": 0.0,
|
552 |
+
"debugging/distinct-1-grams": 0.7613636363636364,
|
553 |
+
"debugging/entropy-1-grams": 3.9967058025744,
|
554 |
+
"debugging/length": 568.0,
|
555 |
+
"debugging/num_segments": 1,
|
556 |
+
"debugging/score": 0.045774647887323945,
|
557 |
+
"debugging/score_std": 0.0,
|
558 |
+
"epoch": 0.25,
|
559 |
+
"objective/train/docs_used": 1022217,
|
560 |
+
"objective/train/instantaneous_batch_size": 8,
|
561 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
562 |
+
"objective/train/original_loss": 0.8801804780960083,
|
563 |
+
"objective/train/theoretical_loss": 3.3449254830448116,
|
564 |
+
"objective/train/tokens_used": 102378976,
|
565 |
+
"theoretical_loss": 3.3449254830448116,
|
566 |
+
"tokens_seen": 3051094016
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 0.25,
|
570 |
+
"learning_rate": 7.582065652522018e-05,
|
571 |
+
"loss": 1.1905,
|
572 |
+
"theoretical_loss": 3.3448709072821874,
|
573 |
+
"tokens_seen": 3051749376
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.25,
|
577 |
+
"learning_rate": 7.542033626901522e-05,
|
578 |
+
"loss": 1.1939,
|
579 |
+
"theoretical_loss": 3.344761800748551,
|
580 |
+
"tokens_seen": 3053060096
|
581 |
+
},
|
582 |
+
{
|
583 |
+
"epoch": 0.26,
|
584 |
+
"learning_rate": 7.502001601281026e-05,
|
585 |
+
"loss": 1.1901,
|
586 |
+
"theoretical_loss": 3.3446527541548132,
|
587 |
+
"tokens_seen": 3054370816
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.26,
|
591 |
+
"learning_rate": 7.46196957566053e-05,
|
592 |
+
"loss": 1.2002,
|
593 |
+
"theoretical_loss": 3.3445437674423437,
|
594 |
+
"tokens_seen": 3055681536
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.27,
|
598 |
+
"learning_rate": 7.421937550040032e-05,
|
599 |
+
"loss": 1.2223,
|
600 |
+
"theoretical_loss": 3.3444348405525948,
|
601 |
+
"tokens_seen": 3056992256
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 0.27,
|
605 |
+
"learning_rate": 7.381905524419536e-05,
|
606 |
+
"loss": 1.2028,
|
607 |
+
"theoretical_loss": 3.3443259734271016,
|
608 |
+
"tokens_seen": 3058302976
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 0.27,
|
612 |
+
"objective/train/docs_used": 1025165,
|
613 |
+
"objective/train/instantaneous_batch_size": 8,
|
614 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
615 |
+
"objective/train/original_loss": 1.2416154146194458,
|
616 |
+
"objective/train/theoretical_loss": 3.3442443622681504,
|
617 |
+
"objective/train/tokens_used": 110570976,
|
618 |
+
"theoretical_loss": 3.3442443622681504,
|
619 |
+
"tokens_seen": 3059286016
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.27,
|
623 |
+
"learning_rate": 7.34187349879904e-05,
|
624 |
+
"loss": 1.1917,
|
625 |
+
"theoretical_loss": 3.344217166007481,
|
626 |
+
"tokens_seen": 3059613696
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.28,
|
630 |
+
"learning_rate": 7.301841473178544e-05,
|
631 |
+
"loss": 1.1963,
|
632 |
+
"theoretical_loss": 3.344108418235432,
|
633 |
+
"tokens_seen": 3060924416
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.28,
|
637 |
+
"learning_rate": 7.261809447558046e-05,
|
638 |
+
"loss": 1.1737,
|
639 |
+
"theoretical_loss": 3.343999730052735,
|
640 |
+
"tokens_seen": 3062235136
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.29,
|
644 |
+
"learning_rate": 7.22177742193755e-05,
|
645 |
+
"loss": 1.1848,
|
646 |
+
"theoretical_loss": 3.343891101401253,
|
647 |
+
"tokens_seen": 3063545856
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.29,
|
651 |
+
"learning_rate": 7.181745396317054e-05,
|
652 |
+
"loss": 1.1799,
|
653 |
+
"theoretical_loss": 3.3437825322229298,
|
654 |
+
"tokens_seen": 3064856576
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.29,
|
658 |
+
"learning_rate": 7.141713370696558e-05,
|
659 |
+
"loss": 1.1818,
|
660 |
+
"theoretical_loss": 3.3436740224597914,
|
661 |
+
"tokens_seen": 3066167296
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.3,
|
665 |
+
"objective/train/docs_used": 1028068,
|
666 |
+
"objective/train/instantaneous_batch_size": 8,
|
667 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
668 |
+
"objective/train/original_loss": 1.3919180631637573,
|
669 |
+
"objective/train/theoretical_loss": 3.3435655720539446,
|
670 |
+
"objective/train/tokens_used": 118762976,
|
671 |
+
"theoretical_loss": 3.3435655720539446,
|
672 |
+
"tokens_seen": 3067478016
|
673 |
+
},
|
674 |
+
{
|
675 |
+
"epoch": 0.3,
|
676 |
+
"learning_rate": 7.101681345076061e-05,
|
677 |
+
"loss": 1.1999,
|
678 |
+
"theoretical_loss": 3.3435655720539446,
|
679 |
+
"tokens_seen": 3067478016
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.3,
|
683 |
+
"learning_rate": 7.061649319455565e-05,
|
684 |
+
"loss": 1.1951,
|
685 |
+
"theoretical_loss": 3.343457180947577,
|
686 |
+
"tokens_seen": 3068788736
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 0.31,
|
690 |
+
"learning_rate": 7.021617293835069e-05,
|
691 |
+
"loss": 1.1921,
|
692 |
+
"theoretical_loss": 3.343348849082957,
|
693 |
+
"tokens_seen": 3070099456
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.31,
|
697 |
+
"learning_rate": 6.981585268214572e-05,
|
698 |
+
"loss": 1.1899,
|
699 |
+
"theoretical_loss": 3.3432405764024353,
|
700 |
+
"tokens_seen": 3071410176
|
701 |
+
},
|
702 |
+
{
|
703 |
+
"epoch": 0.31,
|
704 |
+
"learning_rate": 6.941553242594075e-05,
|
705 |
+
"loss": 1.1887,
|
706 |
+
"theoretical_loss": 3.3431323628484417,
|
707 |
+
"tokens_seen": 3072720896
|
708 |
+
},
|
709 |
+
{
|
710 |
+
"epoch": 0.32,
|
711 |
+
"learning_rate": 6.901521216973579e-05,
|
712 |
+
"loss": 1.1913,
|
713 |
+
"theoretical_loss": 3.343024208363487,
|
714 |
+
"tokens_seen": 3074031616
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.32,
|
718 |
+
"learning_rate": 6.861489191353083e-05,
|
719 |
+
"loss": 1.1801,
|
720 |
+
"theoretical_loss": 3.3429161128901628,
|
721 |
+
"tokens_seen": 3075342336
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.32,
|
725 |
+
"objective/train/docs_used": 1031046,
|
726 |
+
"objective/train/instantaneous_batch_size": 8,
|
727 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
728 |
+
"objective/train/original_loss": 1.355250597000122,
|
729 |
+
"objective/train/theoretical_loss": 3.342889098235679,
|
730 |
+
"objective/train/tokens_used": 126954976,
|
731 |
+
"theoretical_loss": 3.342889098235679,
|
732 |
+
"tokens_seen": 3075670016
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 0.32,
|
736 |
+
"learning_rate": 6.821457165732587e-05,
|
737 |
+
"loss": 1.186,
|
738 |
+
"theoretical_loss": 3.3428080763711403,
|
739 |
+
"tokens_seen": 3076653056
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.33,
|
743 |
+
"learning_rate": 6.78142514011209e-05,
|
744 |
+
"loss": 1.1817,
|
745 |
+
"theoretical_loss": 3.3427000987491717,
|
746 |
+
"tokens_seen": 3077963776
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.33,
|
750 |
+
"learning_rate": 6.741393114491593e-05,
|
751 |
+
"loss": 1.1953,
|
752 |
+
"theoretical_loss": 3.342592179967088,
|
753 |
+
"tokens_seen": 3079274496
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.34,
|
757 |
+
"learning_rate": 6.701361088871097e-05,
|
758 |
+
"loss": 1.1954,
|
759 |
+
"theoretical_loss": 3.3424843199678005,
|
760 |
+
"tokens_seen": 3080585216
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.34,
|
764 |
+
"learning_rate": 6.661329063250601e-05,
|
765 |
+
"loss": 1.1849,
|
766 |
+
"theoretical_loss": 3.3423765186943006,
|
767 |
+
"tokens_seen": 3081895936
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 0.34,
|
771 |
+
"learning_rate": 6.621297037630104e-05,
|
772 |
+
"loss": 1.1971,
|
773 |
+
"theoretical_loss": 3.3422687760896586,
|
774 |
+
"tokens_seen": 3083206656
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 0.35,
|
778 |
+
"objective/train/docs_used": 1033433,
|
779 |
+
"objective/train/instantaneous_batch_size": 8,
|
780 |
+
"objective/train/instantaneous_microbatch_size": 8192,
|
781 |
+
"objective/train/original_loss": 1.3183742761611938,
|
782 |
+
"objective/train/theoretical_loss": 3.3422149267703904,
|
783 |
+
"objective/train/tokens_used": 135146976,
|
784 |
+
"theoretical_loss": 3.3422149267703904,
|
785 |
+
"tokens_seen": 3083862016
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 0.35,
|
789 |
+
"learning_rate": 6.581265012009608e-05,
|
790 |
+
"loss": 1.1814,
|
791 |
+
"theoretical_loss": 3.342161092097024,
|
792 |
+
"tokens_seen": 3084517376
|
793 |
+
},
|
794 |
+
{
|
795 |
+
"epoch": 0.35,
|
796 |
+
"learning_rate": 6.541232986389112e-05,
|
797 |
+
"loss": 1.1732,
|
798 |
+
"theoretical_loss": 3.342053466659626,
|
799 |
+
"tokens_seen": 3085828096
|
800 |
+
},
|
801 |
+
{
|
802 |
+
"epoch": 0.36,
|
803 |
+
"learning_rate": 6.501200960768615e-05,
|
804 |
+
"loss": 1.1698,
|
805 |
+
"theoretical_loss": 3.3419458997207734,
|
806 |
+
"tokens_seen": 3087138816
|
807 |
+
}
|
808 |
+
],
|
809 |
+
"max_steps": 2524,
|
810 |
+
"num_train_epochs": 9223372036854775807,
|
811 |
+
"total_flos": 6.02016841728e+16,
|
812 |
+
"trial_name": null,
|
813 |
+
"trial_params": null
|
814 |
+
}
|
checkpoint-900/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62606ef86d425c76460a848b984d348a02cd2616fd10f4951e23cea6e71b3d5c
|
3 |
+
size 3375
|
checkpoint-900/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 456676457
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ccd1efde0a73e749877469d15e844a6b8370f27762a46a7395cbca1bcb69c73
|
3 |
size 456676457
|